This paper addresses the containment control issue in high-order nonlinear multi-agent systems (MASs) under denial of service (DoS) attacks. First, a neural network-based switching observer with adaptive mechanism is developed to reconstruct unmeasurable agent states under intermittent DoS-induced communication disruptions, establishing new theoretical pathways for directed network topologies. Second, a command-filtered backstepping control framework is proposed to circumvent the inherent complexity explosion in traditional recursive designs by eliminating redundant differentiations of virtual control laws. Ultimately, a distributed adaptive neural network containment control (DANNCC) scheme is established, ensuring all follower agents asymptotically converge into the convex hull spanned by multiple leaders. Furthermore, systematic stability analysis with constructed Lyapunov functions yields boundedness of all closed-loop signals in the system. Moreover, the containment errors can be asymptotically driven to an arbitrarily small magnitude through systematic parameter adjustment. The developed approach’s operational efficacy and real-world applicability are validated through comprehensive simulations across heterogeneous attack scenarios, demonstrating strict adherence to convergence requirements without control performance degradation.

For multi-agent systems (MASs) subject to input delays and time-varying state constraints, this work proposes a predefined-time consensus control scheme. The state constraints, input delays, and additional delays caused by event triggering are obstacles that affect the control performance and practicality of MASs. To achieve predefined-time consensus while strictly satisfying the state constraints, the scheme first tackles two key obstacles: input delays and unknown system nonlinearities. Specifically, the Pade approximation technique is adopted to reconstruct the input delay into a new error variable, and then adaptive neural networks (NNs) are used to compensate for both the delay-induced error and the unknown nonlinearities. Meanwhile, by leveraging an asymmetric barrier Lyapunov function (ABLF) and a predefined-time stability framework, the scheme fundamentally ensures that the MASs achieve state consensus within a predefined time and strictly satisfy the time-varying state constraints. Further, to solve the inherent communication burden problem in networked MASs and improve the applicability of the scheme, a dynamic event-triggered mechanism (DETM) is designed as a complementary optimization: based on a dynamically evolving internal variable, the DETM only triggers communication when necessary, thereby significantly reducing the number of control updates and inter-agent data transmissions. At the same time, the scheme eliminates the requirement for agents to continuously monitor their states to determine triggering conditions, further enhancing the practicality of the scheme. Simulation results verify the effectiveness of the proposed method.

This paper investigates predefined time quantized feedback control for nonlinear large-scale systems with state quantization. To address the discontinuities in virtual control signals caused by quantized states and unmeasured states, a command filter is introduced to smooth control inputs, while a state observer based on fuzzy logic systems (FLSs) is designed to estimate unmeasured states. Furthermore, the hyperbolic tangent function is employed to eliminate control singularities. A quantized-state-based controller is developed using the backstepping technique and predefined time stability criteria, which introduces challenges in stability analysis. To tackle these challenges, a novel stability analysis framework is proposed by integrating predefined time Lyapunov stability theory and Lagrange’s Mean Value Theorem. Finally, simulations are conducted to demonstrate the effectiveness of the proposed control strategy.

This article investigates the problem of the prescribed-time consensus control for nonlinear multiagent systems under performance constraints and actuator attacks. First, a distributed output-feedback-based prescribed-time estimator is designed for each follower. This enables the followers to precisely estimate the leader’s signal. Subsequently, to achieve the control objective with prescribed performance, a prescribed-time performance function is constructed. Integrated with an asymmetric barrier Lyapunov function approach, it guarantees that asymmetric time-varying performance constraints are satisfied within the preset time. Furthermore, fuzzy logic systems are adopted to approximate unknown nonlinear functions. In addition, to handle the issue of unknown control directions, Nussbaum gain functions are incorporated into the controller design. The proposed controller ensures the boundedness of all signals in the closed-loop system, while simultaneously guaranteeing that the tracking errors remain within the prescribed performance bounds. Finally, simulation results demonstrate the advantages and effectiveness of the proposed method.

This article studies the distributed observer-based event-triggered (ET) optimal control problem for nonlinear multiagent systems (NMASs) over jointly connected digraphs. Since agents cannot get the leader under jointly connected digraphs, a distributed observer is constructed to estimate the unknown leader. At the same time, to enhance the efficiency of communication resources utilization between agents, an ET communication mechanism is developed to schedule the agent communication. Subsequently, neural networks (NNs) are adopted to handle the unknown nonlinearities, and an NN state observer is established to reconstruct the unmeasurable states. By utilizing the backstepping technique and adaptive dynamic programming theory, a distributed observer-based ET optimal control algorithm is developed, in which a critic network is designed with a proposed weight updating law to estimate the cost function. It is proven that the presented ET optimal control approach ensures that all signals of NMASs are uniformly ultimately bounded (UUB), and the cost function is minimized. At last, the theoretical results are applied to marine surface vehicles (MSVs) to validate the efficiency of the developed optimal control strategy.

This paper introduces SparseTSF, a novel and extremely lightweight method for Long-term Time Series Forecasting (LTSF), designed to address the challenges of modeling complex temporal dependencies over extended horizons with minimal computational resources. At the heart of SparseTSF lies the Cross-Period Sparse Forecasting technique, which simplifies the forecasting task by downsampling the original sequences to focus on cross-period trend prediction. This technique not only significantly reduces model complexity and the number of parameters but also serves as an implicit regularization mechanism that enhances the model's robustness, achieving an optimal balance between performance and efficiency. Based on this technique, SparseTSF uses fewer than 1,000 parameters to achieve competitive performance compared to state-of-the-art methods, with evident advantages under longer look-back windows (e.g., 720) that allow the model to better exploit inherent periodicity and trend information. Furthermore, SparseTSF showcases remarkable generalization capabilities, making it well-suited for scenarios with limited computational resources, small samples, or low-quality data.

Node classification is a fundamental task in hypergraph learning. Existing methods generally assume that there are a few labeled nodes given in advance. However, in a newly formed hypergraph, collecting label information is challenging and costly in practice. Besides, current approaches mainly exploit the local consistency relationship, i.e., direct neighborhood information, while ignoring the high-order consistency relationship, i.e., high-order proximity information, limiting the discrimination of the latent representations. To address these issues, we propose leveraging knowledge from an auxiliary well-labeled hypergraph (source hypergraph) to assist the learning tasks in the target hypergraph, thus studying the cross-hypergraph node classification problem. Specifically, we propose a model, namely Local and High-order Consistency Coding and Adaptation (LHCCA), which learns both discriminative and transferable node representations. On the one hand, for each hypergraph, by exploiting the local and high-order consistency relationships, LHCCA obtains two kinds of representations, which are then coded by an attention mechanism to achieve a unified representation. On the other hand, the coded source and target node representations are enforced adversarial domain adaptation and contrastive learning to discover transferable features for adaptation. Furthermore, we derive theoretical analyses to establish desirable properties of the proposed model. Extensive experiments on several real-world datasets are conducted, and the promising results demonstrate the effectiveness of the proposed model.

Due to the prohibitive costs and lack of portability associated with full-channel devices, portable miniature EEG devices with only a few electrodes (few-channel) are more suitable for widespread deployment in consumer applications. However, affective state analysis with few-channel EEG presents a significant challenge, as these devices only capture signals from partial brain regions. Existing approaches designed for few-channel devices do not adequately account for the critical role of whole-brain connectivity and suffer from the impact of noise in affective state analysis. To address the challenges, we propose an efficient affective state analysis Network which reconstructs EEG from Few-channel To Full-channel (F2FNet). This method aims to leverage knowledge from full-channel EEG and exclude irrelevant information to enhance the affective state analysis performance of few-channel EEG based on whole-brain connectivity patterns. To ensure information validity and consistency during the reconstruction process, we introduce mechanisms for information compression and control. Additionally, we perform alignment of compressed features within the VAD emotional space to ensure that the model's understanding and extraction of emotional features conform to the definitions of affective theories. Extensive experiments on basic emotion recognition and depression detection demonstrate the efficacy of the proposed method.

Multimodal Sentiment Analysis (MSA) plays a vital role in understanding emotional content from social media and multimedia data. However, existing methods often rely on large-scale labeled datasets, leading to high annotation costs and poor adaptability. They also suffer from modality imbalance and suboptimal feature fusion. To address these issues, we propose MapleNet—a Multimodal Affect Perception framework enhanced by Large Language Models. MapleNet integrates a prototype-guided fusion strategy and a dynamic modality balancing mechanism to improve alignment and collaboration between text and image features. Specifically, a shared-space encoder combined with prompt optimization ensures semantic consistency across modalities. Within the prototype learning framework, the model dynamically adjusts modalityspecific learning by aligning features with class prototypes, thus mitigating imbalance and uncovering complementary affective cues. In addition, MapleNet employs a similaritybased sample retrieval module to construct contextual prompts, enriching sentiment understanding in few-shot settings. Experiments on six benchmark datasets show that MapleNet consistently outperforms state-of-the-art methods, especially under few-shot conditions, achieving superior accuracy and generalization. The relevant code is available at https://github.com/YFanLuo/MapleNet.

This paper presents a cooperative control framework for dual-arm robots that integrates vision-language models (VLMs) with online reinforcement learning (RL) to enhance autonomy and adaptability in complex manipulation tasks. The proposed framework adopts a hierarchical architecture: at the top level, the VLM interprets natural language instructions and visual image to generate task plans; at the middle level, an online RL module refines manipulation policies and ensures adaptive decision-making under environmental uncertainty; and at the bottom level, compliant control based on trajectory planning and impedance regulation enables safe and robust execution. In the feedback, YOLOv5 is used to detect the object, GraspNet is used to obtain the optimal grasp pose, and CLIP (Contrastive Language-Image Pre-Training) is used to judge whether task is completed. Simulations and real-world experiments validate the effectiveness of the proposed method. The dual-arm robot successfully performed various cooperative tasks such as grasping, bottle-cap unscrewing, water pouring, and box carrying, achieving an increase in the task success rate from 43% to 100% with online adaptive learning and training. These results demonstrate that the proposed framework effectively bridges high-level reasoning with low-level control, providing a scalable solution for future applications in service robotics, industrial automation, and human-robot collaboration.

How to guarantee the effective planning trajectory of autonomous driving for mobile vehicles is the main challenge. This study provides a multi-constraint trajectory planning technique to construct safe, smooth, and dynamically viable trajectories in complicated situations. Firstly, a two-stage sampling path generation algorithm is proposed to obtain a cluster of candidate paths, considering road geometry, vehicle kinematics, and static obstacle avoidance constraints. Secondly, a cost function is designed to select the optimal path based on smoothness, consistency with the reference path, and distance to obstacles. Finally, a speed planning model is developed using convex optimization to allocate speed profiles for each path point with dynamic constraints, including time efficiency, boundary conditions, and dynamic obstacle avoidance. Experimental results on mobile vehicles demonstrate the effectiveness and stability of the proposed trajectory planning algorithm in real-world environments and its ability to handle various typical driving scenarios. The success rate of trajectory planning in the experiments was 94%, with an average planning time of 37.3ms.

Soft sensor modeling is the task of using measurable variables to predict target ones, which may involve nonlinearity and temporally dynamics. Despite significant progress, there is a relative lack of research on soft sensor-oriented Quantum Long Short-Term Memory (QLSTM) design and application. As a novel quantum soft sensor approach, a temporally-preserving QLSTM (TP-QLSTM) is proposed by integrating with multiscale attention mechanisms. Specifically, a temporally-preserving-based adaptive variational quantum circuit is designed by establishing entanglement across temporal inputs to improve the temporally learning capability of QLSTM. Moreover, multiscale attention mechanisms are designed in the input and output parts of TP-QLSTM to learn nonlinearities and temporal dynamics from different feature dimensions and temporal ones, as well as from historical hidden states and temporal outputs. In addition, a referential attention-based autoregressive forecasting strategy is proposed as output module of TP-QLSTM to predict the target results. Experiments on two soft sensor cases demonstrate the effectiveness and practicality of our method. Note to Practitioners—In industrial processes, soft sensors are critical for achieving comprehensive state awareness and predictive management. However, practical soft sensors often struggle with complex nonlinear and time-dependent relationships in dynamic processes. As an innovative attempt to enhance soft sensing from a quantum algorithm perspective, we propose a TP-QLSTM by integrating multiscale attention mechanisms. Through designing adaptive quantum circuits that preserve temporal correlations and incorporating multiscale attention mechanisms, our method effectively captures multiscale dynamics and nonlinearities from process data. This enables accurate and robust predictions of key variables in industrial settings. Experiments on real cases confirm that our method achieves high prediction accuracy while maintaining low computational latency—with an average inference time of less than 0.6 ms per sample. A current limitation is that the quantum algorithm is implemented using simulated quantum circuits, which restricts the full exploitation of quantum parallelism. Future work will focus on deploying the model to hardware platforms that support real quantum circuit computation, thus enabling efficient training and inference.

Consensus in fractional-order multi-agent systems (MASs) with time delays has attracted considerable research interest in recent years. Numerous existing findings rely heavily on the stability theory of fractional-order delay systems. In these findings, however, certain stability rates remain inestimable, while others lack rigorous estimation. This paper develops enhanced Mittag-Leffler stability criterion for fractional-order systems incorporating infinite distributed and discrete delays, which provides precise characterizations of convergence rates and establish a pioneering framework for fractional-order stability analysis. Moreover, this work proposes a novel dual-mode adaptive event-triggered strategy (DMAETS) to optimize limited communication resources and enhance network utilization efficiency. The DMAETS framework features time-varying event-triggering thresholds and adaptive control gains that dynamically adjust based on real-time system states. Through innovative DMAETS-based controller designs (internal/boundary configurations) and the proposed stability criterion, the fractional-order coupled PDE-ODE MASs (FCPOMASs) achieve consensus, with corresponding consensus conditions derived as linear matrix inequalities (LMIs). Finally, two simulation examples are presented to illustrate the validity of the theoretical analysis and the feasibility of the control schemes.

The issue of adaptive neural bipartite containment of multi-agent systems (MASs) with deferred state constraints under event-triggered communication (ETC) is explored in this article. Firstly, a dynamic ETC mechanism that only transmits local leader reference signals among follower agents is proposed, effectively reducing communication overhead. Subsequently, state constraints are addressed under entirely unknown initial states by employing a shift function and a nonlinear state-dependent function. Finally, an adaptive neural bipartite containment controller is designed to decrease computational burden, with each controller incorporating a single adaptive law, and the proposed virtual and actual controllers do not involve feasibility conditions and partial derivative terms. It is demonstrated that all closed-loop signals remain bounded, the bipartite containment error converges to a user-defined interval, and state constraints are not breached. The efficacy of the proposed scheme is further verified through two simulation examples.

Fatigued driving is a major societal risk factor in the road safety system, affecting the efficiency of the entire transportation network and public safety. Fatigue detection methods based on multimodal physiological signals can objectively reflect a driver’s neurocognitive state, offering higher monitoring reliability. However, existing methods face two main challenges: 1) the high cost of annotating high-quality physiological signals leads to challenges in learning with limited data; and 2) the signal-to-noise ratio of multimodal physiological signals is variable, leading to imbalances in the confidence in the decision between modalities. To address these issues, this article proposes the meta-evidential dual-stream network (MEDS-Net), which integrates a meta-learning framework with evidential deep learning to establish a solution for driver fatigue detection for the first time. Specifically, MEDS-Net employs a dual-stream evidence generation network to extract heterogeneous features from multimodal physiological signals and uses a Dirichlet distribution to quantify cognitive uncertainty for each modality. Additionally, MEDS-Net introduces a meta-learning framework to enhance the model’s ability to handle data scarcity through the design of task simulation mechanisms and a two-layer optimization strategy. Extensive experiments on the SEED-VIG dataset demonstrate that MEDS-Net outperforms current state-of-the-art methods in terms of effectiveness and generalizability. Furthermore, MEDS-Net can precisely quantify the importance of global features in explaining modal contributions and average activation patterns.

In this article, the distributed surrounding control problem is addressed for the linear multi-agent systems, in which a hierarchical strategy framework is constructed consisting of optimal target assignment and game-driven surrounding control. Aiming at fulfilling the multiple targets surrounding task with high efficiency and balanced mission load, an optimal target assignment mechanism is developed with the assistance of the cross entropy method (CEM) and twin delayed deep deterministic policy gradient algorithm (TD3), where an evaluation function related to the arrival time from each agent to capture the target is proposed. Considering the high degree of autonomy of the targets, a surrounding control protocol driven by the dynamic graph game is proposed afterward. To find the equilibrium solution of the pursuit-escape game, the coupled Hamilton–Jacobi–Bellman (HJB) equation is solved by a delicately designed model based value iteration algorithm, whose stability is demonstrated by the rigorous theoretical analysis. Finally, we undertake numerical experiments to ascertain the efficacy of the introduced game-driven surrounding control strategy.

Multimodal cross-subject emotion recognition has gained increasing attention due to the complementary nature of physiological and behavioral signals, such as electroencephalography (EEG) and eye movements (EM). However, modality heterogeneity and subject variability remain major obstacles, especially in few-shot scenarios. Existing approaches often combine increasingly complex architectures with unsupervised domain adaptation to address these issues, but they typically require large amounts of unlabeled target data and struggle to generalize when samples are scarce. To overcome these limitations, this article proposes a unified multimodal representation learning (UMRL) framework with prototype calibration under the few-shot paradigm. Specifically, the UMRL strategy is designed from an optimization perspective rather than architectural complexity to learn a compact and discriminative joint representation. It encourages compact representations by jointly minimizing cross-modal inconsistency and penalizing modality dominance, ensuring that complementary cues are effectively integrated in a unified embedding space. Nevertheless, emotional prototypes constructed from a few labeled samples of novel subjects are often unstable and sensitive to subject-dependent variability. To further alleviate this issue, this article introduces an emotional prototype calibration mechanism that aligns novel emotional prototypes with semantic priors learned from seen subjects to suppress noise and improve cross-subject generalization. Extensive experiments on multiple multimodal emotion recognition benchmarks with EEG and EM demonstrate that the proposed framework achieves state-of-the-art performance and delivers consistent robustness under few-shot conditions.

Imbalanced exposure of Chinese characters during pretraining often leads to inconsistent performance across downstream tasks. This problem stems primarily from the randomness of the masking strategy and is further aggravated by the semantic granularity mismatch between Chinese and English. To address these challenges, we propose the seeking attribute in language (SAIL) scheme to enhance Chinese language modeling. SAIL constructs a hierarchical attribute pyramid grounded in the rich semantics of Chinese and comprises three core tasks: masked language modeling (MLM), masked character restructuring (MCR), and masked quality evaluation (MQE). MQE employs a Chinese association graph to dynamically assess the quality of randomly masked samples and uses this assessment as a supervisory signal during pretraining. MCR integrates character-level structural information to mitigate the imbalance caused by varying word frequencies. To facilitate multilevel semantic interaction, MLM not only models word-level semantics but also bridges the character-level structural semantics from MCR and the sentence-level semantics from MQE. In turn, MCR and MQE reevaluate and enhance the performance of MLM from the lower and upper layers of the hierarchical pyramid, respectively. Experimental results across a range of Chinese language understanding tasks, including multidomain comprehension, fine-grained entity recognition, and diverse text classification, demonstrate that our model consistently achieves superior average performance. These findings show the generalization capability and transferability of the SAIL framework in modeling complex Chinese semantics.

Major depressive disorder (MDD) is typically accompanied by varying topological dynamics across brain network modularity due to the influence of time-variant and subject-specific factors. Current works primarily characterize the electroencephalograms (EEG) topological relationships based on prior predefined brain regions. However, this predefined strategy cannot dynamically fit to different individuals, which may affect the adaptability of unseen individual for depression detection. This article proposes an adaptive cluster-oriented modularity graph neural network (ACM-GNN) to enhance the adaptability of individual topological interaction for depression detection. Specifically, a cluster-oriented modularity construction (CMC) module dynamically clusters EEG channels into different brain regions based on channel-pairs contrastive learning. It can adaptively construct brain modularity to fit different individual instances. Furthermore, a modularity graph interaction learning (MGIL) module performs multilayer graph information interaction between EEG globality and modularity levels. In this way, more powerful hierarchical information can be integrated by further aggregating representations at different levels. Experiments on two public datasets, MODMA and PRED+CT, demonstrate that the proposed method outperforms the state-of-the-art EEG depression detection methods. Finally, investigations on brain activities reveal the importance of dynamic modular relations for depression detection.

Nighttime flare removal is challenging due to the difficulty of acquiring real-world paired data. Existing methods, trained on synthetic pipelines, often struggle to generalize to real-world scenarios. A key limitation of these pipelines is their focus on single-flare scenes, whereas real-world conditions frequently involve more complex cases, such as multi-flare and composite flare scenarios, which are difficult to simulate effectively. This discrepancy significantly hampers model performance in practical applications. Through detailed analysis, we uncover a fundamental characteristic of flare degradation: regardless of whether the scene is synthetic single-flare, real-world single-flare, or multi-flare, the degradation information exhibits a similar distribution across frequency subbands—predominantly concentrated in the low-frequency region, with a minor presence in the high-frequency region. Notably, the severity of the glare effect correlates with an even stronger concentration in the low-frequency domain. This finding suggests that targeted frequency modeling can bridge the gap between synthetic and real-world domains, forming a principled approach to improving generalization. Building on this insight, we propose the Scale-Aware Frequency-Adaptive Guidance Network for Nighttime Flare Removal (SAFAformer), which integrates a Frequency-Adaptive Guidance Module (FAGM) and a Scale-Aware Transformer Block (SATB) to leverage frequency-domain properties during training. Extensive experiments demonstrate that SAFAformer achieves state-of-the-art performance in flare removal compared to existing methods. Our code and pre-trained models are available on GitHub for validation.

Partial label learning (PLL) is a paradigm in weakly supervised learning. The goal is to identify the ground-truth label from a set of candidate labels associated with a given sample. However, due to the ambiguity of labels, improving the accuracy of ground-truth label recognition is a challenge. In this paper, we propose an innovative training framework PLMR, for solving the PLL problem. Given the specificity of the PLL problem, its data is rich in valid information but significantly noisy. To overcome the problem, PLMR incorporates mutual information (MI) theory to mine the potential information of candidate labels and data features to distinguish between positive and negative sample pairs. This operation is to effectively utilize the raw data information in PLL and reduce the class conflict problem. In this way, the discriminative power of representation is improved according to the positive and negative pair selection strategy. At the same time, PLMR introduces cluster centers to optimize subsequent tasks, combining data augmentation samples with the K-means cross-attention mechanism to refine the optimized cluster centers. This is to improve the ability of the clustering centre to accurately represent the class information, thus improving the overall quality of the clusters. Further, through the ambiguity marking correction mechanism, weights are calculated based on the association between cluster centers and sample representations to guide model training. Experimental results show that PLMR demonstrates excellent classification performance on multiple datasets, verifying its effectiveness and sophistication.

The geometry of road surfaces plays a critical role in the performance of autonomous driving systems. Consequently, achieving accurate and efficient road surface reconstruction (RSR) is of paramount importance. However, due to the inherent effects of perspective projection, distant regions often exhibit geometric distortions and a long-tailed distribution, which pose significant challenges to existing reconstruction methods. To address these issues, we propose a novel framework, termed Direction-aware Pseudo-Stereo Road Reconstruction Network (DPS-Net), which incorporates two lightweight and plug-and-play modules: Direction-Aware Feature Enhancement (DFE) module and Pseudo-Stereo Fusion (PSF) module. The DFE module is designed to enhance the perception of sparse and geometry-invariant features by integrating directional context, while the PSF module captures global dependencies across spatial and channel dimensions through pseudo-stereo fusion. Both modules are constructed with an emphasis on maintaining low computational complexity. We conducted extensive experiments on the public RSRD dataset to evaluate the effectiveness and superiority of our proposed method. The code is available at https://github.com/yidanyi/DPS-Net.

Scene Text Image Super-Resolution (STISR) methods improve recognition accuracy by refining text regions locally. However, most existing approaches are limited by short-range dependencies, hindering the modeling of long-range semantic relationships between characters, which reduces their effectiveness in complex text scenes. Moreover, current methods are predominantly evaluated on synthetic datasets, which do not adequately capture real-world challenges such as diverse text styles, complex backgrounds, and spatial distortions. To address these limitations, we propose a Dual-Guided Visual and Semantic (DGVS) framework. This innovative framework utilizes a recognizer-driven attention mechanism to decouple character sequences, effectively distinguishing text from background noise. Additionally, we incorporate a state-space model to establish global semantic reasoning links, enhancing the comprehension of contextual relationships within text images. Furthermore, we construct Real-World Text (RealWT), a novel real-world benchmark dataset that integrates diverse data sources, including online images and multi-device captures. This dataset incorporates factors like device variations, resolution differences, and degradation, offering a more realistic simulation of real-world conditions. It enables models to learn degradation patterns that closely mirror practical applications, offering a standardized benchmark for evaluating STISR performance. Extensive experiments demonstrate that our method outperforms existing approaches, as validated by evaluations on TextZoom and RealWT. Our dataset and code are available on https://github.com/yoursmith/sde-DGVS.

Image outpainting, a challenging generative task, has advanced significantly with the introduction of text-to-image diffusion models (DM). Despite these advances, DM-based methods frequently encounter the phenomenon in which one modal takes precedence over another, causing the image to be over-guided. Current research relies on manual hyperparameters to achieve bimodal balance. To reduce reliance, Prompt Libra is proposed to automatically balance bimodal prompts during inference and enhance extrapolated images. Given the variation of bimodal cross-attention during DM denoising, we create an adaptive bimodal attention module via attention maps. Furthermore, we design a classifier-free guidance computation based on masked images to improve the semantic control of the masked part and enhance the quality of images. Finally, we propose a semantic transformer to address the problem of quality degradation caused by incomplete prompts. It extracts limited semantics from the source images, which is suitable for scenarios lacking text prompts. Experimental results demonstrate that our method generates images that achieve the state-of-the-art effect on several image quality evaluation metrics while maintaining the image and text prompts in balance.

3D object detection has achieved significant progress in outdoor LiDAR point clouds, however, the inherent irregularity and varying sparsity distribution of point occupancy present a key challenge. Existing transformer-based 3D detectors often treat all tokens within the attention window as equally important, regardless of varying sparsity, which not only fails to address the disparities between the varying beam densities but also results in increased memory and computational costs. In this work, we propose an adaptive structure-aware cascaded transformer (ASCFormer) that dynamically captures density-insensitive multiscale structure features to model long-range dependencies via cascaded learning. Our ASCFormer detector includes an adaptive structure-aware token learning module that embeds voxel-level foreground probability and grid-level local density into the grid tokens to enhance structural perception capability. Moreover, we integrate these factors to compute significance scores, which are then utilized in inverse transform sampling to select a subset of multiscale tokens with varying receptive field sizes. To improve the training convergence of the window-based transformer in 3D voxel space, we employ cascaded learning via cross-stage attention to enhance the feature representation capability and refine the localization precision of 3D bounding boxes. This design of structure-aware reweighting effectively enhances the cascade paradigm, making to more adaptable to the varying sparsity distribution of point clouds. Extensive experiments on the KITTI and Waymo Open datasets demonstrate that the proposed ASCFormer detector achieves exceptional performance compared with state-of-the-art 3D object detection methods. The source code is publicly available at https://github.com/Xinglong-Li1/ASCFormer.

This article introduces a study on the secure control of nonlinear multiagent systems (NMASs) that are vulnerable to denial-of-service (DoS) attacks, with the added complexity that system states are not directly observable. To tackle the inherent nonlinear dynamics, a fuzzy logic systems (FLSs) framework is employed as a modeling tool. Faced with the obstacle of inaccessible system states and outputs during DoS attacks, this article introduces a switching-type secure estimator. This advanced estimator is designed to accurately reconstruct the system state from sporadic output data, ensuring continuous monitoring despite interruptions. By seamlessly integrating the switching-type secure estimator with the average dwell time (ADT) method and leveraging Lyapunov stability theory, the authors have developed an output-feedback secure control strategy. This strategy not only maintains system stability but also guarantees the convergence of consensus tracking errors, even in the presence of unknown states and ongoing DoS attacks. Finally, in order to prove the effectiveness of the consensus security controller, the practicability and reliability of the proposed control scheme are verified by simulation experiments.

This study develops a reinforcement learning (RL)-based control framework with guaranteed predefined performance for nonlinear switched interconnected systems. This approach effectively addresses challenges arising from unmeasurable states and group average dwell time switching mechanisms, allowing both convergence time and accuracy to be preset via parameter configuration. First, the system equations are reconstructed to target nonlinear and interconnected terms, which are then approximated using neural networks (NNs). Additionally, an NNs-based switching state observer is designed to estimate the unmeasurable states. Second, within the backstepping synthesis framework, a distributed optimal controller is designed by integrating a performance transformation function into the cost function, with the resulting control law approximated via an identifier-actor-critic architecture. Furthermore, the group average dwell time-based stability analysis is generalized to address the optimal control challenges inherent in nonlinear switched interconnected systems. Compared with existing studies, this approach demonstrates enhanced extensibility and practicality for real-world applications. Finally, two simulation examples verify the effectiveness and superiority of the proposed method over state-of-the-art alternatives.

Effective policy optimization in multiagent reinforcement learning (MARL) necessitates extensive exploration of high-dimensional state-action spaces. However, such exploration may not only trigger unsafe states but also compromise system stability, posing significant challenges for deployment in safety-critical systems. To address this challenge, this article proposes a safety-stability layer that integrates robust control barrier functions (RCBFs) and input-to-state stable control Lyapunov functions (ISS-CLFs) for multiagent systems operating in unknown environments with uncertain dynamics. Furthermore, by integrating safety-stability constraints with a MARL framework, during the training phase, we exclusively focus on goal-reaching objectives to expand the policy network's exploration space, while in the deployment phase, policy outputs are filtered through a real-time safety-stability layer. In addition, an event-triggered mechanism for action compensation calculation is designed based on safety condition assessments to conserve computational resources. Finally, the effectiveness of the proposed method is validated through simulation experiments in dynamic multiunicycle environments. The results demonstrate that our approach not only ensures strict adherence to safety constraints but also significantly enhances the task execution efficiency of multiagent systems.

The study of the nicotine addiction mechanism is of great significance in both nicotine withdrawal and brain science. The detection of addiction-related brain circuitry using functional magnetic resonance imaging (fMRI) is a critical step in studying this mechanism. However, it is challenging to accurately estimate addiction-related brain circuitry due to the low signal-to-noise ratio of fMRI and the issue of small sample size. In this work, a graph diffusion-infused adversarial learning (GDAL) network is proposed to capture addiction-related brain circuitry accurately. The GDAL combines the graph convolution method with the diffusion model so that the model can fully capture addiction-related brain circuitry in non-Euclidean space. The diffusion reconstruction module (DRM) is designed to reconstruct the brain network to maintain the consistency of sample distribution in the latent space so that the brain circuitry can be detected more accurately. The proposed model reduces the search space by improving the conditional guidance of the DRM so that the model can better understand the latent distribution for the issue of small sample size. The experimental results demonstrate the effectiveness of the proposed method.

Federated learning (FL) enables multiple clients to learn collaboratively in a distributed way, allowing for privacy protection. However, the real-world nonindependent and identically distributed (non-IID) data will lead to client drift, which degrades the performance of FL. Interestingly, we find that the logit difference between the local and global models increases as the model is continuously updated, which is the primary factor behind performance degradation. This is mainly due to catastrophic forgetting caused by non-IID data between clients. To alleviate this problem, we propose a new algorithm, named FedCSD, a class-prototype similarity distillation in a federated framework to align the logits of local and global models. FedCSD does not simply transfer global knowledge to local clients, as an insufficiently trained global model cannot provide reliable knowledge, i.e., class similarity information, and its wrong soft labels will mislead the optimization of local models. Concretely, FedCSD leverages the similarity between local logits and the global prototype to refine the global logits, thereby enhancing its class similarity information. Furthermore, FedCSD adopts an adaptive mask to filter out the terrible soft labels of the global models, thereby preventing them from misleading local optimization. Extensive experiments demonstrate the superiority of our method over the state-of-the-art FL approaches in various non-IID settings. Code is publicly available at https://github.com/IAMJackYan/FedCSD.

Semi-supervised multiview clustering has garnered considerable attention for its ability to integrate multiview data with limited labeled information. However, existing methods predominantly focus on labeled samples, neglecting abundant unlabeled data, which leads to suboptimal utilization of available prior knowledge. Moreover, existing pairwise constraint propagation-based methods typically follow a two-stage procedure, resulting in unstable clustering outcomes. To address these limitations, we introduce a unified framework that integrates multiview subspace clustering with pairwise constraint propagation, proposing a tensor-based semi-supervised multiview subspace clustering (TSMSC) method with pairwise constraint propagation. Specifically, each view's subspace representation is decomposed into a consensus part and private parts, enabling the consensus representation to better approximate the low-rank structure. Then, a pairwise constraint propagation method is developed for multiview data, which propagates the initial pairwise constraint through a low-rank matrix completion approach. Finally, observing that the ideal multiview consensus representation and the propagated pairwise constraint matrix share the same low-rank structure, we naturally construct them into a third-order tensor to capture high-order correlations via tensor low-rank representation, allowing for joint optimization within a unified framework. Extensive experiments on eight real-world datasets demonstrate the superiority of our method over state-of-the-art approaches.

This paper presents a fuzzy event-driven optimal quantized feedback control strategy for unmanned surface vehicle (USV) trajectory tracking under multiple practical constraints, including limited maritime communication resources, model uncertainties, thruster saturation, and positioning constraints. To address the communication limitation, a signal quantization and event-driven mechanism is introduced, where the thruster quantization is characterized by a linear analytical model. A fuzzy adaptive observer (FAO) is used to estimate the quantized feedback signal, while a finite-time disturbance observer (FDO) estimates environmental disturbances. Additionally, a dynamic auxiliary system compensates for thruster saturation effects. A logarithmic barrier function-based constraint mechanism ensures positioning variables remain within predefined safety bounds. The adaptive quantized feedback controller is designed using the backstepping framework and dynamic surface control techniques, with an optimal compensation term based on adaptive dynamic programming (ADP) to minimize the cost function of the tracking error system. The proposed control strategy ensures that all closed-loop signals remain within specified limits. Simulation results confirm the effectiveness and advantages of this approach.

Sparse Principal Component Analysis (SPCA) is a powerful technique for dimensionality reduction and feature extraction in high-dimensional data, with applications spanning various fields such as computer vision, pattern recognition, and data mining. However, the computational intensity of SPCA presents a significant challenge, necessitating the development of efficient and robust algorithms. In this paper, we shed light on the SPCA problem and uncover intriguing structures that enable us to design an efficient algorithm, which we have named SPCA_ACC. Firstly, we identify a separable structure in this problem, which prompts us to draw on the Variable Projection (VP) strategy and generalize it to separable nonlinear problem in Stiefel manifold. This strategy projects out part of the parameters to obtain a reduced problems, allowing the SPCA_ACC algorithm to optimize in a lower-dimensional parameter space. Secondly, we resolve the coupling between different parameters of the SPCA problem in the optimization process on a fixed coordinate-sparsity manifold, which opens the way to the use of second-order Riemannian accelerated VP strategy. Moreover, we systematically analyze the advantages of using VP to solve the SPCA problem from a theoretical perspective, and confirm the local quadratic convergence of our algorithm. Numerical experiments on datasets of different sizes and types demonstrate that our method achieves rapid convergence and significantly reduces computational costs.

Face Super-Resolution (FSR), aiming to improve the quality of Low-Resolution (LR) facial images, has been greatly propelled by the deep learning techniques. However, existing approaches, whether based on Convolutional Neural Networks (CNNs) or Transformers, are either inherently damaging facial structures limited by their architectures or failing to capture essential multi-scale textures due to the rigid receptive fields. To address these concerns, we propose a novel dual-domain feature interaction method called Spatial-frequency Multi-scale feature Learning Network (SMLNet) for FSR by employing a dual-branch architecture. Specifically, the frequency branch captures high-quality global structures and fine high-frequency details, while the spatial branch operates complementarily to preserve fine-grained local texture patterns. Moreover, we further introduce a Multi-scale Spatial-frequency feature Interaction Module (MSIM), which combines a Multi-scale Feature Extraction Block (MFEB) and a Spatial-Frequency feature Interaction Module (SFIM) to interact and aggregate multi-level complementary features from the dual branches. Extensive quantitative experiments and qualitative analyses across multiple datasets, together with evaluations on real-world images, demonstrate that the proposed SMLNet significantly outperforms other state-of-the-art methods.

Cross-modal retrieval facilitates more flexible information access and improves semantic understanding across different modalities. However, traditional cross-modal retrieval models rely on well-aligned datasets, which are often labor-intensive and costly to obtain. In real-world applications, data inevitably includes mismatched pairs, and these semantically inconsistent pairs can significantly degrade retrieval performance. Previous approaches have assumed ideal loss value distributions to optimize models for accurate semantic matching through soft-label estimation. However, the absence of hierarchical semantic correlation learning limits the effectiveness of these models in scenarios involving partial mismatches. To address these challenges, we propose Exploring Hierarchical Cross-Modal Correlation Consistency (EH3C) for cross-modal retrieval under partially mismatched conditions. Specifically, our approach first leverages neighborhood correlation distributions among samples to optimize cross-modal alignment, without assuming ideal distributions. This allows for the measurement of soft matching degrees between cross-modal data pairs and facilitates the effective learning of their positive correlations. Next, we enhance inter-class separability through intra-modal correlation learning by exploiting negative correlations between reliable negative sample pairs, thus enabling a more comprehensive exploration of cross-modal correlations. Finally, to assess the effectiveness and robustness of our approach, we conducted extensive experiments on three benchmark datasets. The results demonstrate that the proposed EH3C significantly improves cross-modal retrieval performance in scenarios involving partial mismatches.

Deep convolutional neural networks can use hierarchical information to progressively extract structural information to recover high-quality images. However, preserving the effectiveness of the obtained structural information is important in image super-resolution. In this paper, we propose a cosine network for image super-resolution (CSRNet) by improving a network architecture and optimizing the training strategy. To extract complementary homologous structural information, odd and even heterogeneous blocks are designed to enlarge the architectural differences and improve the performance of image super-resolution. Combining linear and non-linear structural information can overcome the drawback of homologous information and enhance the robustness of the obtained structural information in image super-resolution. Taking into account the local minimum of gradient descent, a cosine annealing mechanism is used to optimize the training procedure by performing warm restarts and adjusting the learning rate. Experimental results illustrate that the proposed CSRNet is competitive with state-of-the-art methods in image super-resolution.

Cuffless blood pressure (BP) measurement has gained increasing attention due to the global aging population. Data-driven approaches have shown high accuracy for cuffless BP estimation. However, when deployed on wearable devices, they often suffer from being time-consuming because a complete retraining process is required if the training samples or structure need to be expanded. To address these issues, we propose a Knowledge-embedded Bi-incremental Broad Learning System (BpBLS) for cuffless BP estimation using biosignals collected from wearable devices.With a flat structure, BpBLS can be updated flexibly and quickly without retraining the entire model for incremental biosignals and/or training samples. In BpBLS, a novel Pulse Pressure Regularization (PPR) method is proposed to comprehensively capture the BP knowledge, which is then embedded into the system to enhance its accuracy. Experimental results demonstrate that BpBLS exhibits superior performance in both estimation accuracy and computational efficiency compared to the state-of-the-art approaches. For the CAS-BP dataset, the estimation error is 0.60 $\pm$ 8.44 for systolic BP (SBP) and 0.29 $\pm$ 6.45 for diastolic BP (DBP); while for the Aurora-BP dataset, the estimation error is -0.32 $\pm$ 8.46 mmHg for SBP and 0.05 $\pm$ 6.65 mmHg for DBP. More importantly, the training time for both datasets is less than ten seconds, and the computational efficiency is improved by an order of magnitude compared to traditional machine learning methods. Our work will serve as a novel flexible and lightweight framework for cuffless BP measurement.

Existing UAV vehicle-detection datasets, typically captured under static and uniform illumination, fail to adequately represent the variable lighting conditions, dense traffic, and frequent occlusions observed in real-world transportation hubs. To bridge this gap, a new dataset, UAV-HubSurveillance, is introduced to capture complex vehicle interactions across urban transportation nodes under diverse environmental scenarios. Although UAV-HubSurveillance provides rich and multidimensional interaction data, it still suffers from severe occlusions and adverse weather conditions that hinder detection and identification accuracy. To address these limitations, a novel vehicle detection framework, termed bidirectional interactive multi-scale aggregation-yolo (BIMSA-YOLO), is proposed, which integrates bidirectional feature interaction with adaptive multi-scale aggregation to enhance detection robustness. First, the bidirectional shallow fusion module (BSFM) facilitates cross-resolution information exchange through a lightweight gating strategy, preserving fine-grained details of small objects. Second, the interactive deep fusion module (IDFM) reinforces contextual coherence via attention-guided cross-level semantic fusion. Third, the multi-scale adaptive aggregation module (MSAAM) dynamically aligns and integrates multi-scale features to improve robustness against scale variation. Extensive experiments conducted on the UAV-HubSurveillance dataset demonstrate that BIMSA-YOLO significantly enhances detection performance under dynamic, occluded, and adverse-weather conditions. Specifically, the proposed model achieves an mAP0.5of 63.2%, surpassing the baseline by 5.3 percentage points. Furthermore, BIMSA-YOLO also exhibits strong generalization capabilities on VisDrone and CARPK datasets. Our code and dataset are available athttps://github.com/yikuizhai/BIMSA-YOLO

Anchor-based multi-view clustering has gained increasing attention for its efficiency in approximating similarity structures and scaling to large datasets. To reduce the burden of manual hyper-parameter tuning, recent studies have introduced parameter-free extensions. However, existing methods still face critical challenges: anchors are typically fixed after initialization, limiting adaptability to heterogeneous data; enforcing a shared anchor set across views suppresses view-specific diversity; and heuristic or self-weighted fusion strategies often lack explicit cross-view alignment, resulting in structural inconsistencies. To address these issues, we propose a Parameter-Free Multi-view Clustering framework with Adaptive Anchors for Large-scale Data (FPMCAA). Unlike existing approaches that decouple anchor construction and graph fusion, FPMCAA integrates adaptive anchor learning, anchor graph construction, and explicit cross-view alignment within a unified optimization model. Anchors are iteratively refined to capture complex distributions, while view-specific graphs are aligned toward a consensus structure without sacrificing inherent diversity. The framework avoids manual hyperparameter tuning and achieves linear computational complexity through efficient alternating optimization. Extensive experiments on benchmark datasets demonstrate that FPMCAA consistently outperforms state-of-the-art methods in clustering performance, robustness, and scalability. The source code of FPMCAA is available athttps://github.com/Xuchen2020/FPMCAA.

Active learning can effectively reduce the cost of labeling while enhancing model classification performance. However, prior studies have indicated that imbalanced class distributions adversely impact active learning, leading to diminished model effectiveness. Existing approaches to unbalanced active learning often neglect the multi-class imbalance problem and suffer from low performance and high time consumption. To address these issues, this paper introduces a hybrid active learning with online weighted broad learning system (HAL-OWBLS). Its main advantages include: (1) We optimize the initial labeled instance selection through an approximate query strategy to avoid the cold-start problem and introduce a sample selection strategy based on double uncertainty to enhance the rationality of active learning iterations. (2) A weighted broad learning system (WBLS) is chosen as the classifier, and an improved weighting strategy is adopted for multi-class imbalanced data. (3) We theoretically derive an efficient online updating model for WBLS, which reduces the time cost of active learning iterations by using only newly labeled samples for fast updating. The proposed HAL-OWBLS algorithm has better performance and robustness compared with existing related algorithms on various multi-class imbalanced data sets.

The processing of continuous data streams in non-stationary environments has gained increasing attention. However, supervised online learning is often limited by label availability. Furthermore, it is crucial to develop a stable and high-performance online method in non-stationary environments. To tackle these issues, we propose a dynamic chunk-based active learning framework (DCAL). This framework includes a dynamic dual-stage query strategy and an enhanced active learning model. Specifically, the proposed query strategy, referred to as DyDQS, evaluates sample value comprehensively by considering local density, uncertainty, and dynamic imbalance ratio. This approach selects samples that are both representative and uncertain, while also enhancing the likelihood of selecting minority class samples. Additionally, we introduce an enhanced active learning model, named eBLS-W, which is based on the broad learning system (BLS). We redesign the update rule of BLS and equip it with a kernel mapping to improve its robustness and performance, enabling it to better handle non-stationary environments. The effectiveness of the DyDQS, eBLS-W, and DCAL was validated through experiments on synthetic datasets with drift and real-world datasets. The results demonstrate that our approach outperforms other advanced methods in terms of robustness and accuracy.

Active learning can significantly reduce the cost of labeling instances while improving model performance. However, similar to other traditional algorithms, active learning encounters the problem of class imbalance and delivers sub-optimal performance. Additionally, existing approaches suffer from poor performance and are time-consuming. To address these issues, we propose an Actively Incrementally Weighted Broad Learning System (AI-WBLS). Firstly, we introduce an active learning framework based on the weighted broad learning system, which employs a double uncertainty sample selection strategy to enhance the value and reasonableness of sample selection in each iteration of active learning. To further improve the model's adaptability during the iterative learning process, an adaptive weighting strategy is designed to adaptively modify the penalty weights according to the changes in the sample labels. Finally, an efficient incremental paradigm is developed to update the model with newly labelled samples instead of re-training, resulting in improved performance and efficiency. Extensive comparative experiments confirm that our approach outperforms other imbalanced active learning methods.

Multi-view clustering has exhibited exceptional performance by harnessing complementary information and extracting shared semantics across diverse views. However, existing methods still encounter substantial obstacles in exploiting high-quality consensus representation: (i) they typically lack effective guidance mechanisms under unsupervised conditions, leading to suboptimal representation learning, and (ii) they overlook the intrinsic cluster structure when forming sample pairs to align representation across views, conflicting with clustering objectives. To address these issues, we propose a contrastive-based method calledPseudo-LabelSimilarityGraph-driven Multi-ViewClustering (PSGVC). Specifically, to uncover the potential semantic relationships between samples, we construct a pseudo-label similarity graph based on the consensus representation. Then, we design a similarity graph-based contrastive loss, which utilizes the pseudo-label similarity graph as a global supervision signal to guide the optimization of cross-view embedded representation, thereby indirectly improving the quality of consensus representation. Additionally, we propose a weighted cluster-aware contrastive loss to align the consensus representation with view-specific representation. It leverages the cluster structure contained in the pseudo-label similarity graph to achieve cluster-level contrastive learning, further enhancing the quality of the consensus representation. Extensive experimental results show that our PSGVC achieves state-of-the-art clustering performance across multiple datasets.

The contactless interaction approach enables robots to identify object attributes via sensors and advanced perceptual technologies, eliminating the need for physical contact. This approach enhances interaction flexibility and safety while offering a richer, more intuitive human-robot experience. Current research focuses on cross-modal retrieval through non-contact feature extraction, enabling material attribute estimation and advancing object perception. However, existing cross-modal material retrieval methods overlook learning common attributes shared within the same material type. To address this, we propose Materials Perception with Self-paced Prototype contrastive Learning (MPSPL). First, attribute prototype contrastive learning extracts shared characteristics within the same material type, aggregates similar samples, and enhances the perception of deep model material attributes. Second, a self-paced learning strategy dynamically adjusts the contrastive loss temperature coefficient, guiding the model to discern discriminative features across materials and progressively recognize inherent attributes. Finally, extensive experiments validate our method under both known and unknown material category conditions. Experiments demonstrate the superiority of our proposed method over state-of-the-art approaches.

Broad learning system (BLS), as an innovative type of neural network, has demonstrated exceptional performance in regression tasks. Nonetheless, the majority of BLS methods, which rely on the least squares criterion, are highly sensitive to outliers and noisy data, resulting in reduced prediction accuracy. To improve the robustness of broad networks, a sparse Bayesian BLS via adaptive Lasso priors (AL-SBBLS) is proposed in this article to handle regression tasks with data contaminated by outliers and noise. Specifically, adaptive Lasso constraints are first applied to enhance the adaptive sparsity of output weights, which facilitates the automatic selection of highly correlated features. Subsequently, a multilayer Bayesian framework is constructed to provide an adaptive Lasso prior to the output weights, allowing the model for the adaptive learning of regularization factors and the estimation of probability distributions for output values, while further sparsifying the network. By selecting highly correlated features and estimating the probability distributions of output values, the impact of outliers and noise can be effectively mitigated. To effectively train the networks, corresponding optimization algorithms are designed for AL-SBLS and AL-SBBLS using the alternating direction method of multipliers (ADMMs) and variational Bayesian inference methods, respectively. The effectiveness and robustness of the proposed methods are validated through robust regression experiments on 14 real-world datasets and complex nonlinear data. Quantitative results demonstrate that the proposed AL-SBBLS achieves the best performance on most datasets, attaining the lowest average ranking of 1.44 in Friedman tests compared with 11 state-of-the-art BLS variants, which confirms its superior predictive accuracy and robustness. The resource code of AL-SBBLS proposed in this article is available at: https://github.com/taocheny/AL-SBBLS.

Federated Class Incremental Learning (FCIL) enables distributed clients to collaboratively train a global model based on their private sequential tasks without compromising data privacy. Currently, some FCIL methods have been proposed, and most are designed based on deep models. However, enabling these FCIL models to converge requires numerous communication rounds, significantly increasing communication costs. Recently, the Broad Learning System (BLS), an effective and efficient shallow model, was proposed and adapted for CIL tasks [i.e., BLS-Class Incremental Learning (CIL)]. BLS-CIL exhibits fast updates and high retainability. However, it requires prior knowledge of when new class data arrives and cannot be directly used in federated scenarios due to the global catastrophic forgetting in FCIL. Thus, an innovative Federated Class incremental learning method based on BLS (FedCBLS) is proposed, which extends BLS-CIL within the federated scenario and provides three advantages: 1) high accuracy from the local perspective, achieved by integrating BLS-CIL with a newly designed automatic decision-making (ADM) method to detect novel classes and learn them incrementally for local clients; 2) high accuracy from the global perspective, attained through the newly proposed local model refinement (LMR) and global model projection (GMP) methods, mitigating global catastrophic forgetting stemming from heterogeneous data across clients; and 3) extremely low communication costs due to the newly derived closed-form solutions without iterative optimization for both local and global models. Comprehensive experimental results show that our FedCBLS outperforms the state-of-the-art (SOTA) FCIL methods by up to 8.15%, while drastically reducing communication costs to 1% of SOTA’s. Our code is available athttps://github.com/dujie-szu/FedCBLS.git

Current mainstream multiagent reinforcement learning (MARL) algorithms primarily focus on acquiring the global maximum reward throughout the entire training process, from the initial to the final stage. Whereas directly pursuing the global maximum return tends to be inefficient, particularly in environments with sparse rewards or the large-scale multiagent system. To address these challenges, previous algorithms have been developed to maintain individual policies to guide global training. Nevertheless, these approaches generally neglect either efficiency or the potential for local collaboration at the early stage of training. In this article, we propose the role-policy enhanced global policy (RPEGP) algorithm, which integrates the concept of distinct roles within the actor–critic-based MARL framework. RPEGP simultaneously considers both collaborative behaviors among agents and efficient global policy training. Specifically, RPEGP exploits the similarities among agents to assign distinct roles, training role-policies and the global policy concurrently. Through the initialization and enhancement of the role-policies, the global policy is trained more efficiently and effectively. Empirical experiments are conducted in well-known cooperative multiagent environments, including StarCraft II micromanagement (SMAC) and multiagent particle environment (MPE). Experimental results demonstrate that RPEGP outperforms baseline algorithms across various evaluation metrics and training efficiency, confirming its ability to address complex cooperative tasks generically and efficiently.

Due to its exceptional feature representation capabilities and high computational efficiency, the broad learning system (BLS) has been widely employed in various classification tasks. Nevertheless, BLS encounters considerable challenges in semi-supervised classification tasks involving complex heterogeneous data, given the data’s high-dimensional and noisy nature, coupled with a limited number of available labeled samples. To tackle these challenges, this article introduces a semi-supervised BLS based on distance constraint regularization (DRBLS) and a semi-supervised broad ensemble method (E-DRBLS) for high-dimensional data. Specifically, we present a distance constraint regularization (DR) that utilizes both labeled and unlabeled data to derive an optimal projection matrix, which maximizes the preservation of the original data’s intrinsic distribution structure. DR is designed to minimize intraclass distance, maximize interclass distance, and minimize the distance between neighboring samples. To boost the performance of BLS in semi-supervised classification, we integrate DR and BLS to construct the semi-supervised classifier DRBLS. Finally, we propose a mixed dimensionality reduction space generation (MDRSG) method that generates multiple high-quality and diverse mixed dimensionality reduction spaces (MDRSs). Based on MDRS, an ensemble framework, E-DRBLS, is developed for semi-supervised classification tasks targeting high-dimensional data. Comprehensive experiments confirm the superiority of the proposed methods.

Hypersonic flight vehicles (HFVs) exhibit complex nonlinear dynamics and time-varying uncertainties, placing stringent demands on the adaptive learning capabilities of flight control systems. Meanwhile, the limited onboard communication and computational resources further require efficient resource utilization. To address these issues, this article proposes a dynamic event-triggered control (DETC) scheme based on actor–critic framework for HFVs, achieving synergistic optimization of control performance and resource conservation. First, an optimal event-triggered controller is developed within actor–critic framework to regulate the frequency of control input updates. A static event-triggered condition is formulated, and the stability of the closed-loop system is analyzed, with Zeno behavior eliminated, ensuring both stability and feasibility. Building on this, a dynamic variable is introduced, leading to a dynamic event-triggered condition that adaptively adjusts the trigger threshold based on real-time system states. Unlike static event-triggered mechanisms with fixed thresholds, this mechanism further optimizes the frequency of control input updates, achieving more efficient resource utilization while maintaining the desired control performance. Moreover, rigorous theoretical analysis demonstrates that the closed-loop system is stable and Zeno behavior is eliminated under the DETC scheme. Finally, the effectiveness of our proposed DETC scheme is verified through a simulation example.

The autoencoder (AE) is an efficient feature extraction tool that learns latent representations from raw data by minimizing the reconstruction loss. Building upon the AE architecture, deep clustering models are designed to jointly optimize the deep neural network and perform unsupervised clustering. However, existing methods directly impose the clustering objective on the latent features produced by the AE network, thereby neglecting the potential conflict between data clustering and data representation. Specifically, data clustering aims to enhance data aggregation, whereas data representation focuses on ensuring that latent features faithfully reflect the manifold structure of the raw data. To address this issue, this article proposes an innovative expanded deep embedding clustering (E-DEC) model, in which the AE network is employed to seek better latent representations, and a novel residual expansion module (REM) is integrated to construct an expanded feature space that better serves clustering tasks. Furthermore, adversarial learning between the soft cluster assignments and a prior one-hot distribution is adopted in lieu of the conventional Kullback–Leibler (KL) divergence, so as to enhance the discrimination of different clusters and avoid the degeneracy problem. Finally, an entropy regularization technique is incorporated to adaptively refine the affinity graph throughout the clustering process, thereby reducing the sensitivity of clustering performance to the initial affinity graph. Extensive experiments on real-world benchmark datasets demonstrate the superiority of the proposed model over state-of-the-art deep clustering methods.

This article addresses the adaptive optimal tracking control problem of nonlinear switched systems with unstable unmodeled dynamics. One challenge is how to find the optimal control strategy for a modeledx-dynamic system containing the unmodeled dynamics. Another challenge is how to achieve both optimality and stability of the closed-loop system with unstable dynamics. To this end, a novel solution combines adaptive dynamic programming and the small-gain approach, integrating integral penalties on control, states, and unstable dynamics via actor–critic learning and nonzero game mechanisms. The small-gain approach links closed-loop optimality and stability. For unstable dynamics, stability analysis employs a combined fast-slow switching strategy with gain allocation satisfying the small-gain theorem conditions; optimality analysis compensates unstable dynamics via adaptive parameter estimation and derives the optimal controller via a two-player game. Under small-gain conditions, the designed optimal controller ensures closed-loop output tracks reference signals with ultimately bounded errors. Finally, simulation results validate the proposed approach.

Current vision-language models (VLMs) understand complex vision-text tasks by extracting overall semantic information from largescale cross-modal associations.However, extracting from large-scale cross-modal associations often smooths out semantic details and requires large computations, limiting multimodal fine-grained understanding performance and efficiency.To address this issue, this paper proposes a detail-oriented prompt learning (DoPL) method for vision-language models to implement fine-grained multi-modal semantic alignment with merely 0.25M trainable parameters.According to the low-entropy information concentration theory, DoPL explores shared interest tokens from text-vision correlations and transforms them into alignment weights to enhance text prompt and vision prompt via detail-oriented prompt generation.It effectively guides the current frozen layer to extract fine-grained text-vision alignment cues.Furthermore, DoPL constructs detail-oriented prompt generation for each frozen layer to implement layer-by-layer localization of finegrained semantic alignment, achieving precise understanding in complex vision-text tasks.DoPL performs well in parameter-efficient finegrained semantic alignment with only 0.12% tunable parameters for vision-language models.The state-of-the-art results over the previous parameter-efficient fine-tuning methods and full fine-tuning approaches on six benchmarks demonstrate the effectiveness and efficiency of DoPL in complex multi-modal tasks.

Multi-modal sarcasm detection (MSD) identifies sarcasm and accurately understands users' real attitudes from text-image pairs.Most MSD researches explore the incongruity of textimage pairs as sarcasm information through consistency preference methods.However, these methods prioritize consistency over incongruity and blur incongruity information under their global feature aggregation mechanisms, leading to incongruity distortions and model misinterpretations.To address the above issues, this paper proposes a pioneering inconsistency preference method called incongruityaware tension field network (ITFNet) for multimodal sarcasm detection tasks.Specifically, ITFNet extracts effective text-image feature pairs in fact and sentiment perspectives.It then constructs a fact/sentiment tension field with discrepancy metrics to capture the contextual tone and polarized incongruity after the iterative learning of tension intensity, effectively highlighting incongruity information during such inconsistency preference learning.It further standardizes the polarized incongruity with reference to contextual tone to obtain standardized incongruity, effectively implementing instance standardization for unbiased decision-making in MSD.ITFNet performs well in extracting salient and standardized incongruity through an incongruity-aware tension field, significantly tackling incongruity distortions and cross-instance variance.Moreover, ITFNet achieves state-of-the-art performance surpassing LLaVA1.5-7B with only 17.3M trainable parameters, demonstrating its optimal performance-efficiency in multi-modal sarcasm detection tasks.

We propose a compressive yet effective mesh tokenization, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces. BPT compresses mesh sequences by employing block-wise indexing and patch aggregation, reducing their length by approximately 75% compared to the vanilla coordinate sequences. This compression milestone unlocks the potential to utilize mesh data with significantly more faces, thereby enhancing detail richness and improving generation robustness. Empowered with the BPT, we have built a foundation mesh generative model training on scaled mesh data to support flexible control for point clouds and images. Our model demonstrates the capability to generate meshes with intricate details and accurate topology, achieving SoTA performance on mesh generation and reaching the level for direct product usage.

Low-rank adaptation (LoRA) efficiently adapts LLMs to downstream tasks by decomposing LLMs' weight update into trainable low-rank matrices for fine-tuning.However, the random low-rank matrices may introduce massive taskirrelevant information, while their recomposed form suffers from limited representation spaces under low-rank operations.Such dense and choked adaptation in LoRA impairs the adaptation performance of LLMs on downstream tasks.To address these challenges, this paper proposes OHoRA, an orthogonal high-rank adaptation for parameter-efficient fine-tuning on LLMs.According to the information bottleneck theory, OHoRA decomposes LLMs' pre-trained weight matrices into orthogonal basis vectors via QR decomposition and splits them into two low-redundancy high-rank components to suppress task-irrelevant information.It then performs dynamic rank-elevated recomposition through Kronecker product to generate expansive task-tailored representation spaces, enabling precise LLM adaptation and enhanced generalization.OHoRA effectively operationalizes the information bottleneck theory to decompose LLMs' weight matrices into low-redundancy high-rank components and recompose them in rank-elevated manner for more task-tailored representation spaces and precise LLM adaptation.Empirical evaluation shows OHoRA's effectiveness by outperforming LoRA and its variants and achieving comparable performance to full fine-tuning with only 0.0371% trainable parameters.

Learning a generalized EEG representation under limited data and subject variability is a long-standing challenge. Most studies utilized data augmentation to extend the distribution of training data, which may hinder the diversity of augmented samples to cover more subject variability. In this paper, we propose a decomposed statistics-diverse feature augmentation (DSFA) framework for generalized EEG learning. The wavelet-based decomposed representation module decomposes signals into approximation and detail features, thus deriving semantics from original signals into approximation features to avoid over-transformation. The statistics-diverse feature augmentation module augments features to extend beyond the original feature space by manipulating the statistics of features. Extensive experiments on three datasets demonstrate that our approach achieves state-of-the-art performance in different classification tasks. Our repository is public at https://github.com/1940653868/DSFA.

Generating compact and sharply detailed 3D meshes poses a significant challenge for current 3D generative models. Different from extracting dense meshes from neural representation, some recent works try to model the native mesh distribution (i.e., a set of triangles), which generates more compact results as humans crafted. However, due to the complexity and variety of mesh topology, most of these methods are typically limited to generating meshes with simple geometry. In this paper, we introduce a generic and scalable mesh generation framework PivotMesh, which makes an initial attempt to extend the native mesh generation to large-scale datasets. We employ a transformer-based autoencoder to encode meshes into discrete tokens and decode them from face level to vertex level hierarchically. Subsequently, to model the complex typology, our model first learns to generate pivot vertices as coarse mesh representation and then generate the complete mesh tokens with the same auto-regressive Transformer. This reduces the difficulty compared with directly modeling the mesh distribution and further improves the model controllability. PivotMesh demonstrates its versatility by effectively learning from both small datasets like Shapenet, and large-scale datasets like Objaverse and Objaverse-xl. Extensive experiments indicate that PivotMesh can generate compact and sharp 3D meshes across various categories, highlighting its great potential for native mesh modeling.

In this work, we focus on enhancing the realism of face age transformation. Previous methods often relied on style transfer strategies or text-attention manipulation, which frequently result in undesirable artifacts or distorted facial defects. We propose DMDM, an age transformation method by Dual-Modal collaborative attention using Diffusion Models. Specifically, we introduce a collaborative text-image attention based editing method that balances age semantic control and visual harmony of generated face. To further refine fidelity, we propose the Softer Image Attention Injection Mechanism, which dynamically integrates image guidance. Additionally, we design a query image set to retrieve relevant images accroding to source face and other attributes for image guidance. Finally, Age-aware Face Restoration module is proposed to enhance high-frequency details according to age through a cascaded refinement pipeline. Extensive experiment demonstrates that DMDM achieves state-of-the-art performance, especially in visual quality.

Data-Knowledge dual-driven fashion can enhance model performance by complementing data-driven basis with expert knowledge. However, cutting-edge works in speech emotion recognition (SER) primarily evolve in data-driven training, failing to incorporate prior knowledge to form a closed loop and posing an obstacle to capture task-specific details when used independently. In this paper, we propose a Dual-Drive Broad Attentive Network (DiBAN) to achieve comprehensive emotional learning for SER. Specifically, the Dual-Drive Emotional Modeling module incorporates handcrafted extractor, pre-trained model and tailored base models, to conduct integral emotional modeling. Subsequently, the Multi-Model Attention-Aware Learning module is designed to refine the data-knowledge emotional disparities based on the attention-enhanced entropy loss. Finally, the Broad Adaptive Decision Fusion module performs adaptive fusion of emotional decisions from different drives. Extensive experiments on seven SER corpora demonstrate that DiBAN achieves significant improvements over the base models and outperforms comparative methods, fully showcasing its superiority.

It is challenging to employ a quadruped robot for real-time mapping and positioning in a large range of scenes. The significant vibration and instability of the quadruped robot during mobility, as well as the quantity of computation required to convey a wide variety of complex landscapes, result in unsatisfactory drawing construction accuracy and inefficient real-time performance. Therefore, we propose an accurate robust spinning LiDAR SLAM (ARS-SLAM) algorithm for a quadruped robot under the large-scale scene. The tightly coupled iterative Kalman filter in FAST-LIO2 is introduced into the front end of the cartographer framework to improve the accuracy and robustness of robot pose estimation. To reduce the computational complexity of the original cartographer framework, a pose threshold optimization algorithm was introduced to effectively remove redundant information from loop detection and improve computational efficiency and real-time performance. We tested the system's performance against the most advanced point-cloud-based methods, LIO-SAM and FAST-LIO2, on a large dataset of large science parks and underground parking lots, and the results show that the proposed system achieves the same or better accuracy and real-time performance.

Limited EEG data and subject variability pose significant challenges to the generalization of EEG-based emotion recognition. Most existing approaches augment EEG data using deterministic methods, often neglecting to ensure both diversity and fidelity in the generated samples. This oversight leads to insufficient domain diversity and emotional semantic information for a generalized model independent of individuals. This paper proposes an Information-Aware Graph Augmentation (InfoGA) framework for generalized EEG emotion recognition. The graph uncertainty augmentation module augments both the connectivity and features of EEG graphs by modeling statistical uncertainty, enabling the model to simulate domain shifts and improve generalizability against subject variability. Additionally, two information-aware constraints are introduced to ensure diversity and fidelity in the augmented EEG graphs. The graph diversity constraint enriches the emotional knowledge of the augmented graphs, while the graph fidelity constraint preserves their emotional semantic fidelity by integrating consistency learning with supervised learning. Extensive experiments on three public EEG emotion datasets, i.e., SEED, SEED-IV, and SEED-V, demonstrate that InfoGA achieves superior generalizability compared to baseline methods.

The redundancy of emotion-agnostic features and inter-subject variability significantly undermine the adaptability of EEG-based emotion recognition models. Previous studies have largely overlooked the influence of emotional responses at both intra- and inter-region levels across individuals. Consequently, the emotion-aware representations exhibit substantial redundancy and limited adaptability to cross-subject variability. To address these issues, this paper proposes a multi-graph orthogonal adaptation network (MoRa) that enhances the robustness of emotion-aware representations and mitigates inter-subject variability in cross-subject EEG emotion recognition. Specifically, the multi-graph module performs intra-region orthogonal decoupling of emotion-aware and agnostic information, reducing redundancy and enhancing consistency across dual emotional spaces. To reduce inter-region redundancy, the cross-region emotion refinement module integrates soft orthogonality and knowledge distillation to enhance collaborative information exchange across regions. Moreover, cross-subject experiments on the SEED and SEED-IV datasets demonstrate that the MoRa achieves state-of-the-art performance in EEG emotion recognition.

Major depressive disorder (MDD) is characterized by imbalanced connectivity between brain regions, rather than simply increased or decreased activity in a specific region. Current studies on depression detection using EEG predominantly utilize whole-brain signal (full-channel). However, due to the cost and convenience limitations of full-channel devices, portable miniaturized EEG devices with only a few electrodes (few-channel) are more suitable for widespread use in daily scenarios. Depression detection from few-channel EEG data is challenging because these devices can only capture EEG signals from a portion of the brain regions. To address the challenge, we propose a novel Convenience-Oriented Depression Detection model (CoDD). The model aims to enhance the performance of MDD detection using few-channel EEG by leveraging knowledge from full-channel EEG. Specifically, we capture prior whole-brain connectivity patterns from full-channel data to reconstruct missing channels in few-channel EEG data, supplementing the few-channel data with critical encodings and cooperative relationships related to depression. In addition, we use full-channel data to guide the process of information mining and depression detection to ensure that the training process conforms to the original data distribution. Experiments conducted on the MODMA and PRED+CT datasets demonstrate that the model achieves SOTA performance in depression detection under few-channel device conditions, validating the effectiveness of the proposed technique.

Abstract Multi-view learning is an emerging field that aims to enhance learning performance by leveraging multiple views or sources of data across various domains. By integrating information from diverse perspectives, multi-view learning methods effectively enhance accuracy, robustness, and generalization capabilities. The existing research on multi-view learning can be broadly categorized into four groups in the survey based on the tasks it encompasses, namely multi-view classification approaches, multi-view semi-supervised classification approaches, multi-view clustering approaches, and multi-view semi-supervised clustering approaches. Despite its potential advantages, multi-view learning poses several challenges, including view inconsistency, view complementarity, optimal view fusion, the curse of dimensionality, scalability, limited labels, and generalization across domains. Nevertheless, these challenges have not discouraged researchers from exploring the potential of multiview learning. It continues to be an active and promising research area, capable of effectively addressing complex real-world problems.

Missing traffic data caused by sensor failures or communication errors significantly hinders the efficiency of downstream tasks in Intelligent Transportation Systems (ITS), such as the critical functions of traffic monitoring and decision-making. Since missing data contains important information, it is essential to extract dynamic spatial-temporal correlations in traffic processes by incorporating these missing features. Motivated by these concerns, a novel Dynamic Spatial-Temporal Imputation Network with Missing Features (DSTMIN) is proposed to accurately impute traffic data. DSTMIN comprises an embedding layer, a Mask Attention module (MA), and a Fusion Graph Convolution module (FGC). Specifically, an embedding layer is designed to accurately represent the distribution of missing data, thereby capturing both temporal features and missing features. Furthermore, in order to effectively capture the temporal correlations, MA integrates the missing features to emphasize the significance of observed data and reduce the adverse effects caused using incomplete data. To capture spatial correlations, FGC constructs the spatial graphs and model dynamic spatial correlations from traffic subsequences and the missing-data graph in the presence of missing features. The proposed DSTMIN is adequately evaluated to demonstrate its superior performance on two datasets, which achieves a remarkable 20% reduction in imputation error compared to state-of-the-art methods.

We propose an online learning algorithm tailored for a class of machine learning models within a separable stochastic approximation framework. The central idea of our approach is to exploit the inherent separability in many models, recognizing that certain parameters are easier to optimize than others. This paper focuses on models where some parameters exhibit linear characteristics, which are common in machine learning applications. In our proposed algorithm, the linear parameters are updated using the recursive least squares (RLS) algorithm, akin to a stochastic Newton method. Subsequently, based on these updated linear parameters, the nonlinear parameters are adjusted using the stochastic gradient method (SGD). This dual-update mechanism can be viewed as a stochastic approximation variant of block coordinate gradient descent, where one subset of parameters is optimized using a second-order method while the other is handled with a first-order approach. We establish the global convergence of our online algorithm for non-convex cases in terms of the expected violation of first-order optimality conditions. Numerical experiments demonstrate that our method achieves significantly faster initial convergence and produces more robust performance compared to other popular learning algorithms. Additionally, our algorithm exhibits reduced sensitivity to learning rates and outperforms the recently proposedslimTrainalgorithm (Newman et al. 2022). For validation, the code has been made available on GitHub.

Graph-based methods have demonstrated exceptional performance in semi-supervised classification. However, existing graph-based methods typically construct either a predefined graph in the original space or an adaptive graph within the output space, which often limits their ability to fully utilize prior information and capture the optimal intrinsic data distribution, particularly in high-dimensional data with abundant redundant and noisy features. This paper introduces a novel approach: Semi-Supervised Classification with Optimized Graph Construction (SSC-OGC). SSC-OGC leverages both predefined and adaptive graphs to explore intrinsic data distribution and effectively employ prior information. Additionally, a graph constraint regularization term (GCR) and a collaborative constraint regularization term (CCR) are incorporated to further enhance the quality of the adaptive graph structure and the learned subspace, respectively. To eliminate the negative effect of constructing a predefined graph in the original data space, we further propose a Hybrid Subspace Ensemble-enhanced framework based on the proposed Optimized Graph Construction method (HSE-OGC). Specifically, we construct multiple hybrid subspaces, which consist of meticulously chosen features from the original data to achieve high-quality and diverse space representations. Then, HSE-OGC constructs multiple predefined graphs within hybrid subspaces and trains multiple SSC-OGC classifiers to complement each other, significantly improving the overall performance. Experimental results conducted on various high-dimensional datasets demonstrate that HSE-OGC exhibits outstanding performance.

The identification of separable nonlinear models, prevalent in tasks such as signal analysis, image processing, time series analysis, and machine learning, presents a non-convex optimization challenge that necessitates the development of efficient identification algorithms. The Variable Projection (VP) algorithm has been proven to be quite effective for addressing these problems; however, traditional VP relying on the Hessian matrix and its inverse are highly time-consuming and unsuitable for complex, large-scale applications. This letter introduces a novel approach that employs the exponential moving average of gradient and gradient estimation bias to indirectly estimate the curvature of the objective landscape, proposing a Moving Average-based Variable Projection method (MAVP). The proposed algorithm utilizes only gradient information and can properly tackle the coupling relationships between different parameters during the optimization process, thereby achieving faster convergence. Numerical results on nonlinear time series analysis and image reconstruction demonstrate that the MAVP algorithm exhibits significant efficiency and effectiveness.

Semi-supervised semantic segmentation has witnessed remarkable advancements in recent years. However, existing algorithms are based on convolutional neural networks, and directly applying them to Vision Transformers poses certain limitations due to conceptual disparities. To this end, we propose TokenSwap, a data augmentation technique designed explicitly for semi-supervised semantic segmentation with Vision Transformers. TokenSwap aligns well with the global attention mechanism by mixing images at the token level, enhancing the learning capability for contextual information among image patches and the utilization of unlabeled data. We further incorporate image augmentation and feature augmentation to promote the diversity of augmentation. Moreover, to enhance consistency regularization, we propose a dual-branch framework where each branch applies image and feature augmentation to the input image. We conduct extensive experiments across multiple benchmark datasets, including Pascal VOC 2012, Cityscapes, and COCO. Results suggest that the proposed method outperforms state-of-the-art algorithms with notably observed accuracy improvement, especially under limited fine annotations.

Recognizing human emotions through behavioral and physiological signals is fundamental to overall health. However, since emotion occurs transiently, a semantics mismatch exists between the uniformly annotated label and multimodal temporal signals, leading to emotional ambiguity. Previous studies used the annotated label to guide feature learning, which makes it intractable to accurately identify emotional elicitation moments within each signal. Moreover, the inconsistency of specific elicitation moments across different signals complicates emotion recognition. The model hardly learns discriminative features due to emotional ambiguity, which weakens its ability to differentiate between emotions. To tackle the above challenges, this paper proposes a novel label feature co-learning model (LFCL) for emotion recognition through multimodal signals. Specifically, the LFCL leverages unimodal and multimodal information and adaptively generates instance-level emotion labels, thus precisely locating emotion elicitation moments within each signal. To promote emotion consistency across different signals, the LFCL incorporates a dynamic label calibration mechanism to balance the label generation process with historical information. Furthermore, to enhance the deep interaction between signals, the LFCL conducts multimodal interactive fusion to integrate multi-level multimodal features and extract global emotional information. The LFCL performs precise label-to-feature alignment to capture discriminative features of each signal, effectively alleviating emotional ambiguity and improving the ability to distinguish different emotions. Extensive experiments on three publicly available datasets demonstrate the effectiveness and generalization of the proposed model.

Emotion recognition based on electroencephalography (EEG) data has gained rapid development because of its believability and accuracy. However, most existing EEG emotion recognition methods suffer from three issues: 1) underutilization of multi-scale emotion representations, 2) underexploitation of emotion labels and intrinsic geometric structures, and 3) inherent non-stationarity characteristic and individual variability of EEG signals. To this end, we propose an Adaptive Manifold Convolutional Broad Learning System (AM-ConvBLS) to capture the multi-scale distribution aligned emotion patterns in the geometric structure preserved emotion submanifold space. To begin with, a Multi-Scale Representation Learning (MSRL) module is developed to learn diverse multi-scale emotion representations. The Domain Discrepancy Elimination (DDE) module is then developed to further align feature distributions in the source and target domains. To further utilize EEG emotion labels, we devise a Label Manifold Information Exploration (LMIE) module to retain the sample label consistency. In addition, a global feature importance analysis method for AM-ConvBLS based on Shapley Additive Global importancE (SAGE) is designed to investigate the EEG frequency band importance and brain neural activation patterns. Experiments on SEED, SEED-IV, and SEED-V datasets demonstrate the effectiveness and superiority of our AM-ConvBLS.

EEG emotion recognition presents several challenges, including region correlation, local and long-range node connectivity, and multi-channel patterns, necessitating advanced methods capable of effectively capturing and utilising complex EEG signal information. This paper introduces a novel method, the dual-gate Chebyshev Linkage network (DGC-Link), which comprises three main components: the Chebyshev Linkage (CL) module for extracting regional correlation features, the dual-gate module for regulating the flow of different-order information, and the deep network for extracting multi-channel features and enhancing representation capabilities. Validated on three datasets (SEED, DREAMER, and MPED) with ablation experiments demonstrating each component's effectiveness, DGC-Link achieves superior recognition performance compared to state-of-the-art methods. Notably, it achieves 96.43% accuracy on differential entropy on the SEED dataset, and 98.58%, 97.62%, and 98.01% for valence, arousal, and dominance classifications on the DREAMER dataset, along with 78.48% and 44.93% for 3-class and 7-class classifications on the MPED dataset. These results highlight DGC-Link's potential for improved performance in EEG emotion recognition.

The existence of emotion-irrelevant representations and individual variability impedes the extraction of robust emotional representations, limiting the adaptability of EEG emotion recognition. Massive studies focus on the mining of emotion-aware information, overlooking emotion-agnostic information, which is insufficient for the extraction of emotion-relevant features against redundancy and variation. In this paper, Graph Orthogonal Purification Network (Grop) is proposed to enhance individual adaptability through improvements in the orthogonality and transferability between emotion-relevant and emotion-irrelevant features. Specifically, the proposed Grop utilized a graph representation extraction module to capture both emotion-relevant and emotion-irrelevant features by the dual graph. The representation orthogonal purification module is developed to eliminate redundant information through feature projection and feature purification. Moreover, the dual emotional space alignment module is imposed to align distribution discrepancies in different emotion feature spaces. To assess the effectiveness of the proposed Grop, various experiments are conducted on two public EEG emotion datasets, i.e., SEED and SEED-IV. The results achieve state-of-the-art performance, demonstrating the capability of the Grop to capture robust emotion features and alleviate the intra- and inter-subject discrepancies.

The abnormality in depression exhibits reciprocal imbalanced connectivity between brain regions rather than increased or decreased activity of one particular area. Current works primarily align the distributions of EEG electrodes with insufficient simulation of neurophysiological structures. Moreover, they neglect significant collaborative relationships among diverse brain regions, which limits the performance of MDD detection. Considering the comprehensive information across brain regions and domains, we propose a novel EEG-based MDD detection model named Time-Frequency Agent Graph Learning (TFAGL), to capture the specific whole-brain level collaborative mechanism of MDD. Specifically, we generate agent nodes adaptively to perform global interactions among regions to sufficiently simulate the function of principal neurons, thereby forming a dynamic local-global connectivity graph to capture connectivity patterns for intra- and inter-regions. Furthermore, interactive learning across different receptive fields through multi-scale graph convolution is applied for each domain and connectivity. Besides, we construct feature extractors for both time and frequency domains and apply intra- and inter-domain constraints to remove redundancy and enhance the discriminability, thus obtaining comprehensive information representations. Extensive experiments on the public EEG MDD detection datasets demonstrate the superiority of TFAGL compared with the state-of-the-art methods.

Trustworthy Graph Neural Networks (GNNs) for EEG emotion recognition should identify emotions accurately and elucidate corresponding rationales. Current GNNs have achieved notable performance by dynamically modeling emotional connections between EEG channels. However, these GNNs lack interpretability due to the absence of explicit rationale behind their predictions. This paper conducts a comprehensive identification of important EEG channels to enhance the interpretability of EEG emotion recognition from the perspective of mutual information. Specifically, an Adjacency-Explainable Graph Neural Network (AEG) for ante-hoc interpretability is proposed to capture genuine EEG emotional connections, which gives a theoretical guarantee to remove spurious connections. Moreover, a Channel-wise Adaptive Class Activation Mapping Explainer (CACA) for post-hoc interpretability is developed to locate the EEG channels that contribute most to predictions. Experimental results on three datasets, i.e., SEED, SEED-IV, and DREAMER, prove that imbuing training processes with enhanced interpretability ensures significant performance improvements in emotion recognition. Quantitative comparisons of post-hoc interpretability also demonstrate the superiority of CACA. Furthermore, this paper illustrates two potential applications of the proposed methodologies, showing their broader utility and significance.

The piezoelectric actuator will exhibit the problem of unknown control direction under high-speed operating conditions. Hence, the realization of high-speed control for nonlinear systems driven by piezoelectric actuators requires the fixed-time stability to enhance the convergence rate and the Nussbaum technique to handle the problem of unknown control directions. However, these two techniques are incompatible because the required conditional inequalities for each are different. To resolve this incompatibility, we have incorporated the projection operator into the design of the adaptive updating law. On the basis of ensuring that the adaptive estimation parameter is bounded, we have established the conditional inequality for Nussbaum technique. Then, some nonlinear damping terms are incorporated into the stability analysis to counteract a term containing Nussbaum function, thereby reducing the difficulty of the fixed-time stability analysis. Furthermore, the predefined tracking accuracy and fixed-time stability are theoretically proven through the stability analysis. Finally, the efficiency of the proposed control method is validated through semi-physical experiments on a cylindrical piezoelectric actuator.

Existing works have made some progress in point cloud registration, but most of them measure performance only on point cloud pairs with high overlap. In practical applications, it is often difficult to ensure that the collected point clouds overlap in large regions due to problems such as occlusion and noise. Therefore, a good low-overlap point cloud registration method is of great practical significance. However, extracting reliable correspondences from point clouds has always been a challenging task, particularly when dealing with low-overlap situation. In this paper, we propose a novel method for low-overlap point cloud registration via efficient correspondence augmentation, called AugLPCR, which not only enhances correspondences with high confidence, but also employs confidence weights to mitigate the impact of outliers. After the augmentation, the correspondences used for the transformation have a large amount of inliers, leading to improved registration performance. Extensive experiments on indoor and outdoor datasets demonstrate that the proposed AugLPCR is capable of maintaining consistent performance and achieve results comparable to or better than the state-of-the-art methods. Note to Practitioners—The motivation of this paper is to address the problem of registering two low-overlap point clouds. Mainstream algorithms for point cloud registration typically assume a sufficient overlap between point clouds. However, in practical scenarios, it is common to encounter scans with inadequate overlap. These conditions often hinder the extraction of reliable correspondences. This paper introduces an effective method for augmenting correspondences to address the problem of low inlier rates within predicted correspondences. While augmenting correspondences with high confidence, it also mitigates the influence of outliers and ambiguous points. Additionally, traditional approaches often divide superpoint regions before matching, but this can lead to the elimination of points in overlapping regions alongside outliers. To address this issue, we adjust the order of superpoint matching and region partitioning. The proposed framework can be easily applied to other correspondence-based point cloud registration models.

The interval observer, recognized as a potent tool for fault detection (FD), diverges from the adoption of fixed thresholds to enhance the timeliness and precision of detection. This study endeavors to design an FD mechanism for fuzzy cyber-physical systems (CPSs) subjected to adversarial influences based on improved attack tolerant interval observer. Specifically, the proposed frequency-information-based unknown input interval observer (UIIO) not only enables a more precise estimation of the interval range under the influence of attack signals but also isolates unknown decoupled inputs. Furthermore, it facilitates specific performance design for signals within a particular frequency range. Following the stability analysis of the system, linear solvable conditions are presented to ensure the robustness, fault sensitivity of the augmented system, as well as non-negativity of the augment system matrix. Finally, the proposed attack-tolerant FD mechanism is validated through simulation examples, including the influence of the prior attack information to detection interval width and the detection performance for small-amplitude faults or faults with specific frequency characteristics.Note to Practitioners—CPSs constitute the core of the next-generation manufacturing industry, applicable in areas like unmanned autonomous systems, smart grids, and intelligent healthcare, capitalizing on wide-ranging cyber space utilization. Nonetheless, this breadth also exposes them to elevated risks, including the threat of actuator attacks. The novel fault detection scheme developed in this paper is capable of operating in real-time when the system is confronted with various threats such as disturbances, faults, and actuator attacks. This approach obviates the requirement for knowledge about the nature of actuator attack signals, while enabling the generation of a system state estimation interval with a tunable error range. Leveraging frequency-dependent techniques, the developed scheme, even in the presence of potential actuator attack and disturbance, is particularly well-suited for the detection of fault signals with specific frequency domain characteristics.

The most existing studies on fixed-time control are restricted to nonlinear systems without the quantized signals. To remove this restriction, for a class of strict-feedback nonlinear systems (SFNSs) with input and output quantization, a new adaptive fuzzy fixed-time control scheme is presented in this article. Firstly, since the functions in SFNSs are unknown, fuzzy logic systems (FLSs) are applied to approximate them. Based on the quantized input and output signals, a novel fuzzy state observer is devised to evaluate the unmeasurable states. Secondly, in the backstepping design process, because of the discontinuity of output quantization, the partial derivatives of the virtual control signals are difficult to obtain. To get over this difficulty, a command filtering technology is adopted. Furthermore, an actual quantized fixed-time controller and novel parameter adaptive laws are established. Thirdly, to compensate the effects of the quantization errors,Lemmas 10and11are presented. It is indicated that the presented control scheme can ensure the practical fixed-time stability of control systems. Finally, an example is given to demonstrate the effectiveness of the presented scheme.Note to Practitioners—In practical remote control systems, because of the limitation of communication channel capacity, signals usually need to be quantized before transmission. However, the most existing fixed-time control schemes for SFNSs do not study the signals quantization. This means that the control processes still rely on the continuous states/output and control input signals, which are not practical in engineering application. Therefore, based on FLSs and command filtering technology, this paper focuses on developing a novel adaptive fuzzy quantized fixed-time control scheme. This scheme ensures that SFNSs under the input and output quantization is still practically fixed-time stable.

This paper addresses the challenge of adaptive fuzzy event-triggered bipartite consensus control for a class of nonlinear multi-agent systems (MASs) with full-state asymmetric constraints, incorporating both cooperative and adversarial communication between agents. To ensure consensus tracking performance in the presence of asymmetric full-state constraints, the nonlinear MASs are augmented with an enhanced nonlinear function. Fuzzy logic systems (FLSs) are employed to handle unfamiliar nonlinearities effectively. To reduce the communication burden and enhance transient performance, an event-triggered control strategy is introduced, accompanied by the construction of an observer utilizing triggered output signals to assess unmeasured states. Furthermore, the control scheme is formulated by integrating dynamic surface control (DSC) and adaptive backstepping techniques. The validity of the proposed approach is verified through Lyapunov’s theory, demonstrating that all signals within the closed-loop system are bounded. Simulation results further support the effectiveness of the proposed methodology.Note to Practitioners—With the rapid development and deep integration of intelligent control theory, the control design of MASs is still challenging in many engineering problems. However, in practical applications, there is not only cooperation but also competition between agents, and the system states are unmeasured and subject to various forms of constraints. To solve this problem, we introduce an improved nonlinear transformation function. When network resources are limited, continuous communication is sometimes not feasible in engineering applications. To minimize the communication burden, we propose an event-triggered control strategy, which combines dynamic surface control technology and adaptive backstepping technology to design the trigger controller. The proposed scheme can effectively save resources and deal with various constraints of system states and may be applied to other similar engineering fields.

In the field of online learning, handling imbalanced data streams with concept drift has become a substantial challenge. Research interest in the combined challenges of concept drift and class imbalance is steadily growing. When dealing with concept drift, existing methods usually adopt active detection or passive adaptation to deal with concept drift. However, a single adaptation method is relatively limited in dealing with joint concept drift. This paper introduces a novel hybrid ensemble framework (HEF-IDS) specifically designed to tackle drifting data streams while effectively accommodating class imbalance. The framework integrates an active detection module and a passive adaptation module. In the passive adaptation module, we use a hybrid sampling strategy to balance data chunks, construct a sub-ensemble classifier for each balanced chunk, and combine it with a weighted voting scheme to deal with the class imbalance and adapt to the latest concept. In the process of active detection, we design a new sample selection mechanism that stores the most informative samples in the buffer, and uses these samples for training when drift is detected to prevent catastrophic forgetting. Comparative results on artificial and real-world datasets show that the proposed HEF-IDS is superior to other advanced online classification methods.

As data continues to grow exponentially, the importance of online learning across various domains has increased significantly. However, most existing studies assume that the true class label for each incoming data point is readily available, an assumption that is often impractical. To address this issue, this paper introduces a novel algorithm called Density-based Clustering and One-Class Ensemble Active Learning (DCOE-AL). This approach constructs an ensemble model by combining a clustering algorithm with the One-Class Broad Learning System (OCBLS), which represents clusters within the feature space. Furthermore, a new active learning mechanism is developed to enable DCOE-AL to effectively handle challenges associated with concept drift and label scarcity. The proposed method is evaluated on multiple synthetic data streams that exhibit diverse types of concept drift, as well as on several real-world data streams. Comparative evaluations demonstrate that DCOE-AL achieves superior performance while requiring significantly fewer labeled samples.

Time series anomaly detection is a pivotal task in data analysis, yet it poses the challenge of discerning normal and abnormal patterns in label-deficient scenarios. While prior studies have largely employed reconstruction-based approaches, which limit the models’ representational capacities. Moreover, existing deep learning-based methods are not sufficiently lightweight. Addressing these issues, we present PatchAD, our novel, highly efficient multiscale patch-based MLP-Mixer architecture that utilizes contrastive learning for representation extraction and anomaly detection. With its four distinct MLP Mixers and innovative dual project constraint module, PatchAD mitigates potential model degradation and offers a lightweight solution, requiring only0.403 Mparameters. Its efficacy is demonstrated by state-of-the-art results across8datasets sourced from different application scenarios, outperforming over30comparative algorithms. PatchAD significantly improves the classical F1 score by6.84%, the Aff-F1 score by4.27%, and the V-ROC by2.49%. Simultaneously, an in-depth analysis of the mechanisms underlying PatchAD has been conducted from both theoretical and experimental perspectives, validating the design motivations of the model.

The work aims to solve the high-speed high-precision tracking control problem of piezoactuators in the presence of stochastic disturbances. First, a cascade model composed of the Preisach operator and a class of stochastic nonlinear systems is proposed to describe the sophisticated actuator dynamics during high-speed operation, and then a hysteresis decomposition strategy is developed to transform the Preisach model into an appropriate form tractable to control design so that a robust adaptive fuzzy control framework can be constructed successfully to suppress the hysteresis nonlinearities, and to robustify bounded stochastic disturbances. More importantly, based on such a framework, the fixed-time stability (instead of practical fixed-time stability), and the prescribed steady-state tracking performance can be established simultaneously. Besides theoretical analysis, some experimental tests are also conducted to illustrate the effectiveness of the proposed scheme.

Numerous significant temporal graph tasks, such as graph similarity ranking, trend analysis and anomaly detection, necessitate low-dimensional and high-order graph-level embedding in terms of the evolving nodes and topologies over time. However, most existing graph embedding methods focus on extracting node-level embeddings, while ignoring these evolutions. Therefore, these methods inadequately consider the impact of trends on the overall graph. Moreover, there are a large number of nodes in temporal graphs, which make it difficult to generate effective graph embeddings directly by aggregating dynamic node embeddings. In this study, we propose a novel temporal attention network for learning graph-level embedding learning called GraphTAN. Specifically, the proposed model employs pooling attention to select crucial nodes and filter out noisy ones for each snapshot, thereby enhancing the quality of aggregated graph embeddings. Furthermore, we design a graph-level temporal attention mechanism to effectively extract temporal graph embeddings, capturing trends and patterns across snapshots. The proposed model is evaluated on three downstream tasks. Experimental results demonstrate that GraphTAN captures both the topology structure and fine-grained trend effectively, outperforming the state-of-the-art methods with big margins on multiple tasks over several real networks.

The underlying time-variant and subject-specific brain dynamics lead to statistical uncertainty in electroencephalogram (EEG) representations and connectivities under diverse individual biases. Current works primarily augment statisticallike EEG data based on deterministic modes without comprehensively considering uncertain statistical discrepancies in representations and connectivities. This results in insufficient domain diversity to cover more domain variations for a generalized model independent of individuals. This article proposes an uncertainty-guided graph augmentation network (Ugan) to generalize EEG emotion recognition across subjects by comprehensively mimicking and constraining the uncertain statistical shifts across individuals. Specifically, an uncertainty-guided graph augmentation module is employed to augment both connectivities and features of EEG graph by manipulating domain statistical characteristics. With the original and augmented EEG graph covering diverse domain variations, the model can mimic the uncertain domain shifts to achieve better generalizability against potential subject variability. To extract discriminative characteristics and preserve emotional semantics after augmentation, a graph coteaching learning module is designed to facilitate coteaching knowledge learning between the original and augmented views. Moreover, a coteaching regularization module is developed to constrain semantic domain invariance and consistency, thereby rendering the model invariant to uncertain statistical shifts. Extensive experiments on three public EEG emotion datasets, i.e., Shanghai Jiao Tong University emotion EEG dataset (SEED), SEED-IV, and SEED-V, validate the superior generalizability of Ugan compared to the state-of-the-art methods.

Affective brain–computer interfaces (aBCIs) have shown promising applications due to the significant advancements in utilizing electroencephalogram (EEG) signals for emotion recognition. By measuring neuronal activity across various brain regions, EEG provides rich spatial information that is essential for discriminative feature extraction and effective emotion recognition. However, existing deep learning models face challenges in effectively capturing and leveraging local and global spatial dependencies. To address this, we propose a hierarchical spatial aggregation Transformer (HSA-Former) for EEG-based emotion recognition, which explores spatial relationships from multiple levels, including electrodes, intrabrain regions, and interbrain regions. The HSA-Former is characterized by: 1) a multihierarchical spatial information learning architecture that sequentially extracts diverse spatial features from electrodes, through intrabrain regions, and across interbrain regions; 2) a parallel learning approach that captures internal spatial features of different brain regions from different channels; and 3) an effective aggregation method that mitigates the problem of information loss typically caused by direct pooling in Transformers. Extensive experiments on three public datasets (i.e., SEED, SEED-IV, and SEED-V) demonstrate that the proposed HSA-Former outperforms existing state-of-the-art methods. Interestingly, the weights learned by HSA-Former emphasize the frontal, temporal, and occipital lobes as critical brain regions, aligning with established mechanisms underlying emotion recognition.

The multicloud environments (MCE) represent a novel paradigm encompassing multiple infrastructure as a service (IaaS) providers, enabling users to tailor and optimize cloud services according to their specific requirements. This approach effectively addresses the limitations of a single cloud environment (SCE) regarding technical constraints, geographical coverage deficiencies, and cost-effectiveness concerns while catering to the increasingly diverse and expanding user demands. In MCE, users must employ appropriate strategies to efficiently allocate diverse tasks across multiple cloud service providers (CSPs) by leveraging the best available resources. Traditional scheduling algorithms are inadequate for addressing the complexities of such MCE. This study introduces a framework for the task scheduling procedure in MCE, treating independent task scheduling as a Markov decision process (MDP). We propose a novel agent environment framework that is designed based on the distinctive characteristics of MCE and enables independent task scheduling. Furthermore, we propose a task scheduling algorithm for MCE based on deep reinforcement learning (DRL) to optimize cost and makespan according to diverse user requirements. The simulation experiments are conducted using both simulated datasets and real-world datasets, demonstrating that our proposed algorithm surpasses the other five algorithms in terms of cost minimization and makespan optimization.

Credit card (CC) fraud detection within the realm of financial security faces challenges such as data imbalance, large-scale anonymized transaction datasets, and the need for system-specific model training. Past methods often fail to address these aforementioned issues simultaneously. Utilizing a single model results in a lack of zero-shot capability without adaptation for real-world scenarios. This article introduces LLM40FD, a novel framework that leverages a large language model (LLM) to overcome these obstacles in anonymous zero-shot fraud detection. LLM40FD addresses the aforementioned challenges in CC fraud detection by employing a distribution-based one-class function and the walking embedding, without reliance on labeled data or fine-tuning in downstream. Additionally, LLM40FD enhances the model’s ability to detect fraudulent patterns and define robust decision boundaries. This is achieved through a dual-augmentation strategy and implicit contrastive learning, which generate enriched positive and negative samples. Our experiments demonstrate that LLM40FD not only achieves state-of-the-art (SOTA) performance in the full-shot setting but also exhibits strong zero-shot capability even with limited training data. Furthermore, we conduct additional experiments to validate the effectiveness and working mechanism of LLM40FD.

Affective music generation is a challenge for symbolic music generation. Existing methods face the problem that the perceived emotion of the generated music is not evident because music datasets containing emotional labels are relatively small in quantity and scale. To address this issue, an attribute-enhanced affective music transformer (AE-AMT) model is proposed to generate perceived affective music with attribute enhancement. In addition, a multiquantile-based attribute discretization (MQAD) strategy is designed, enabling the model to generate intensity-controllable affective music pieces. Furthermore, A replication-expanded compound representation of the control signals (RECR) method is designed for control signals to improve the controllability of the model. In objective experiments, the AE-AMT model demonstrated a 29.25% and 19.5% improvement in overall emotion accuracy, along with a 30% and 32% improvement in arousal accuracy on the datasets EMOPIA and VGMIDI. These improvements are achieved without significant difference in objective music quality, while also providing ample novelty and diversity compared to the current state-of-the-art approach. Moreover, subjective experiments revealed that the AE-AMT model outperformed comparison models, especially in low valence and arousal based on the Wilcoxon signed ranks test. Additionally, the soft variant model of AE-AMT exhibited a significant advantage in valence, low arousal, and overall music quality. These experiments showcase the AE-AMT model's ability to significantly enhance arousal performance and strike a balance between emotional intensity and musical quality through adaptable strategies.

This article studies the adaptive neural network (NN) event-triggered secure control issue for stochastic nonlinear systems subject to sensor attacks. NNs are adopted to identify unknown nonlinear dynamics, and an NN state estimator is established to address the issue resulting from unmeasurable states. An NN observer is proposed to estimate unknown sensor attack signals. To save limited communication resources and reduce the number of controller updates, an event-triggered control (ETC) scheme is introduced. Then, an adaptive NN event-triggered secure control algorithm is designed by backstepping control method. The results demonstrate the stability of the control system and its consistent convergence in tracking errors under sensor attacks. Finally, simulations are shown to verify the effectiveness of the investigated theory.

The limitations of acquisition equipment often result in scene image data of limited size, posing a challenge for comprehensive analysis of social image datasets. Advances in generative models have introduced image outpainting techniques that expand the size of acquired social scene images, thereby enhancing the value of social image data. Stable diffusion (SD), which benefits from the guidance of caption prompts, shows excellent performance in image outpainting. However, its heavy reliance on manual prompts leads to a significant drawback: a decrease in the quality of generated images without prompts. To overcome this challenge, we propose a novel self-prompt diffusion model for image outpainting that extrapolates images based on the semantics of the source image, thereby removing the dependence on manual prompts. Specifically, we design a prompt autoencoder that uses an autoregressive transformer to map prompt embeddings into their semantic space, facilitating the construction of a semantic decoder. The semantic decoder and prompt embeddings are then cooptimized within the proposed prompt embedding network, allowing the mapping of image features to the stable diffusion prompt embeddings. Furthermore, by exploiting the inherent generative capabilities of diffusion models, we introduce a seam line regeneration mechanism to address the common problem of seam lines when splicing input and generated images. Comparative experiments on the Places2 and COCO datasets show that our method outperforms current state-of-the-art approaches on visual quality metrics and is adaptable to the stable diffusion model without additional fine-tuning.

Subjective tasks involve annotating instances according to personal opinions, emotions, and feelings. The neural network model must learn about human thought and expression complexity. Handling instances with different annotation opinions is the main challenge in subjective tasks. Existing methods focus on majority voting or integrating opinions from a few assigned annotators, leading to biased decisions and limited performance. To address this issue, this article proposes a cascade perspective network (CPNet) to uncover reliable disagreement for subjective tasks. Specifically, CPNet learns each annotator’s personalized knowledge from annotation disagreement and stores them in an annotator bank through the personal perspective module for abundant disagreement information. Then, CPNet obtains consistent opinions by referring to all annotators’ opinions from the annotator bank through the comprehensive perspective module to reduce bias caused by noise. CPNet improves decision-making by considering the diversity and comprehensiveness of all annotators’ opinions. Moreover, it performs well in subjective tasks with limited or numerous annotators. The state-of-the-art (SOTA) results on subjective datasets from different domains demonstrate the effectiveness and generalizability of CPNet.

When capturing images under strong light sources at night, intense lens flare artifacts often appear, significantly degrading visual quality and impacting downstream computer vision tasks. Although transformer-based methods have achieved remarkable results in nighttime flare removal, they fail to adequately distinguish between flare and non-flare regions. This unified processing overlooks the unique characteristics of these regions, leading to suboptimal performance and unsatisfactory results in real-world scenarios. To address this critical issue, we propose a novel approach incorporating Location Prior Guidance (LPG) and a specialized flare removal model, LPFSformer. LPG is designed to accurately learn the location of flares within an image and effectively capture the associated glow effects. By employing Location Prior Injection (LPI), our method directs the model’s focus towards flare regions through the interaction of frequency and spatial domains. Additionally, to enhance the recovery of high-frequency textures and capture finer local details, we designed a Global Hybrid Feature Compensator (GHFC). GHFC aggregates different expert structures, leveraging the diverse receptive fields and CNN operations of each expert to effectively utilize a broader range of features during the flare removal process. Extensive experiments demonstrate that our LPFSformer achieves state-of-the-art flare removal performance compared to existing methods. Our code and a pre-trained LPFSformer have been uploaded to GitHub for validation.

Reflection removal is a crucial issue in image reconstruction, especially for high-definition images. Removing undesirable reflections can greatly enhance the performance of various visual systems, such as medical imaging, autonomous driving, and security surveillance. However, the resolution of existing reflection removal datasets is not high and the training data heavily relies on synthetic data, which hampers the performance of reflection removal methods and restricts the development of effective techniques tailored for high-definition images. Therefore, this paper introduces a new dataset, Real-world Reflection Removal in 4K (RR4K). This novel dataset, with its large capacity and high resolution of$6000\times 4000$pixels, represents a significant advancement in the field, ensuring a realistic and high quality benchmark. Furthermore, building upon the dataset, we propose an efficient method for single-image reflection removal, optimized for high-definition processing. This method employs the U-Net architecture, enhanced with large kernel distillation and scale-aware features, enabling it to effectively handle complex reflection scenarios while reducing computational demands. Comprehensive testing on the RR4K dataset and existing low-resolution datasets has demonstrated the method’s superior efficiency and effectiveness. We believe that our constructed RR4K dataset can better evaluate and design algorithms for removing undesirable reflection from real-world high-definition images. Our dataset and code are available athttps://github.com/jengchauwei/RR4K.

Underwater images often suffer from various issues such as low brightness, color shift, blurred details, and noise due to light absorption and scattering caused by water and suspended particles. Previous underwater image enhancement (UIE) methods have primarily focused on spatial domain enhancement, neglecting the frequency domain information inherent in the images. However, the degradation factors of underwater images are closely intertwined in the spatial domain. Although certain methods focus on enhancing images in the frequency domain, they overlook the inherent relationship between the image degradation factors and the information present in the frequency domain. As a result, these methods frequently enhance certain attributes of the improved image while inadequately addressing or even exacerbating other attributes. Moreover, many existing methods heavily rely on prior knowledge to address color shift problems in underwater images, limiting their flexibility and robustness. In order to overcome these limitations, we propose the Embedding Frequency and Dual Color Encoder Network (FDCE-Net) in our paper. The FDCE-Net consists of two main structures: 1) Frequency Spatial Network (FS-Net) aims to achieve initial enhancement by utilizing our designed Frequency Spatial Residual Block (FSRB) to decouple image degradation factors in the frequency domain and enhance different attributes separately; 2) To tackle the color shift issue, we introduce the Dual-Color Encoder (DCE). The DCE establishes correlations between color and semantic representations through cross-attention and leverages multi-scale image features to guide the optimization of adaptive color query. The final enhanced images are generated by combining the outputs of FS-Net and DCE through a fusion network. These images exhibit rich details, clear textures, low noise and natural colors. Extensive experiments demonstrate that our FDCE-Net outperforms state-of-the-art (SOTA) methods in terms of both visual quality and quantitative metrics. The code of our model is publicly available at:https://github.com/Alexande-rChan/FDCE-Net.

Domain generalization aims at learning a model with transferable knowledge from one or more source domain(s) in the presence of domain shift, enabling the model to achieve effective generalization for an unseen target domain. Most existing methods pursue domain-invariant representations of samples to address the challenges of heterogeneous distributions across domains. However, most of such methods are limited to simple data manipulation at the instance level or computing style statistics in feature space for distribution alignment. Such operations fail to effectively capture the contextual semantics across domains from both the intra and inter-views. In this paper, we propose contextual Distribution Alignment via a Contrastive Learning strategy with domain correlation, called DACL, which sufficiently exploits both intra- and inter-domain invariant representations for image domain generalization classification. Specifically, a new Fourier-based augmentation method is developed to capture high-level semantic invariant features. Second, a domain-based feature fusion module is further proposed to increase the diversity of features, which mainly extracts both intra- and inter-domain prototypes via clustering to learn cross-domain representations. Finally, we propose a contrastive learning strategy that takes domain correlation into account, which uses spatial second-order statistics as a metric to measure the relevance between multiple source domains. Extensive experiments are conducted on two domain generalization tasks over six benchmarks, demonstrating that DACL achieves state-of-the-art performance against baseline models. A series of ablation studies are performed and in-depth analyses are conducted in visualization to further verify the rationality and effectiveness of the proposed method.

The underlying time-variant and subject-specific brain dynamics lead to inconsistent distributions in electroencephalogram (EEG) topology and representations within and between individuals. However, current works primarily align the distributions of EEG representations, overlooking the topology variability in capturing the dependencies between channels, which may limit the performance of EEG emotion recognition. To tackle this issue, this article proposes an adaptive attention-modulated graph network (AdamGraph) to enhance the subject adaptability of EEG emotion recognition against connection variability and representation variability. Specifically, an attention-modulated graph connection module is proposed to explicitly capture the individual important relationships among channels adaptively. Through modulating the attention matrix of individual functional connections using spatial connections based on prior knowledge, the attention-modulated weights can be learned to construct individual connections adaptively, thereby mitigating individual differences. Besides, a deep node-graph representation learning module is designed to extract long-range interaction characteristics among channels and alleviate the over-smoothing problem of representations. Furthermore, a graph domain co-regularized learning module is imposed to tackle the individual distribution discrepancies in connection and representations across different domains. Extensive experiments on three public EEG emotion datasets, i.e., SEED, DREAMER, and MPED, validate the superior performance of AdamGraph compared with state-of-the-art methods.

Multiview Subspace Clustering (MvSC) has demonstrated impressive clustering performance on multiview data. Most existing methods rely on either raw features or reduced-redundancy data for subspace representation learning, followed by spectral clustering to derive the final results. However, these methods maintain a fixed feature space during subspace learning, which limits information propagation and compromises both representation quality and clustering performance. To address this issue, this article proposes an adaptive dictionary learning approach for MvSC (AMvSC), which seamlessly integrates redundancy reduction and representation learning within a unified framework to facilitate mutual information propagation. Specifically, an adaptive dictionary learning strategy is designed to automatically reduce redundancy and noise in the original feature space during the subspace representation learning process. This strategy ensures effective information exchange, thereby enhancing the quality of the learned representations. Additionally, low-rank constraints, combined with smoothness and diversity regularization, are applied to further refine the subspace representations and comprehensively capture complex correlations among samples. Finally, an alternating optimization algorithm is developed to iteratively update the unified learning model. Extensive experiments validate the effectiveness and superiority of the proposed method.

Metric learning aims to learn a discriminative metric space, where samples of the same class stay close, and those of different classes far apart. Existing classical metric learning methods based on linear transformation have limited learning performance due to the low representation capability. Although deep metric learning learns nonlinear mappings, the training may come across convergence issues and be unstable. Additionally, many classical metric learning algorithms suffer from long computational time for iterative optimization especially when data dimension is high. Deep metric learning also requires high training cost. To learn a metric space more efficiently and effectively, this article proposes a novel broad metric learning (BML) model, which learns the data transformation by training a broad network. BML maps input data to a broad feature space by fast and convenient nonlinear feature mapping based on random weights, and learns a linear transformation to a discriminative output space. Intraclass distance is reduced by minimizing the distance between data and their class-specific reference points in the target space. The hard-triplet distance learning (HDL) is proposed to learn the distance of hard positive and negative sample pairs, which enhances the intraclass compactness and interclass separation. Closed-form solutions are adopted to solve the optimization problems efficiently when learning the linear transformation. Experiments are conducted on nine datasets to verify the efficiency and effectiveness of BML. BML learns fast and achieves high classification and clustering accuracies in the learned data space.

The broad learning system (BLS) is a lightweight neural network known for its efficient learning capabilities; however, it is limited by its reliance on a binary label strategy. Existing label enhancement models primarily focus on increasing the distances between labels from different classes, which inadvertently expands the distance within the same category. For classification tasks, maintaining similarity within the intraclass is essential for ensuring the model's effectiveness. To address this issue, we propose a groupwise label enhancement BLS model that ensures both intraclass similarity and interclass disparity of labels. Specifically, we develop a novel regression target that generalizes existing label enhancement targets in BLS, increasing the distances between labels of different classes while overcoming the constraints imposed by binary labels. Moreover, we design a groupwise constraint to jointly enhance the intraclass similarity and interclass disparity of labels. Additionally, we propose a novel alternating direction method of multipliers-based optimization algorithm to solve our proposed model, ensuring both computational efficiency and theoretical convergence. Experimental results on several public datasets demonstrate the outstanding effectiveness and efficiency of our proposed model compared to other state-of-the-art methods.

Multiview semi-supervised learning is a popular research area in which people utilize cross-view knowledge to overcome the limitation of labeled data in semi-supervised learning. Existing methods mainly utilize deep neural network, which is relatively time-consuming due to the complex network structure and back propagation iterations. In this article, co-training broad Siamese-like network (Co-BSLN) is proposed for coupled-view semi-supervised classification. Co-BSLN learns knowledge from two-view data and can be used for multiview data with the help of feature concatenation. Different from existing deep learning methods, Co-BSLN utilizes a simple shallow network based on broad learning system (BLS) to simplify the network structure and reduce training time. It replaces back propagation iterations with a direct pseudo inverse calculation to further reduce time consumption. In Co-BSLN, different views of the same instance are considered as positive pairs due to cross-view consistency. Predictions of views in positive pairs are used to guide the training of each other through a direct logit vector mapping. Such a design is fast and effectively utilizes cross-view consistency to improve the accuracy of semi-supervised learning. Evaluation results demonstrate that Co-BSLN is able to improve accuracy and reduce training time on popular datasets.

Broad learning system (BLS) is an effective neural network requiring no deep architecture, however it is somehow fragile to noisy data. The previous robust broad models directly map features from the raw data, which inevitably learn useless or even harmful features for data representation when the inputs are corrupted by noise and outliers. To address this concern, a discriminative and robust network named as dynamic graph regularized broad learning (DGBL) with marginal fisher representation is proposed for noisy data classification. Different from the previous works, DGBL eliminates the effect of noise before the random feature mapping by the proposed robust and dynamic marginal fisher analysis (RDMFA) algorithm. The RDMFA is able to extract more robust and informative representations for classification from the latent clean data space with dynamically generated graphs. Furthermore, the dynamic graphs learned from RDMFA are incorporated as regularization terms into the objective of DGBL to enhance the discrimination capacity of the proposed network. Extensive quantitative and qualitative experiments conducted on numerous benchmark datasets demonstrate the superiority of the proposed model compared to several state-of-the-art methods.

This article proposes a spatial learning control system for robots to achieve a desired behavior during interacting with unknown environments. In contacting with the environment, the force is estimated by a force observer, so sensing devices are not required. Motivated by the human interaction versatility, the reference trajectory of the robot is updating with a learning law such that the interacting force can be maintained at a desired level. Compared with the trajectory iteration algorithm based on time domain, which requires maintaining a fixed motion speed for each iteration, the proposed method can remove this limitation and have better feasibility. The adaptive controller with neural networks can compensate the uncertain dynamics of the system and ensure the control accuracy. Through Lyapunov's theory, the system is proved to be stable, and all the states are bounded. Comparative simulations and experiments are conducted on a robot platform to verify the effectiveness of the proposed method.

This article addresses the optimal control problem for nonlinear multiagent systems (MASs) with an uncertain nonlinear leader subject to intermittent Denial-of-Service (DoS) attacks. The main challenge is estimating the leader's dynamics when the uncertain nonlinear dynamics of the leader are unknown to all followers and communication between subsystems is intermittently disrupted by attacks. Furthermore, the uncertainty in the followers' dynamics adds complexity, making it difficult to eliminate reliance on the identifier network. To overcome these challenges, we develop a learning-based adaptive distributed observer to estimate the leader's dynamics under attacks. Based on this observer, a single-critic optimal consensus tracking control scheme is proposed to solve the leader-follower consensus problem in uncertain MASs without requiring an identifier network. It is proven that all system signals are uniformly ultimately bounded (UUB), and consensus tracking is achieved. The effectiveness of the proposed method is validated through a simulation example.

This article investigates the distributed resilient energy management (EM) strategy for the seaport microgrid under stealthy attacks. First, based on an analysis of seaport microgrid characteristics, we construct an EM model that aims at minimizing both operating cost and security defense resource (SDR) cost. Second, we present a distributed, resilient strategy by defining node security levels and establishing dynamic security intervals. We prove that the gap between the obtained feasible solution and the optimal one is bounded. The designed strategy is capable of tolerating the effect of the unlimited number of stealthy attacked nodes on the seaport microgrid. In addition, given the limited SDRs for the resilient EM of the island seaport microgrid, a distributed mechanism for searching the minimum security connected dominating set (MSCDS) is proposed to minimize the size of trusted nodes. Finally, simulation results demonstrate the effectiveness of the proposed strategy. Note to Practitioners: This article addresses the vulnerability of the seaport microgrid, a critical issue that impacts EM and disrupts seaport operations. Current approaches to seaport EM do not account for potential attacks. Meanwhile, existing methods for attack resilience often overlook the costs of security resources. We propose a new approach for the distributed and resilient EM of the island seaport microgrid. Secure operation is achieved by protecting the fewest trusted nodes, thereby conserving SDRs. We then show how this algorithm (searching the MSCDS) can be efficiently designed. Preliminary simulations indicate its feasibility, though it has yet to be tested in a production environment. Future research will focus on designing trusted nodes within dynamic topologies.

A neural network adaptive quantized predefined-time control problem is studied for switching stochastic nonlinear systems with full-state error constraints under arbitrary switching. Unlike previous research on rapid convergence, the predefined-time stability criteria are introduced and established for stochastic nonlinear systems, ensuring the stabilization of the control system within a specified time frame. The chattering issue is avoided and it is split into two limited nonlinear functions using a hysteresis quantizer. To address the full-state error constraint problem, a universal barrier Lyapunov function is presented. The common Lyapunov function approach is used to demonstrate the stability of controlled systems. The results demonstrate that the proposed control method ensures all closed-loop signals are probabilistically practically predefined time-stabilized (PPTS), with the system output closely tracking the specified reference signal. Finally, simulated examples validate the effectiveness of the suggested control technique.

Broad learning system (BLS) is renowned for its excellent generalization and high efficiency in data classification. However, when confronted with class imbalance problems, BLS treats all samples as equally important, resulting in performance degradation. In addition, the presence of noise and outliers in imbalanced data further complicates BLS's ability to handle real-world classification problems. To address these challenges, this article proposes a graph-embedding intuitionistic fuzzy adaptive broad learning system (GEIB). The graph embedding strategy proposed by GEIB leverages the geometric topology of the data and class-specific information, effectively capturing variability among imbalanced samples and improving class separability. Furthermore, we introduce intuitionistic fuzzy theory. The BLS integrated with it considers both the homogeneity and heterogeneity of sample neighborhoods, enabling it to address uncertainty and imprecision in the data. It further differentiates clean samples from noisy ones in imbalanced datasets, thereby enhancing model robustness. To further investigate the prior distribution information of imbalanced data, we design an adaptive class-specific penalty mechanism based on global distribution and local density information. This mechanism accounts for both intraclass and interclass density information and class global distribution. We verify the superiority of our method by conducting a comparison with current approaches using real-world datasets that include both Gaussian noise and noise-free versions.

This study focuses on achieving hierarchical optimal synchronization in a fractional-order nonlinear multi-agent system (FONMAS) composed of a single leader and multiple followers, analyzed within the framework of Stackelberg–Nash game theory. The leader makes decisions by anticipating the optimal responses of all followers, whereas each follower concurrently reacts optimally to the leader's strategy by engaging in a Nash game. To obtain the optimal control policy of the FONMAS, a regularized fuzzy reinforcement learning approach is proposed. First, a fractional-order (FO) Hamilton–Jacobi–Bellman (HJB) equation in coupled form is formulated, which serves as the basis for deriving the optimal control policies of both the leader and the followers. It is further proven that these strategies constitute a Stackelberg–Nash equilibrium (SNE). Next, due to the asymmetry among agents, solving the FO coupled HJB equations becomes challenging. To address this, a hierarchical learning framework grounded in FO value iteration is proposed, which depends solely on partial knowledge of the system dynamics. We demonstrate that, given mild coupling assumptions, this method converges asymptotically to equilibrium policies. Furthermore, a regularized actor–critic (A-C) framework with fuzzy logic is employed to estimate the cost function and optimal control policy, and the FO weight update rules are developed by formulating a Lyapunov function for the optimal fuzzy weight deviation, ensuring convergence to optimal weight values. Ultimately, both theoretical analysis and simulation results support the efficiency of the proposed method.

Fuzzy Broad Learning System (Fuzzy BLS) constitutes an effective neural network architecture that has demonstrated remarkable efficacy across various real-world application domains. Nonetheless, Fuzzy BLS may result in suboptimal performance and face challenges in effectively addressing the issue of imbalanced classification. To tackle the challenge mentioned above, a novel Mixture-of-Expert-based Fuzzy Broad Learning System (MFBLS) is proposed. In MFBLS, a fuzzy system is integrated to deal with the fuzziness of input data. Concurrently, based on the advantages of the Mixture-of-expert framework, the feature weight of each expert system is dynamically adjusted via a gating network to enhance the importance of key features, thereby enhancing the overall capability of the model. Besides, several classical over-sampling techniques are employed to address sample imbalance in datasets to achieve a more balanced class distribution. Subsequently, the Extreme Gradient Boosting (XGBoost) algorithm is utilized on the oversampled dataset for feature selection, aiming to enhance the efficiency and the predictive precision of subsequent model training in MFBLS. Finally, through a comparative analysis of state-of-the-art machine learning methods, the superiority of MFBLS in handling imbalanced datasets is validated through a series of experimental evaluations on various imbalanced datasets.

The fuzzy broad learning system (FBLS) has received increasing attention due to its ability to quickly train from broad learning systems (BLS) and interpretability with fuzzy inference. However, the randomness of BLS brings instability to the training performance of the model, so the hyperparameters of the model are crucial for its performance. Currently, many FBLS use grid search to determine hyperparameters. However, grid search brings longer search time and the parameters obtained have randomness, which may not necessarily be the optimal hyperparameters. In response to these challenges, this paper proposes a fuzzy broad learning system with automatic determination of hyperparameters (ADHFBLS). We construct a novel FBLS based on the interval type-2 fuzzy set and design an incremental learning algorithm for rules and enhancement nodes to support rapid model expansion. Meanwhile, a heuristic hyperparameter automatic optimization algorithm is designed to overcome the randomness and long optimization time of grid search. Experiments have shown that ADHFBLS has higher accuracy and shorter model tuning time compared to some state-of-the-art models based on FBLS.

Hypergraph representation learning (HGRL) has attracted widespread attention for its ability to capture high-order relationships (simultaneous interactions among multiple entities) in hypergraphs. However, most existing HGRL methods struggle with uncertainties throughout HGRL processes, including input signals, message passing, and inference. These uncertainties, such as redundant or noisy attributes, distorted structures, noisy node/hyperedge representations, and parameter estimation biases, undermine model robustness and reliability. To address this issue, we introduce fuzzy logic into HGRL for the first time, and propose a new HGRL framework called fuzzy hypergraph representation learning and inference (FHRLI). It effectively manages uncertainties from both data and model perspectives, resulting in more expressive representations. In addition, it allows for more precise and robust inference based on uncertain evidence. Contemplating the influence of label scarcity and uncertainties (annotation errors), we further develop an unsupervised HGRL algorithm, named fuzzy hypergraph contrastive representation learning (FHCRL), by combining the proposed FHRLI framework with hypergraph contrastive learning. Extensive experiments across various tasks verify the effectiveness and competitiveness of the proposed FHRLI framework and FHCRL compared to the state-of-the-art baselines. Furthermore, we experimentally demonstrate that the proposed FHRLI framework can achieve superior robustness and wide universality, along with providing a certain explanatory analysis.

In this study, a novel fault-tolerant broad fuzzy learning control scheme is proposed for a flexible single-link manipulator with input delay and output constraints. The broad fuzzy neural network is utilized to effectively approximate the time delay of the controller and compensate for the unknown nonlinear uncertainties. By applying the Lyapunov direct method and barrier Lyapunov function, the semi-global uniformly ultimately boundedness (SGUUB) of the system is demonstrated, which guarantees that all system states converge to zero within the specified limitation. Finally, the simulation and experiment results, compared with those of different neural networks, manifest the validity of the proposed control method.

This article focuses on studying an adaptive fuzzy predefined-time tracking control problem for uncertain high-order nonlinear interconnected systems with input quantization. The considered plants contain unknown nonlinear functions, quantized input signals, and external disturbances. Fuzzy logic systems (FLSs) are employed to estimate the unknown nonlinear functions, and by using its structural properties, the difficulty of designing the state variable functions is simplified. By employing adaptive backstepping recursive technique combined with power-based Lyapunov functions, the predefined-time control strategy is presented. Notably, a novel predefined-time filter is used to avoid repeated differentiation of virtual control functions. By applying predefined-time Lyapunov stability theory, the stability analysis demonstrates that all signals in the closed-loop systems remain bounded and the tracking error converges within a predefined settling time. Ultimately, a simulation example is provided to illustrate the validity of the proposed control strategy.

Hyperspectral images (HSIs) contain rich spatial and spectral information, while light detection and ranging (LiDAR) data can provide elevation details. Effectively fusing HSI and LiDAR data can help achieve more accurate classification results. However, the joint classification of HSI and LiDAR data still faces several challenges, such as the redundancy of HSI spectral bands, the limitations of singular multimodal data fusion strategy, and the high cost of pixelwise labeling in remote sensing images. To tackle these challenges, we propose a classification method based on candidate pseudo labels pruning and dual mixture of experts (CPLP-DMoEs). First, we employ the multihead mixture of bands (MMoBs) to perform diverse, dense mixing of spectral bands, thereby alleviating the issue of high similarity between adjacent bands. Then, to overcome the limitations of single fusion strategies, we design a mixture of multimodal fusion expert (MoMFE) mechanism, which selects and mixes multiple fusion experts (FEs) to achieve diverse feature fusion of HSI and LiDAR data. Next, we introduce information entropy to balance the selection of FEs. Finally, facing the challenge of limited labeled samples, we propose a candidate pseudo labels pruning (CPLP)-based semi-supervised learning method. CPLP can prune the candidate pseudo label set from both intrasample and intersample perspectives to obtain more reliable pseudo labels, thereby facilitating the learning of a more accurate classification model. The experimental results on three datasets, including Houston 2013, MUUFL, and Augsburg, validate the effectiveness of the proposed method.

Conventional models for hyperspectral image (HSI) classification usually demand a substantial quantity of labeled training data. However, when labeled training HSIs are unavailable or have different distributions from test HSIs, many classification models tend to exhibit significant performance declines. For the cross-scene HSI classification task, unsupervised domain adaptation (UDA) technique has been widely developed. Existing discrepancy-based or adversarial-based UDA methods may fail to learn discriminative class boundaries when large class distribution shift (CDS) exists. To alleviate this limitation, we propose the model named spatially enhanced refined classifier (SERC), which includes a coarse classifier (CC) and a refined classifier (RC). The RC constructs a memory module to fuse global-spatial and spectral information simultaneously and uses the neighborhood aggregation technique to generate the refined predictions. The refined predictions are then transferred to pseudolabels to train the CC. Thereby, a mutually reinforcing relationship between the two classifiers is established. Furthermore, we propose the class distribution match (CDM) strategy to further alleviate the serious CDS problem. Notably, SERC does not require additional training parameters, which are commonly used in existing UDA methods. Despite its simplicity, SERC achieves outstanding results. Our method has been extensively evaluated on three public HSI datasets and has shown superior performance compared with state-of-the-art (SOTA) approaches. The source code can be found athttps://github.com/Wangzs0228/SERC.

With the rapid advancements in deep learning technology, the field of remote sensing change detection (RSCD) has witnessed significant improvements and innovations. In this context, bitemporal image processing, using features directly extracted by the backbone for subsequent fusion operations, may be obstructed by external environmental factors, potentially limiting the effective capture of complex feature variations. Moreover, overlooking local features during the fusion of bitemporal features can significantly affect the final detection results. As a result, achieving accurate change detection (CD) still encounters various challenges. To tackle these issues, this paper proposes a CD network (AEGL-Net) with Adaptive Multiscale Enhancement (AME) and Global-Local Feature Fusion (GLFF) modules. First, AME enhances features at each stage of backbone extraction through an adaptive strategy, balancing the enhancement of semantic information and texture details. Then, GLFF is used to fuse the bitemporal image features, which enhances the modeling of global dependencies while also fusing shared and context-aware weights to enhance the local features. Finally, the merged features are fed into the decoder to generate precise change maps. Experiments conducted with four open RSCD datasets (LEVIR-CD, S2Looking, SYSU-CD, and UAV-CD) demonstrate that our proposed AEGL-Net outperforms ten state-of-the-art models in the RSCD field. Our code is available at https://github.com/yikuizhai/AEGL-Net.

Although deep learning has advanced remote sensing change detection (RSCD), most methods rely solely on image modality, limiting feature representation, change pattern modeling, and generalization—especially under illumination and noise disturbances. To address this, we propose MMChange, a multimodal RSCD method that combines image and text modalities to enhance accuracy and robustness. An Image Feature Refinement (IFR) module is introduced to highlight key regions and suppress environmental noise. To overcome the semantic limitations of image features, we employ a vision-language model (VLM) to generate semantic descriptions of bi-temporal images. A Textual Difference Enhancement (TDE) module then captures fine-grained semantic shifts, guiding the model toward meaningful changes. To bridge the heterogeneity between modalities, we design an Image-Text Feature Fusion (ITFF) module that enables deep cross-modal integration. Extensive experiments on LEVIR-CD, WHU-CD, and SYSU-CD demonstrate that MMChange consistently surpasses state-of-the-art methods across multiple metrics, validating its effectiveness for multimodal RSCD. Code is available at: https://github.com/yikuizhai/MMChange.

This article aims to address the distributed robust platooning control of connected automated vehicles (CAVs) with general unknown uncertain dynamics. Despite recent progress in this area, achieving the objective of distributed robust platooning control for CAVs with limited communication resources and uncertain dynamics is an outstanding problem. To solve such a problem, a new Zeno-free event-triggered scheme is successfully established to determine whether the vehicle's state should be sampled and transmitted among the interacting vehicles. An adaptive law for updating the weighting matrix for the neural network approximator is designed, where the relative state variables are utilized only at triggered instants. Moreover, such a neuro-adaptive approach incorporates a low-pass filter structure to effectively mitigate undesirable high-frequency oscillations that may arise with the application of high-gain learning rates. Following this, a new class of distributed event-based neuro-adaptive control protocols is meticulously designed to guarantee the uniform ultimate boundedness of spacing error, relative velocity, and relative acceleration of the whole platoon. Finally, simulation examples with different scenarios are conducted, and it is interesting to find that the proposed protocol has a lower average communication rate than traditional ones without the low-pass filter structure.

Since cross-modal hashing requires minimal storage and computation, it is becoming increasingly popular with the exponential growth of multimedia content on the internet. However, the lack of accurate supervisory data has curtailed the effectiveness of unsupervised hashing techniques. Conversely, supervised hashing strategies necessitate considerable human and financial resources for data annotation. To address this limitation, we propose a novel semi-supervised cross-modal hashing method called Enhanced Cross-Modal Hashing via Hybrid Distillation and Structural Refinement (HDSR). Specifically, we first learn the features of inter-modal and inter-instance similarity relationships through pointwise semantic alignment and listwise similarity partial order learning, respectively, to extract refined structural representations from partially labeled data. Secondly, by fusing inter-modal similarity to construct higher-order affinity matrices, we precisely delineate the semantic correlation information across cross-modal data, facilitating stable self-supervised training of unlabeled data through the application of momentum fusion strategies. Finally, the refined structural representation of labeled data is transferred into unlabeled branches through hybrid distillation, enhancing the performance of cross-modal hash learning by generating compact and accurate hash codes. The proposed HDSR is compared with several state-of-the-art deep cross-modal hashing methods on three widely used benchmark databases, and the experimental results verify its efficiency and superiority.

The encoder-decoder architecture is a prevailing paradigm for semantic segmentation. It has been discovered that aggregation of multi-stage encoder features plays a significant role in capturing discriminative pixel representation. In this work, we rethink feature reconstruction for scale alignment of multi-stage pyramidal features and treat it as a Query Update (Q-UP) task. Pixel-wise affinity scores are calculated between the high-resolution query map and low-resolution feature map to dynamically broadcast low-resolution pixel features to match a higher resolution. Unlike prior works (e.g. bilinear interpolation) that only exploit sub-pixel neighborhoods, Q-UP samples contextual information within a global receptive field via a data-dependent manner. To alleviate intra-category feature variance, we substitute source pixel features for feature reconstruction with their corresponding category prototype that is assessed by averaging all pixel features belonging to that category. Besides, a memory module is proposed to explore the capacity of category prototypes at the dataset level. We refer to the method as Category Prototype Transformer (CPT). We conduct extensive experiments on popular benchmarks. Integrating CPT into a feature pyramid structure exhibits superior performance for semantic segmentation even with low-resolution feature maps, e.g. 1/32 of the input size, significantly reducing computational complexity. Specifically, the proposed method obtains a compelling 55.5% mIoU with greatly reduced model parameters and computations on the challenging ADE20K dataset.

The CLIP visual feature-based image captioning models have developed rapidly and achieved remarkable results. However, existing models still struggle to produce descriptive and discriminative captions because they insufficiently exploit fine-grained visual cues and fail to model complex vision-language alignment. To address these limitations, we propose a Ranking Diffusion Transformer (RDT), which integrates a Ranking Visual Encoder (RVE) and a Ranking Loss (RL) for fine-grained image captioning. The RVE introduces a novel ranking attention mechanism that effectively mines diverse and discriminative visual information from CLIP features. Meanwhile, the RL leverages the ranking of generated caption quality as a global semantic supervisory signal, thereby enhancing the diffusion process and strengthening vision-language semantic alignment. We show that by collaborating RVE and RL via the novel RDT-and by gradually adding and removing noise in the diffusion process-more discriminative visual features are learned and precisely aligned with the language features. Experimental results on popular benchmark datasets demonstrate that our proposed RDT surpasses existing state-of-the-art image captioning models in the literature. The code is publicly available at: https://github.com/junwan2014/RDT.

For the maritime environment with limited communication bandwidth at sea, this paper investigates the distributed unmanned surface vehicles (USVs) formation tracking control problem with input and state quantization based on a time-varying threshold event-triggered mechanism. While ensuring that each follower USV can quickly form a formation and follow the virtual leader on the desired trajectory, it reduces the execution frequency of the controller, decreases the control amplitude, and saves communication resources. Firstly, a distributed event-triggered extended state observer (ESO) is designed to observe the virtual leader’s position information, and another ESO is used to estimate the quantized state information of each USV and the uncertainty terms existing in the model. Subsequently, the kinematic guidance law and the kinetic control laws based on a time-varying threshold event-triggered mechanism are proposed in quantized environment using the hierarchical design approach. In addition, the linear splitting of the input quantization makes the designed controller no longer require a priori information on the quantization parameters. Finally, the stability of the designed distributed USV formation tracking control system with input and state quantization based on the time-varying threshold event-triggered mechanism is demonstrated by input-to-state stability theory, and the absence of Zeno behavior in the proposed control strategy is also verified. Three sets of simulation experiments demonstrate the effectiveness and scientific validity of the proposed method.

Accurate performance and low energy consumption are essential for trajectory tracking control of an underactuated surface vessel (USV) to satisfy marine operation requirements. This paper studies the user-specified optimal tracking control problem for the USV in the presence of modeling uncertainties. A fuzzy weights-based adaptive reinforcement learning (RL) control scheme is developed to achieve the tracking control with the predefined convergence time and steady-state accuracy while minimizing the performance index function. The constructed performance index function includes the surge velocity control law and the constrained position tracking error. Following that, an optimal backstepping design frame is proposed to derive the controllers with unknown gradient terms by constructing the error subsystems at the kinematic and kinetic levels of the USV. Then, a fuzzy reinforcement learning algorithm (FRLA) is presented to derive the optimal control solutions of corresponding error subsystems. Since the fuzzy basis function vectors derived from measured states of the USV system may be zero vectors, the persistence excitation condition may not always be satisfied. Thus, in the design of fuzzy RL updating laws of critics and actors, a positive parameter compensation technique is proposed to make the matrixes consist of fuzzy basis functions strictly positive definite. It releases the need for assumption of persistence excitation, and the convergence of the critic weight estimate and the boundedness of closed-loop systems can be guaranteed. Finally, the effectiveness of the presented method is demonstrated by numerical simulations and real-world experiments.

Multi-modal emotion recognition (MER) integrates multi-modal signals to help computers comprehensively understand human emotions, which is a crucial technology in human-computer interactions. However, the amount of labeled multi-modal emotion data is small and limits MER performance due to its expensive manual annotations. Meanwhile, semi-supervised learning (SSL) methods improving MER models with enormous unlabeled data suffer from confirmation bias, resulting in biased data distribution. To tackle these challenges, this paper proposes a cyclic data distillation semi-supervised learning (CDD-SSL) for MER tasks. CDD-SSL leverages multiple pre-trained unimodal teacher models and confidence-boosting pseudo-labelling (CBPL) to boost the confidence of multi-modal ensemble outputs and distill reliable and class-representative data from numerous unlabeled data. It then utilizes reliable and less-biased data to train a multi-modal student model and provides feedback to update all unimodal teacher models. CDD-SSL is a cyclic teacher-student framework with a feedback mechanism that gradually mitigates confirmation bias and obtains an effective MER model. Experimental results on four benchmark datasets demonstrate that CDD-SSL achieves superior performance over both the semi-supervised methods and the state-of-the-art fully-supervised models in MER tasks.

Semi-supervised multi-label learning (SSMLL) involves learning a multi-label classifier from a small set of labeled data and a large set of unlabeled data. Label enhancement (LE), accounting for the relative importance of labels, has been effective in improving the performance of supervised multi-label learning models. Nevertheless, generating a robust SSMLL model with LE based on incomplete label information remains challenging. In this paper, we pioneer the idea of applying LE to SSMLL. First, we design a kNN aggregation-based method, aiming to assign pseudo-labels to unlabeled data and perform the LE process by aggregating label information from neighboring instances. Leveraging the topological structure of the feature space is an effective LE approach for training. However, LE, decoupled from the training process, lacks the dynamic feedback of the training model. To improve this, we incorporate a label propagation mechanism that iteratively optimizes the LE process with the guidance of the available label information. Moreover, we consider local label correlations according to local linear embedding to further enhance the generalization ability of the learning model. Extensive experiments demonstrate that the proposed approach can effectively recover latent label information, resulting in significant performance improvement in SSMLL.

Space-air-ground (SAG) integrated heterogenous networks can provide pervasive intelligence services for various ground users (GUs). The network can help cellular networks release network resources and alleviate congestion pressure. Moreover, one important application of the network is that digital twin (DT) can enable nearly-instant wireless connectivity and highly-reliable data mapping from physical systems to digital world in a real-time fashion. The integration of SAG and DT (SAG-DT) reduces the gap between data analysis and physical status, which can further realize robust edge intelligence services. However, the random computation task arrival, time-varying channel gains, and the lack of mutual trust among ground GUs hinder better quality of service in the promising SAG-DT network. In this paper, we envision a SAG-DT integrated blockchain model to transfer the task data to the aerial network, and then perform the computation offloading, energy harvesting and privacy protection. Moreover, we propose a Lyapunov-aided multi-agent deep federated reinforcement learning (MADFRL) algorithm framework to optimize the CPU cycle frequency, the size of block, the number of DTs, and harvested energy to minimize the execution costs and privacy overhead. Extensive performance analyses indicate that the MADFRL algorithm framework can strengthen the data privacy via blockchain verification mechanism and approaches the optimal performance on the basis of lower computation complexity. Finally, simulation results corroborate that the proposed Lyapunov-aided MADFRL algorithm is superior to advanced benchmarks in terms of execution costs, task processing quantities and privacy overhead.

Over the past decade, low-Earth-orbit (LEO) satellite networks have emerged as a critical infrastructure in communication systems, providing wide coverage, high reliability, and global connectivity. Recently, the development of 6G technologies has challenged the LEO satellite networks to guarantee deterministic scheduling for time-sensitive services. However, traditional deterministic networking techniques fall short for LEO satellite networks. First, these techniques impose strict time constraints, but in LEO satellite networks, delay and jitter typically range in the tens of milliseconds, which exceed these limits and render them infeasible. Second, the dynamic topologies of LEO satellite networks challenge the inflexible scheduling strategies generated by these techniques, leading to sub-optimal performance and potential strategy failures. To tackle the first problem, we propose a Cycle Specified Queuing and Forwarding (CSQF) based deterministic flows scheduling mechanism. It relaxes strict time constraints by employing cyclic multi-queue scheduling, enabling more flexible and reliable long-distance transmission. For the second problem, we propose a learning-based swarm intelligence method for deterministic flows scheduling in dynamic LEO satellite networks. It includes an algorithm that combines a Dynamic Graph Convolutional Network (DGCN) with an Adaptive Ant Colony Optimization (ACO) algorithm, referred to as the DGCN-ACO algorithm. The DGCN captures the dynamic feature of the network and generates the heuristic information. The Adaptive ACO utilizes the heuristic information and considers each flow's attribute to generate multi-path scheduling strategies for each deterministic flow, as well as updates the DGCN. The experiment results demonstrate the effectiveness of our proposed algorithm.

The reuse of 3D CAD models is crucial for industrial manufacturing because it shortens development cycles and reduces costs. Significant progress has been made in deep learning-based 3D model retrievals. There are many representations for 3D models, among which the multi-view representation has demonstrated a superior retrieval performance. However, directly applying these 3D model retrieval approaches to 3D CAD model retrievals may result in issues such as the loss of the engineering semantic and structural information. In this paper, we find that multiple views and B-rep can complement each other. Therefore, we propose the view graph neural network (VGNet), which effectively combines multiple views and B-rep to accomplish 3D CAD model retrieval. More specifically, based on the characteristics of the regular shape of 3D CAD models, and the richness of the attribute information in the B-rep attribute graph, we separately design two feature extraction networks for each modality. Moreover, to explore the latent relationships between the multiple views and B-rep attribute graphs, a multi-head attention enhancement module is designed. Furthermore, the multimodal fusion module is adopted to make the joint representation of the 3D CAD models more discriminative by using a correlation loss function. Experiments are carried out on a real manufacturing 3D CAD dataset and a public dataset to validate the effectiveness of the proposed approach.

The human skeleton establishment aims to provide accurate localization information of the human body from RGB images and establish a complete human skeleton for many applications, such as action recognition, video surveillance, and human-computer interaction. Considering the inherent human body structure, many recent methods group the relevant body parts and utilize the deep convolutional network to learn the visual context from the part groups. However, the grouping approaches used in these methods heavily rely on prior knowledge of the human body shape but lose important relationships between parts. In this paper, we introduce the Accurate Part Grouping Network (Accurate-PGNet), a novel network for hierarchically grouping body parts in a data-driven manner. In contrast to the previous methods, we use neural architecture search (NAS) to optimize the architecture of Accurate-PGNet and properly group the body parts. The part grouping respects the diverse visual patterns of parts, producing groups containing different body parts. From each group, we learn the visual feature map. It helps to capture the correlation between parts and predict their locations. The feature maps of the part groups are merged hierarchically to capture the higher-order context of parts in larger groups. We extensively evaluated our method on the challenging benchmarks, demonstrating that Accurate-PGNet effectively helps to achieve state-of-the-art results.

As an effective alternative to deep neural networks, broad learning system (BLS) has attracted more attention due to its efficient and outstanding performance and shorter training process in classification and regression tasks. Nevertheless, the performance of BLS will not continue to increase, but even decrease, as the number of nodes reaches the saturation point and continues to increase. In addition, the previous research on neural networks usually ignored the reason for the good generalization of neural networks. To solve these problems, this article first proposes the Extreme Fuzzy BLS (E-FBLS), a novel cascaded fuzzy BLS, in which multiple fuzzy BLS blocks are grouped or cascaded together. Moreover, the original data is input to each FBLS block rather than the previous blocks. In addition, we use residual learning to illustrate the effectiveness of E-FBLS. From the frequency domain perspective, we also discover the existence of the frequency principle in E-FBLS, which can provide good interpretability for the generalization of the neural network. Experimental results on classical classification and regression datasets show that the accuracy of the proposed E-FBLS is superior to traditional BLS in handling classification and regression tasks. The accuracy improves when the number of blocks increases to some extent. Moreover, we verify the frequency principle of E-FBLS that E-FBLS can obtain the low-frequency components quickly, while the high-frequency components are gradually adjusted as the number of FBLS blocks increases.

Weakly supervised object classification and localization are learned object classes and locations using only image-level labels, as opposed to bounding box annotations. Conventional deep convolutional neural network (CNN)-based methods activate the most discriminate part of an object in feature maps and then attempt to expand feature activation to the whole object, which leads to deteriorating the classification performance. In addition, those methods only use the most semantic information in the last feature map, while ignoring the role of shallow features. So, it remains a challenge to enhance classification and localization performance with a single frame. In this article, we propose a novel hybrid network, namely deep and broad hybrid network (DB-HybridNet), which combines deep CNNs with a broad learning network to learn discriminative and complementary features from different layers, and then integrates multilevel features (i.e., high-level semantic features and low-level edge features) in a global feature augmentation module. Importantly, we exploit different combinations of deep features and broad learning layers in DB-HybridNet and design an iterative training algorithm based on gradient descent to ensure the hybrid network work in an end-to-end framework. Through extensive experiments on caltech-UCSD birds (CUB)-200 and imagenet large scale visual recognition challenge (ILSVRC) 2016 datasets, we achieve state-of-the-art classification and localization performance.

The dynamic neural network (DNN), in contrast to the static counterpart, offers numerous advantages, such as improved accuracy, efficiency, and interpretability. These benefits stem from the network's flexible structures and parameters, making it highly attractive and applicable across various domains. As the broad learning system (BLS) continues to evolve, DNNs have expanded beyond deep learning (DL), orienting a more comprehensive range of domains. Therefore, this comprehensive review article focuses on two prominent areas where DNN structures have rapidly developed: 1) DL and 2) broad learning. This article provides an in-depth exploration of the techniques related to dynamic construction and inference. Furthermore, it discusses the applications of DNNs in diverse domains while also addressing open issues and highlighting promising research directions. By offering a comprehensive understanding of DNNs, this article serves as a valuable resource for researchers, guiding them toward future investigations.

The broad learning system (BLS) has recently been applied in numerous fields. However, it is mainly a supervised learning system and thus not suitable for specific practical applications with a mixture of labeled and unlabeled data. Despite a manifold regularization-based semi-supervised BLS, its performance still requires improvement, because its assumption is not always applicable. Therefore, this article proposes an incremental-self-training-guided semi-supervised BLS (ISTSS-BLS). Distinctive to traditional self-training, where all unlabeled data are labeled simultaneously, incremental self-training (IST) obtains unlabeled data incrementally from an established sorted list based on the distance between the data and their cluster center. During iterative learning, a small portion of labeled data is first used to train BLS. The system recursively self-updates its structure and meta-parameters using: 1) the double-restricted mechanism and 2) the dynamic neuron-incremental mechanism. The double-restricted mechanism is beneficial to preventing the introduction of incorrect pseudo-labeled samples, and the dynamic neuron-incremental mechanism guides the self-updating of the network structure effectively based on the training accuracy of the labeled data. These strategies guarantee a parsimonious model during the update. Besides, a novel metric, the accuracy-time ratio (A/T), is proposed to evaluate the model's performance comprehensively regarding time and accuracy. In experimental verifications, ISTSS-BLS performs outstandingly on 11 datasets. Specifically, the IST is compared with the traditional one on three scales data, saving up to 52.02% learning time. In addition, ISTSS-BLS is compared with different state-of-the-art alternatives, and all results indicate that it possesses significant advantages in performance.

Time-series anomaly detection has gained considerable prominence in numerous practical applications across various domains. Nonetheless, the scarcity of labels leads to the neglect of anomalous patterns in data, as well as the inherent complexities and variances in the definitions of temporal anomalies, pose significant challenges for insufficient recognition of anomaly patterns. In addition, real-time anomaly detection poses high demands on low computational cost and model robustness, presenting substantial obstacles for unsupervised time-series anomaly detection. In this article, we propose the data-driven spontaneous perturbation based on the sequence-image strategy and temporal anomaly knowledge enhancement strategy based on artificial anomalous data pairs to enhance the cognition of abnormal knowledge in unsupervised scenarios. On this basis, we propose the denoising autoencoder based on the broad learning system (DBLS-AE), which sufficiently learns the anomalous patterns, achieving efficient anomaly detection with low computational costs. To enhance the robustness in handling complex and diverse temporal anomalies, we further propose the progressive diversity denoising autoencoders based on the broad learning system (PddBLS-AE), which gradually prioritizes challenging samples and constructs a diverse ensemble of DBLS-AEs, markedly improving both performance and robustness. By innovatively utilizing the broad learning system (BLS), PddBLS-AE achieves accelerated training compared with advanced deep learning models. Comprehensive evaluations across multiple datasets robustly substantiate the efficacy of PddBLS-AE.

The convolutional neural network (CNN) and transformer have gained significant attention in the field of single image super-resolution (SISR), owing to their powerful capacity in nonlinear feature extraction. Nonetheless, these two types of approaches hold their own limitations. For instance, the interaction between convolutional kernels and image content is agnostic in CNN, while the computational complexity increases quadratically along with the spatial resolution in the transformer. To address these concerns, in this article, we propose a novel unified framework named transformer and convolution coupled contrastive network (TC3Net) for SISR, which holds a triple-branch structure to integrate the merits of both CNN and transformer. The proposed TC3Net is mainly composed of several stacked CNN feature extraction (CFE) blocks, transformer feature extraction (TFE) blocks, and coupled contrastive blocks (CCBs) for diverse feature extraction. Particularly, the CCB that consists of the coupled attention block (CAB) and the local-global feature extraction (LGFE) block is designed to fuse feature maps and extract coupled information for better image reconstruction. Moreover, a contrastive loss between the transformer and CNN feature maps is further introduced to enhance their discriminative characteristics and complement the fused features. Experimental results demonstrate that TC3Net outperforms several state-of-the-art (SOTA) methods in the aspect of achieving a better balance between model size and performance.

The popular multiagent reinforcement learning (MARL) methods primarily focus on exploring the capability of value functions to facilitate multiagent coordination. These MARL methods, following the centralized training with decentralized execution (CTDE) paradigm, tend to design ingenious network architectures while overlooking the impact of coordination through expanding local observation information. To tackle this deficiency, we model the multiagent systems (MASs) as a graph and use a graph neural network (GNN) to extract rich information between one agent and the others efficiently. Moreover, we propose a multigraph-neural-network information representation (MGIR) method that uses the power of GNN in local observation information extraction, enabling the acquisition of higher quality information. Specifically, multiple GNNs are used during centralized training to characterize the MAS from different perspectives and extract representations of latent variables. During distributed execution, these latent variables are leveraged to expand local observation information. Extensive comparative experiments substantiate that our proposed MGIR demonstrates superior coordination performance when compared with baseline methods. In addition, it can be flexibly integrated into various value function decomposition methods of MARL.

To meet requirements for real-time trajectory scheduling and distributed coordination, underwater target hunting task is challenging in terms of turbulent ocean environments and dynamic adversarial environment. Despite the existing research in game-based target hunting area, few approaches have considered dynamic environmental factors, such as sea currents, winds, and communication delay. In this article, we focus on a target hunting system consisted of multiple unmanned underwater vehicles (UUVs) and a target with high maneuverability. Besides, differential game theory is leveraged to analyze adversarial behaviors between hunters and the escapee. However, it is intractable that UUVs have to deploy an adaptive scheme to guarantee the consistency and avoid the escape of the target without collision. Therefore, we conceive the Hamiltonian function with Leibniz's formula to obtain feedback control policies. In addition, it proves that the target hunting system is asymptotically stable in the mean, and the system can satisfy Nash equilibrium relying on the proposed control policies. Furthermore, we design a modified multiagent reinforcement learning (MARL) to facilitate the underwater target hunting task under the constraints of energetic flows and acoustic propagation delay. Simulation results show that the proposed scheme is superior to the typical MARL algorithm in terms of reward and success rate.

Due to the complexity and self-evolutionary property of graph data in reality, graph learning methods require both validity to represent unstructured data and scalability to adapt to evolving graphs. However, current works have representation learning limitations on optimizable graph feature space due to the bottleneck of the structure depth. Moreover, they encounter a complete retraining process when graphs evolve, especially in the case without the assistance of new labels. To address the above issues, we propose a scalable graph broad network (SGB-Net), which contains three proposed modules: the graph feature broad transformation layer (GFBT layer) for enhancing graph embedding and two update algorithms (SGB-Net-U, SGB-Net-S) for endowing scalability. The GFBT layer aims to explicitly expand the graph feature space and broadly build the model. It constructs two expandable feature spaces in various graph scales to embed graphs discriminatively. SGB-Net-U is an exploratory method designed to tackle the label-free graph incremental learning (GIL) problem by leveraging unsupervised incremental knowledge to expand graph representation. SGB-Net-S endows scalability in classical incremental learning scenarios involving labels. Benefiting from its broad construction framework, SGB-Net not only enhances graph embeddings but also seamlessly adapts and improves performance in response to graph expansion without requiring retraining. In the experiments conducted on 15 benchmark datasets, SGB-Net outperforms state-of-the-art GNNs in terms of both effectiveness and scalability.

Developing a distributed bipartite optimal consensus scheme while ensuring user-predefined performance is essential in practical applications. Existing approaches to this problem typically require a complex controller structure due to adopting an identifier-actor-critic framework and prescribed performance cannot be guaranteed. In this work, an adaptive critic learning (ACL)-based optimal bipartite consensus scheme is developed to bridge the gap. A newly designed error scaling function, which defines the user-predefined settling time and steady accuracy without relying on the initial conditions, is then integrated into a cost function. The backstepping framework combines the ACL and integral reinforcement learning (IRL) algorithm to develop the adaptive optimal bipartite consensus scheme, which contributes a critic-only controller structure by removing the identifier and actor networks in the existing methods. The adaptive law of the critic network is derived by the gradient descent algorithm and experience replay to minimize the IRL-based residual error. It is shown that a compute-saving learning mechanism can achieve the optimal consensus, and the error variables of the closed-loop system are uniformly ultimately bounded (UUB). Besides, in any bounded initial condition, the evolution of bipartite consensus is limited to a user-prescribed boundary under bounded initial conditions. The illustrative simulation results validate the efficacy of the approach.

Temporal link prediction is one of the most important tasks for predicting time-varying links by capturing dynamics within complex networks. However, it suffers from difficulties such as vulnerability to adversarial attacks and inadaptation to distinct evolutionary patterns. In this article, we propose a robust temporal link prediction architecture via stable gated models with reinforcement learning (SAGE-RL) consisting of a state encoding network (SEN) and a self-adaptive policy network (SPN). The former is utilized to capture network dynamics, while the latter helps the former adapt to distinct evolutionary patterns across various time periods. Within the SEN, a novel stable gate is introduced to ensure multiple spatiotemporal dependency paths and defend against adversarial attacks. An SPN is proposed to select different SEN instances by approximating the optimal action function, thereby adapting to various evolutionary patterns to learn the robust temporal and structural features from dynamic complex networks. It is proven that SAGE-LR with integral Lipschitz graph convolution is stable to relative perturbations in dynamic complex networks. With the aid of extensive experiments on five real-world graph benchmarks, SAGE-LR is shown to substantially outperform current state-of-the-art approaches in terms of precision and stability of temporal link prediction and ability to successfully defend against various attacks. We also implement the temporal link prediction in shipping transaction networks, which forecast effectively its potential transaction risks.

The multisource unsupervised domain adaptation (MUDA) scenario poses a significant challenge in the field of intelligent fault diagnosis (IFD), where the goal is to transfer the knowledge learned from multiple labeled source domains to an unlabeled target domain. Existing IFD-oriented MUDA approaches frequently fail to recognize the distinct importance of each source domain relative to specific target samples, or lack flexibility in integrating diagnostic insights from multiple sources. In response, a novel MUDA approach is proposed for IFD, termed point-to-set metric-gated mixture of experts (PSMMoEs). This method leverages a mixture-of-experts (MoEs) framework to automatically integrate the complementary information from multiple source domains. It develops a deep point-to-set distance (PSD) metric learning technique within the MoE's gating mechanism, effectively fusing domain-specific features by assessing the similarity between individual target samples and each source domain. The method ensures balanced training across progressive stages, harmonizing multitask learning with joint training for the MoE framework. Furthermore, a multilayer maximum mean discrepancy (MMD) measurement is employed for domain alignment, ensuring feature alignment across different domains at multiple levels. In order to assess the efficacy of the proposed method, it is compared with several leading domain adaptation methods on publicly available and laboratory-based rotating machinery fault datasets. The experimental results demonstrate superior classification and adaptation capabilities of the proposed fault diagnosis method.

Graph convolutional networks (GCNs) have shown great prowess in learning topological relationships among electroencephalogram (EEG) channels for EEG-based emotion recognition. However, most existing GCN-only methods are designed with a single spatial pattern, lacking connectivity enhancement within local functional regions and ignoring the data dependencies of EEG original data. In this article, hierarchical dynamic GCN (HD-GCN) is proposed to explore dynamic multilevel spatial information among EEG channels, with discriminative features of EEG signals as auxiliary information. Specifically, representation learning in topological space consists of two branches: one for extracting global dynamic information and one for exploring augmentation information in local functional regions. In each branch, a layerwise adjacency matrix is utilized to enrich the expressive power of GCN. Furthermore, a data-dependent auxiliary information module (AIM) is developed to capture multidimensional fusion features. Extensive experiments on two public datasets, SJTU emotion EEG dataset (SEED) and DREAMER, demonstrate that the proposed method consistently exceeds state-of-the-art methods. Interpretability analysis of the proposed model is performed, discovering the active brain regions and important electrode pairs related to emotion.

Real-world data tends to exhibit an inherent hierarchical structure, providing a natural multiview perspective where features at different scales can be treated as distinct views. However, most existing multiview clustering algorithms primarily focus on the inter-sample relationships at a single level. These methods overlook the hierarchical structures present in the data and are specifically designed for native multiview data. This article introduces a comprehensive multiview clustering framework that transforms both typical data and images into a unified multiview feature representation. The framework allows for extracting multiscale features from the raw data and clustering different types of data with the same algorithm. A novel scale-driven pre-processing approach unifies the feature structure across various data types and explores local relationships among samples at multiple scales. Features at larger scales delineate the global cluster contours, while features at smaller scales reveal fine-grained local details. Subsequently, the proposed method learns the view-specific partitions from different scales of views and derives consensus features through tensor low-rank representation. By optimizing these consensus features, the approach effectively captures the precise cluster shapes from coarse to fine-grained levels. The final label indicator matrix is directly obtained from these consensus features. To demonstrate the effectiveness and versatility of the proposed method, we conducted experimental comparisons with state-of-the-art (SOTA) algorithms in both multiview clustering and image segmentation across diverse datasets. The source code and datasets are released at https://github.com/ChuanbinZhang/SDTR.

In the task of dynamic human pose estimation (dynamic HPE), the temporal relationships between human body parts should be captured comprehensively to understand the dynamic human motions, where the correlated motion information eventually helps to recognize body parts. The popular methods are successful in terms of utilizing long-term motion information captured by low-speed cameras. Yet they neglect the underlying intermediate motions between captured frames, which comprise the temporal-interim poses lost in the video. In this article, we introduce a novel framework, temporal-interim pose synthesis and distillation, to produce and leverage the intermediate motion information for dynamic motion establishment. The pose synthesis yields the visual feature maps of the intermediate poses, which appear between the existing video frames. It allows the synthesized and current poses to form richer motion patterns. Next, the pose distillation divides the body parts into several groups, where it learns the specific part-wise relationship within each group. It degrades the complexity of learning useful part-wise relationships from rich motion patterns and extracts more detailed motion information for fine-grained part groups. We extensively evaluate our method on challenging datasets for dynamic pose estimation, achieving state-of-the-artresults.

Deep multiview clustering provides an efficient way to analyze the data consisting of multiple modalities and features. Recently, the autoencoder (AE)-based deep multiview clustering algorithms have attracted intensive attention by virtue of their rewarding capabilities of extracting inherent features. Nevertheless, most existing methods are still confronted by several problems. First, the multiview data usually contains abundant cross-view information, thus parallel performing an individual AE for each view and directly combining the extracted latent together can hardly construct an informative view-consensus feature space for clustering. Second, the intrinsic local structures of multiview data are complicated, hence simply embedding a preset graph constraint into multiview clustering models cannot guarantee expected performance. Third, current methods commonly utilize the Kullback-Leibler (KL) divergence as clustering loss and accordingly may yield appalling clusters that lack discriminate characters. To solve these issues, in this article we propose two new AE-based deep multiview clustering algorithms named AE-based deep multiview clustering model incorporating graph embedding (AG-DMC) and deep discriminative multiview clustering algorithm with adaptive graph constraint (ADG-DMC). In AG-DMC, a novel cross-view representation learning model is established delicately by performing decoding processes based on the cascaded view-specific latent to learn sound view-consensus features for inspiring clustering results. In addition, an entropy-regularized adaptive graph constraint is imposed on the obtained soft assignments of data to precisely preserve potential local structures. Furthermore, in the improved model ADG-DMC, the adversarial learning mechanism is adopted as clustering loss to strengthen the discrimination of different clusters for better performance. In the comprehensive experiments carried out on eight real-world datasets, the proposed algorithms have achieved superior performance in the comparison with other advanced multiview clustering algorithms.

Broad learning system (BLS) have demonstrated excellent performance in terms of both speed and accuracy in tasks such as image classification. In BLS, the feature nodes predominantly utilize linear features, and sparse representation is mainly employed in the feature optimization component. The robustness of these features to different data needs to be improved. Although there are many improved algorithms for BLS in feature optimization, there is no improvement based on fractional calculus at present. This article proposes BLS-FC, a novel data classification and regression method that can seamlessly combine BLS and fractional calculation. Fractional calculus describes the properties of data between integer orders and has memory properties. Fractional Fourier transform (Frft) also has time domain and frequency domain information. First, Frft is added to the broad learning feature node extraction to enrich the node features, which is called BLS-Frft. Second, fractional calculus is integrated into the BLS-Frft sparse representation feature optimization, and the feature representation capability is enhanced by fractional differential memory. This part is called BLS-FS. Finally, in order to solve the problem of unstable features of random fractional order subspaces, a fractional order multiscale feature interaction based on BLS-Frft is proposed, which is called BLS-MF. Experimental results across various classification and regression datasets demonstrate the superior performance of the proposed method.

Due to its marvelous performance and remarkable scalability, a broad learning system (BLS) has aroused a wide range of attention. However, its incremental learning suffers from low accuracy and long training time, especially when dealing with unstable data streams, making it difficult to apply in real-world scenarios. To overcome these issues and enrich its relevant research, a robust incremental BLS (RI-BLS) is proposed. In this method, the proposed weight update strategy introduces two memory matrices to store the learned information, thus the computational procedure of ridge regression is decomposed, resulting in precomputed ridge regression. During incremental learning, RI-BLS updates two memory matrices and renews weights via precomputed ridge regression efficiently. In addition, this update strategy is theoretically analyzed in error, time complexity, and space complexity compared with existing incremental BLSs. Different from Greville's method used in the original incremental BLS, its results are closer to the solution of one-shot calculation. Compared with the existing incremental BLSs, the proposed method exhibits more stable time complexity and superior space complexity. The experiments prove that RI-BLS outperforms other incremental BLSs when handling both stable and unstable data streams. Furthermore, experiments demonstrate that the proposed weight update strategy applies to other random neural networks as well.

Time series anomaly detection is the process of identifying anomalies within time series data. The primary challenge of this task lies in the necessity for the model to comprehend the characteristics of time-independent and abnormal data patterns. In this study, a novel algorithm called adaptive memory broad learning system (AdaMemBLS) is proposed for time series anomaly detection. This algorithm leverages the rapid inference capabilities of the broad learning algorithm and the memory bank's capacity to differentiate between normal and abnormal data. Furthermore, an incremental algorithm based on multiple data augmentation techniques is introduced and applied to multiple ensemble learners, thereby enhancing the model's effectiveness in learning the characteristics of time series data. To bolster the model's anomaly detection capabilities, a more diverse ensemble approach and a discriminative anomaly score are recommended. Extensive experiments conducted on various real-world datasets demonstrate that the proposed method exhibits superior inference speed and more accurate anomaly detection compared to the existing competitors. A detailed experimental investigation is presented to elucidate the effectiveness of the proposed method and the underlying reasons for its efficacy.

Anomaly detection has become a key focus in maintaining the stability and reliability of the cloud environment. Although with excellent feature extraction ability, deep learning-based anomaly detection methods entail a time-consuming training process. Broad learning system (BLS) provides an alternative supervised way for efficient training. However, due to the imbalance of the collected cloud computing data in which anomaly accounts for a low proportion, sufficient feature extraction from anomaly behaviors with BLS becomes a challenge. Moreover, the input generation of BLS only considers the independence of data, and the generalization of BLS in the correlation modeling of cloud computing data is limited. To tackle the above issues, we introduce an effective anomaly detector, CatBRS, an improved BLS with rebalance operations. Initially, we employ a hybrid resampling method of SMOTE-Tomek to mitigate data imbalance, retain non-synthetic samples for training, and involve synthetic samples in the input generation later. Subsequently, we extend BLS by refining the process of input generation. This enhanced system employs a simple recurrent architecture to model temporal dynamics. Additionally, it integrates an autoencoder-based model with metric learning to obtain category-constrained discriminant features. The improvement in BLS facilitates more comprehensive feature extraction. Finally, extensive experiments are conducted to evaluate the performance of CatBRS on four benchmark datasets. CatBRS shows improvements of up to 3.81% in AUC and 6.09% in F1 compared to suboptimal baseline methods with a low training cost.

Predicting the runtime of tasks is of great significance as it can help users better understand the future runtime consumption of the tasks and make decisions for their heterogeneous devices, or be applied to task scheduling. Learning features from user task history data for predicting task runtime is a mainstream method. However, this method faces many challenges when applied to edge intelligence. In the Big Data era, user devices and data features are constantly evolving, necessitating frequent model retrains. Meanwhile, the noisy data from these devices requires robust methods for valuable insight extraction. In this paper, we propose an edge server-oriented deep neuro-fuzzy system (ESODNFS) that can be trained and inferred on edge servers, for providing users with task runtime prediction services. We divided the dataset and trained it on multiple improved adaptive-network-based fuzzy inference system units (ANFISU), and finally conducted joint training on a deep neural network (DNN). By partitioning the dataset, we reduced the number of parameters for each ANFISU, and at the same time, multiple units can be trained in parallel, supporting fast training and iteration. Additionally, the application of fuzzy inference can effectively learn the features in noisy data and make accurate predictions. The experimental results show that ESODNFS can accurately predict the runtime of real tasks. Compared with other DNN and DNFS, it can achieve good prediction results while reducing training time by over 35%.

This article is devoted to solving the leaderless and leader-following consensus tracking problems for a class of disturbed second-order multiagent systems (MASs) under the influence of actuator attacks. To achieve this, a two-step control strategy is developed, where the effects of disturbances and actuator attacks on the achievement of consensus tracking are addressed in distinct stages. In the first step, a reference system model is constructed for each agent. Upon which a sliding mode control (SMC) protocol is constructed and utilized to resolve the consensus tracking problem of disturbed second-order MASs in the absence of actuator attacks, facilitating the design of a baseline control term for the MASs under consideration. In the second step, a secure control policy is trained using an off-policy soft actor-critic algorithm, aiming at achieving secure consensus tracking in the presence of actuator attacks. Both numerical simulations and a multipendulum consensus example verify that the designed control structure has better control performance than using only the SMC method and also effectively improves the training efficiency over the traditional reinforcement learning (RL) alone method.

This article focuses on the trajectory tracking control of under-actuated unmanned surface vehicles subject to unknown ocean current and input quantization. Regarding kinematics, we devise an extended-state-observer-based guidance law capable of compensating for ocean currents to track the intended trajectory. Concerning kinetics, we propose an event-triggered adaptive fuzzy quantization control law using a linear analytical model to depict input quantization, eliminating the need for prior quantization parameter information. A notable aspect is the reduction in both execution frequency and magnitude, thereby mitigating communication burdens. The stability of this control strategy is proofed through input-to-state stability analysis. Simulation experiments are conducted to affirm the viability of the event-triggered adaptive fuzzy quantization control strategy.

Graffiti detection is essential in historic building protection and urban neighborhood management. Graffiti detection has made significant progress in recent years based on the development of deep learning. However, small-scale graffiti, interference from the background, and the false detection of word parts in graffiti make it a challenging problem. This article proposes a Transformer-based high-precision graffiti detection method, namely DIG. Precisely, it consists of three modules: 1) Spatial query selection (SQS), scale-aware IoU loss (SIL); 2) Denoising Task with binary contrastive denoising (BCDN); and 3) IoU-guided box denoising (IBD) modules. To detect small-scale graffiti, this paper proposes SIL to help the loss function to perceive small-scale graffiti and large-scale graffiti fairly. To reduce the false detection of word parts, this article presents the SQS module, which integrates spatial information into the query selection process of the Encoder to filter out falsely detected bounding boxes within the graffiti. To reduce the interference from the background, this article introduces a denoising task with BCDN and IBD modules, improving the model’s ability to distinguish graffiti from the background and accurately select appropriate bounding boxes. A large number of experimental results on the STORM dataset show that our method achieves state-of-the-art results with an$AP_{50}$of 87.9%. Moreover, DIG achieved competitive results on the FineFM dataset for mask detection. This indicates that DIG can also be conveniently transferred to detect other scenarios.

DT, as a conditional sequence modeling (CSM) approach, learns the action distribution for each state using historical information, such as trajectory returns, offering a supervised learning paradigm for offline reinforcement learning (Offline RL). However, due to the fact that decision transformer (DT) solely concentrates on an individual trajectory with high returns-to-go, it neglects the potential for constructing optimal trajectories by combining sequences of different actions. In other words, traditional DT lacks the trajectory stitching capability. To address the concern, a novel DT (PCDT) for Offline RL is proposed. Our approach begins by pretraining a standard DT to explicitly capture behavior sequences. Next, we apply the sequence importance sampling to penalize actions that significantly deviate from these behavior sequences, thereby constructing a pessimistic critic. Finally,Q-values are integrated into the policy update process, enabling the learned policy to approximate the behavior policy while favoring actions associated with the highestQ-value. Theoretical analysis shows that the sequence importance sampling in pessimistic critic decision transformer (PCDT) establishes a pessimistic lower bound, while the value optimality ensures that PCDT is capable of learning the optimal policy. Results on the D4RL benchmark tasks and ablation studies show that PCDT inherits the strengths of actor–critic (AC) and CSM methods, achieving the highest normalized scores on challenging sparse-reward and long-horizon tasks. Our code are available at https://github.com/Henry0132/PCDT.

This article addresses the nonsingular practical fixed-time adaptive fuzzy control problem of nonstrict-feedback multiagent systems (MASs) with actuator faults. By utilizing fuzzy-logic systems (FLSs), the identification of unknown nonlinearities in MASs is achieved while avoiding the algebraic loop problem. The singularities in fixed-time control are prevented by incorporating an adding power integration technique into the control scheme. Furthermore, we design an adaptive update law to mitigate the effects of unknown actuator faults and external disturbances. An adaptive fuzzy practical fixed-time MASs consistency control algorithm is proposed by combining these techniques with backstepping control. Based on stability analysis, the designed control scheme ensures that all MAS signals remain bounded within a fixed time and that the convergence time to achieve consistency does not depend on the initial states of the MASs. Finally, the validity of the proposed nonsingular practical fixed-time consensus control scheme is verified through simulation examples.

The sensitivity of the broad learning system (BLS) based on the minimum-mean-square error (MMSE) criterion to non-Gaussian noise limits the application of this system. In order to solve this problem, this article proposes robust BLS (GC-BLS) based on generalized maximum correntropy criterion (GMCC). GMCC has a more general kernel function, which can effectively extract high-dimensional features of the data. In the non-Gaussian noise environment, GC-BLS shows excellent robustness. However, if the kernel width deviates from its optimal value, the performance of the system constructed based on the entropy criterion may fluctuate or even degrade. Since robust regression methods can improve robustness and are independent of kernel width, this motivates us to further construct MGC-BLS based on M-estimator functions. MGC-BLS can effectively suppress the performance degradation caused by kernel width deviation and has better robustness when selecting an appropriate M-estimator function. The two algorithms are optimized by fixed-point iteration, the update strategy in the iterative process is analyzed, and the sufficient conditions for the convergence of the algorithms are given. Compared with other BLS variants, GC-BLS and MGC-BLS can show better performance in the tests. Experiments on University of California Irvine (UCI) regression datasets and time-series datasets show the effectiveness of the two new algorithms.

This article explores the tracking issue for dc-dc buck power converter with stochastic disturbance, specifically focusing on how output voltage tracks to a desired voltage in a finite-time when the load changes. Meanwhile, considering unmodeled dynamics and nonaffine inputs, we propose an innovative finite-time fuzzy prescribed performance switching tracking algorithm to achieve tracking goal. For realizing the requirements of performance, the algorithm converts the tracking error to a new state by means of a coordinate transformation via the tangent function. In addition, the universal approximation capacity of the fuzzy-logic system is utilized to estimate the unknown nonlinear term effectively. On this basis, the designed adaptive dynamic event-triggered controller can not only ensure that all the signals for the closed-loop system remain bounded in probability but also guarantee that the tracking error will converge to a predetermined small neighborhood. Meanwhile, different piecewise functions are added into the controller to characterize prescribed performance and avoid singularity problems, respectively. Finally, the effectiveness of the tracking control algorithm is fully demonstrated by the simulations of the dc-dc buck power converter.

The application of artificial intelligence technology has greatly enhanced and fortified the safety of energy pipelines, particularly in safeguarding against external threats. The predominant methods involve the integration of intelligent sensors to detect external vibration, enabling the identification of event types and locations, thereby replacing manual detection methods. However, practical implementation has exposed a limitation in current methods - their constrained ability to accurately discern the spatial dimensions of external signals, which complicates the authentication of threat events. Our research endeavors to overcome the above issues by harnessing deep learning techniques to achieve a more fine-grained recognition and localization process. This refinement is crucial in effectively identifying genuine threats to pipelines, thus enhancing the safety of energy transportation. This paper proposes a radial threat estimation method for energy pipelines based on distributed optical fiber sensing technology. Specifically, we introduce a continuous multi-view and multi-domain feature fusion methodology to extract comprehensive signal features and construct a threat estimation and recognition network. The utilization of collected acoustic signal data is optimized, and the underlying principle is elucidated. Moreover, we incorporate the concept of transfer learning through a pre-trained model, enhancing both recognition accuracy and training efficiency. Empirical evidence gathered from real-world scenarios underscores the efficacy of our method, notably in its substantial reduction of false alarms and remarkable gains in recognition accuracy. More generally, our method exhibits versatility and can be extrapolated to a broader spectrum of recognition tasks and scenarios.

Skeleton-based methods in Gait Emotion Recognition (GER) that abstract gait as a spatial-temporal graph in a non-Euclidean space have achieved remarkable success. However, existing studies neglect capturing crucial spatial-temporal implicit dependencies and make insufficient use of manually crafted affective complementary information. In this paper, we propose a novel Temporal Group Attention Network with Affective Complementary Learning (T2A). Specifically, we propose a Temporal Group Attention (TGA) module, which captures spatial-temporal implicit dependencies and crucial features across space-time. Moreover, we design an affective complementary learning strategy, which first introduces an Affective Denoising (AD) module to reduce the impact of noise in weak emotion-related information and learn augmented affective features. Then, we adopt a decision-level fusion of the denoised affective features with the deep skeleton features to compensate for the discrepancies between different feature spaces. Experimental results on Emotion-Gait and EMOGAIT demonstrate that our proposed method significantly outperforms state-of-the-art methods.

Templates serve as a good starting point to implement a design (e.g., banner, slide) but it takes great effort from designers to manually create. In this paper, we present Desigen, an automatic template creation pipeline which generates background images as well as harmonious layout elements over the background. Different from natural images, a background image should preserve enough non-salient space for the overlaying layout elements. To equip existing advanced diffusion-based models with stronger spatial control, we propose two simple but effective techniques to constrain the saliency distribution and reduce the attention weight in desired regions during the background generation process. Then conditioned on the background, we synthesize the layout with a Transformer-based autoregressive generator. To achieve a more harmonious composition, we propose an iterative inference strategy to adjust the synthesized background and layout in multiple rounds. We constructed a design dataset with more than 40k advertisement banners to verify our approach. Extensive experiments demonstrate that the proposed pipeline generates high-quality templates comparable to human designers. More than a single-page design, we further show an application of presentation generation that outputs a set of theme-consistent slides. The data and code are available at https://whaohan.github.io/desigen.

The vulnerability of individual-database learned model for Micro-Expression Recognition (MER) has significantly hindered their performance in real-world scenarios. Cross-Database Micro-Expression Recognition (CDMER) aims to enhance the robustness and generalization performance for more complicated situations. Most existing CDMER methods typically attempt to leverage spatial information to eliminate the inevitable domain shift between source and target domains. In this paper, we propose a novel feature space reconstruction model that provides feature space with better generalization for CDMER. Specifically, we introduce the Spatial and Frequency Domain Co-learning (SFDC), a three-branch module, that adaptively exploits the spatial and frequency characteristics of intermediate feature representations, capturing the global and local features of micro-expression adequately. Furthermore, to facilitate the synchronization of two domains, Source and Target Domain Synchronization (STDS) module is employed to guide the alignment of different subspaces simultaneously. Extensive experimental results on the SMIC and CASME II databases demonstrate the effectiveness of the reconstruction and the superiority of our proposed method over state-of-the-art (SOTA) methods.

Soft Prompt Transfer(SPT) uses well-trained soft prompts as initialization to improve prompt tuning efficiency. However, most methods in SPT learn only a single and task-specific prompt for each source task. It may not be suitable for the target task and results in poor transferability on target task. To address this issue, we propose Snapshot Prompt Ensemble (SPE) method for parameter-efficient soft prompt transfer. Specifically, SPE extracts multiple soft prompts from each source task via taking snapshots at different training phases of prompt tuning. SPE then adaptively ensembles the multiple soft prompts and obtains a fused and instance-dependent prompt for the target task by a cross-task attention module. SPE can effectively exploit the prompts at different training phases and provide a more suitable starting point for target prompt training. Extensive experiments on various NLU tasks demonstrate that SPE outperforms state-of-the-art methods while SPE tunes less than 0.4% of the parameters compared to full fine-tuning.

Speech emotion recognition plays a crucial role in human-computer interaction. However, data distribution of speech signals varies among individuals for emotion recognition. It may guide models to focus more on identity information rather than emotional information, which impairs the generalization ability of models. To address this issue, this paper proposes a novel Disentanglement Network (DTNet) to disentangle emotional features from acoustic features. Specifically, DTNet first captures hidden identity features from acoustic features through an identity-aware module. Then, we design a disentanglement module to disentangle emotional features from acoustic features within the constraints of a reconstruction module and the hidden identity features. These modules enable the DTNet to extract more discriminative emotional features for emotion recognition. Experimental results on both speaker-independent and speaker-dependent settings have proven the effectiveness of DTNet, and this method achieves an unweighted accuracy (UA) of 74.8% on the IEMOCAP dataset and UA of 95.5% on the Emo-DB dataset, outperforming the state-of-the-art methods on both datasets.

Xiaojun Kuang, C. L. Philip Chen, Shuzhen Li, Tong Zhang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

The Broad Learning System (BLS) has been established as an effective flat network alternative to Deep Neural Networks (DNNs), delivering high efficiency while achieving competitive accuracy. Despite its advantages, the incremental learning methods of BLS face challenges in stability and computation when expanding with new nodes or input. We introduce two novel incremental learning algorithms based on factorization updates for BLS that optimize node and input additions to overcome these limitations. Our node addition algorithm utilizes QR decomposition and Cholesky factorization, using the update of the Cholesky factor instead of pseudo-inverse computations. For input addition, we propose an iterative Cholesky factor update algorithm. Our algorithms demonstrate not only faster computation compared to the existing BLS but also improved testing accuracy on the MNIST or Fashion-MNIST dataset. This work presents a significant step forward in the practical application and scalability of BLS in various data-dense environments.

The integration of Intelligent Welding Systems (IWS) in smart manufacturing leverages advancements in sensors, robotics, and artificial intelligence to optimize welding processes. However, in industry practice, we still face challenges such as sufficient data is not available for every manufacturing task, the costs associated with welding data annotation quality, and the risk of knowledge forgetting during the continual welding process. To tackle these issues, we developed an Adaptive Domain-Enhanced Transfer Learning (ADETL) framework that integrates self-supervised and continual learning strategies. This framework is adept at using incremental and unlabeled data for pre-training, in which we analyze the parameter space, loss landscape, and make the model understand the behaviour of knowledge transfer from diverse source domains. The ADETL framework improves the performance of defect classification, offering a promising solution to the challenges inherent in automatic, continuous welding operations.

Probability calibration is a method to improve the reliability of models by linking the predicted probability to accuracy. Most research follow a static strategy of full fine-tuning. These studies do not consider dynamic data and sparse parameters in Language Models as a Service(LMaaS), leading to limited effectiveness of probability calibration. To address above issues, we propose a dynamic probability calibration algorithm (DPCA) to consider both data flow and parameter freezing. DPCA consists of streaming annotation (SA) task and dynamic calibration (DC) task. The SA task takes a specified number of samples from the training data stream. The sampled data is automatically annotated according to the deviation between predicted probability and true label. The DC task injects the probability deviation of the SA task into next training epoch through adapter-tuning. DPCA achieves data augmentation in LMaaS through joint learning of sample labels and their predicted probability deviation. This work validates DPCA through the implementation on BERT architecutre. The proposed model achieves overall performance improvement on both Chinese and English NLP tasks. Experimental results demonstrate a 2.17% decrease in average ECE without de-creasing in accuracy. Experimental analysis demonstrate the effectiveness and generalizability of DPCA in LMaaS.

Multi-modal physiological signals fusion integrates multiple heterogeneous physiological signals to characterize human physiological activities, which is basic research on biomedical signal processing. Most researches on multi-modal physiological signal fusion are based on heterogeneous graph fusion networks (HGFNs) while they ignore the high-order correlations between multi-modal physiological signals. Moreover, most HGFNs suffer from the over-smoothing problem, causing failures in deeper networks. To address these issues, this paper proposes a deep hypergraph convolutional network called DHFusion for multi-modal physiological signal fusion. Specially, DHFusion designs deep hypergraph convolution (DHGCN) layer to effectively integrate multiple physiological signals and obtain multi-modal features. DHFusion then introduces JK readout layer to enable multi-layer DHGCN to capture deep multi-modal features based on high-order correlations. DHFusion effectively solves the over-smoothing of HGFNs and performs well in representing deep multi-modal features. Experimental results over the state-of-the-art methods on two benchmark datasets demonstrate the effectiveness of the proposed method.

Concrete structural crack damage classification is of importance for road safety. This paper proposes a new method based on broad neural network for crack damage classification in concrete structures. It includes three stages. Firstly, a pre-trained deep neural network is used to extract the features from crack images. Secondly, principal component analysis is used to project the retrieved features from high dimensions to low dimensions. Thirdly, broad learning system is employed to predict the classification using the low-dimensional features. Experimental results demonstrate that this method reduces the model's training time and improves classification accuracy.

Convolutional Neural Networks (CNNs) have ex-hibited great power in various vision tasks. However, the lack of transform-invariant property limits their further applications in complicated real-world scenarios. In this work, we pro-posed a novel generalized one-dimension convolutional operator (OneDConv), which dynamically transforms the convolution kernels based on the input features in a computationally and parametrically efficient manner. The proposed operator can extract the transform-invariant features naturally. It improves the robustness and generalization of convolution without sac-rificing the performance of common images. The proposed OneDConv operator can substitute the vanilla convolution. Thus, it can readily be incorporated into popular convolutional architectures, supporting end-to-end training. Empirical evaluations on popular benchmarks reveal OneDConv's superior performance over the standard convolution and competitive models in handling canonical and distorted images.

The asymmetry of emotional responses is observed in electroencephalogram (EEG) of different frequency bands across various spatial brain regions in neuroscience research. Many prior works have primarily emphasized the dependencies among channels in the spatial domain, neglecting the dynamic interaction of EEG in both spatial and frequency domains, which may limit the performance of EEG emotion recognition. To address these issues, we propose the dual-domain attention based adaptive graph convolutional network (DDA-AGCN) for EEG emotion recognition. Specifically, we propose the lightweight dual-domain attention mechanism (DDA) based on random vector similarity measurement and the squeezeexcitation technique to capture important characteristics in the channel and frequency domain respectively. Furthermore, the adaptive graph convolutional network (AGCN) is utilized to adaptively filter and refine low signal-to-noise ratio EEG data, while also learning the dynamic connectivity patterns among important EEG channels and extracting higher-level abstract features for emotion recognition tasks. To validate the effectiveness of the proposed method, experimental comparisons were conducted on SEED, SEED-IV, and MPED. The experimental results show that our method achieves highly competitive classification performance compared to existing methods. Moreover, under fair comparison, the DDA demonstrates better performance and computational efficiency than self-attention.

This study investigates the feasibility of incorporating the broad learning (BL) model in federated learning. Traditional deep learning-based federated learning encounters challenges such as excessive communication volume and extended training time. To address these issues, federated learning with the broad learning model has attracted much attention. We provide a detailed discussion on server-side aggregation for BL models, including the initialization process and three feasible aggregation approaches for single-round aggregation. Then, ablation studies are conducted to assess the suitable BL model architectures within the context of federated learning. Furthermore, we perform a comparative analysis between these approaches and existing federated learning schemes to evaluate their advantages and limitations. Our research suggests that federated learning with BL models is highly feasible in certain scenarios and can effectively tackle the issues of transmission efficiency. Finally, we analyze our findings and propose further investigation to improve algorithms for more efficient performance of federated broad learning systems in the future.

Speech emotion recognition (SER) captures emotional information from speech signals to recognize users' emotional states, which plays a crucial role in conversational human-computer interaction. Most SER researches focus on ex-ploiting emotional information from global temporal or spectral features, but it may neglect detailed emotion-related information such as phonemes and syllables. To address this problem, this paper proposes a multi-granularity temporal-spectral representation learning (MG-TSRL) network for speech emotion recognition tasks. Specifically, MG-TSRL extracts different temporal features in phonetic, syllabic, and sentential granular-ity from spectrograms to retain more detailed emotional-related information. It then designs multilayer emotion-aware units to capture emotion-related frequency patterns and obtain deep spectrum features at each temporal granularity feature. MG-TSRL further introduces a fast broad learning system and feeds deep temporal-spectral features to it to obtain more accurate emotions. MG-TSRL gradually achieves effective temporal-spectral representation learning through multi-granularity temporal features and multilayer frequency pattern learning. The state-of-the-art results on the CASIA, RAVDESS, and SAVEE datasets are respectively 95.17%, 92.78%, and 87.50% in unweighted accuracy, demonstrating the effectiveness of MG-TSRL in speech emotion recognition.

Recently, the multi-cloud environment (MCE) has increasingly become the preferred choice of users. As with the cloud environment, efficient workflow scheduling in a MCE remains crucial for identifying the cost efficiency and overall performance of the MCE. In MCE, the resources exhibit heterogeneity, complexity, and dynamism. Simultaneously, the intricate inter-task dependencies among workflow tasks, diverse Quality of Service (QoS) metrics for users, and multiple cloud service providers’ (CSPs) billing mechanisms significantly amplify the workflow scheduling challenge. Motivated by the application of reinforcement learning (RL) in workflow scheduling in a cloud environment, this paper proposes a scheduling algorithm that takes advantage of the asynchronous advantage actor–critic algorithm (A3C) to balance cost, makespan and resource utilization in workflow scheduling in a MCE. By analyzing the elements in the MCE, we design and define multiple agents in the MCE, and each cloud service provider will have an agent to record the state and update the local parameters. For the workflow task submitted by the user, the action is selected according to the initialization policy and submitted to the scheduling action to allocate the task to a designated virtual machine in the MCE so that each agent can more clearly perceive the environment change and adapt to the MCE. In contrast to the traditional A3C algorithm, we design a new critic network according to the data characteristics of real-world scientific workflows so that each agent is more suitable for real-world scientific workflow data. Through multiple sets of simulation experiments, the workflow scheduling algorithm based on the A3C algorithm in the MCE (MCWS-A3C) was compared with three benchmark methods. The experimental results show that the proposed method has better advantages than other methods in terms of cost, makespan, and resource utilization . Specifically, on the Montage_100 dataset, the average cost was reduced by 55.12% compared to other methods. The pioneering introduction of the A3C algorithm that adapts to the dynamic environment into the MCE brings more possibilities to address the issue of workflow scheduling in the MCE.

Abstract Representation-based methods have found widespread applications in various classification tasks. However, these methods cannot deal effectively with imbalanced data scenarios. They tend to neglect the importance of minority samples, resulting in bias toward the majority class. To address this limitation, we propose a density-based discriminative nonnegative representation approach for imbalanced classification tasks. First, a new class-specific regularization term is incorporated into the framework of a nonnegative representation based classifier (NRC) to reduce the correlation between classes and improve the discrimination ability of the NRC. Second, a weight matrix is generated based on the hybrid density information of each sample’s neighbors and the decision boundary, which can assign larger weights to minority samples and thus reduce the preference for the majority class. Furthermore, the resulting model can be efficiently optimized through the alternating direction method of multipliers. Extensive experimental results demonstrate that our proposed method is superior to numerous state-of-the-art imbalanced learning methods.

Single Image Super-Resolution (SISR) aims to reconstruct a high-resolution image from its corresponding low-resolution input. A common technique to enhance the reconstruction quality is Non-Local Attention (NLA), which leverages self-similar texture patterns in images. However, we have made a novel finding that challenges the prevailing wisdom. Our research reveals that NLA can be detrimental to SISR and even produce severely distorted textures. For example, when dealing with severely degrade textures, NLA may generate unrealistic results due to the inconsistency of non-local texture patterns. This problem is overlooked by existing works, which only measure the average reconstruction quality of the whole image, without considering the potential risks of using NLA. To address this issue, we propose a new perspective for evaluating the reconstruction quality of NLA, by focusing on the sub-pixel level that matches the pixel-wise fusion manner of NLA. From this perspective, we provide the approximate reconstruction performance upper bound of NLA, which guides us to design a concise yet effective Texture-Fidelity Strategy (TFS) to mitigate the degradation caused by NLA. Moreover, the proposed TFS can be conveniently integrated into existing NLA-based SISR models as a general building block. Based on the TFS, we develop a Deep Texture-Fidelity Network (DTFN), which achieves state-of-the-art performance for SISR. Our code and a pre-trained DTFN are available on GitHub†for verification.

Limited data availability poses a perennial challenge in the field of generative image generation. However, current up-sampling methods suffer from inherent deficiencies, resulting in generators' failure to faithfully restore images with identical resolution and distribution. This is primarily evident in the diminishing mutual information as image resolution increases. Considering the above issue, we propose MICGAN, a data-efficient Generative Adversarial Network (GAN) that compensates for mutual information in every layer output feature of the generator through dense frequency skip connections. MICGAN is grounded in information theory, offering a robust theoretical foundation for mitigating mutual information decay. Additionally, we demonstrate that the augmented mutual information primarily stems from increased high-frequency components in images. Furthermore, we introduce three sub-architectures–MICGAN-A, MICGAN-C, and MICGAN-S–—each employing distinct feature fusion methods. Extensive experiments across thirteen diverse datasets validate the advancements and effectiveness of MICGAN compared to state-of-the-art methods.

Abstract Cold-start active learning (CSAL) selects valuable instances from an unlabeled dataset for manual annotation. It provides high-quality data at a low annotation cost for label-scarce text classification. However, existing CSAL methods overlook weak classes and hard representative examples, resulting in biased learning. To address these issues, this paper proposes a novel dual-diversity enhancing and uncertainty-aware (Deuce) framework for CSAL. Specifically, Deuce leverages a pretrained language model (PLM) to efficiently extract textual representations, class predictions, and predictive uncertainty. Then, it constructs a Dual-Neighbor Graph (DNG) to combine information on both textual diversity and class diversity, ensuring a balanced data distribution. It further propagates uncertainty information via density-based clustering to select hard representative instances. Deuce performs well in selecting class-balanced and hard representative data by dual-diversity and informativeness. Experiments on six NLP datasets demonstrate the superiority and efficiency of Deuce.

Cross-subject EEG emotion recognition suffers a major setback due to high inter-subject variability in emotional responses. Many prior studies have endeavored to alleviate the inter-subject discrepancies of EEG feature distributions, ignoring the variable EEG connectivity and prediction deviation caused by individual differences, which may cause poor generalization to the unseen subject. This paper proposes a graph domain disentanglement network (GDDN) to generalize EEG emotion recognition across subjects in terms of EEG connectivity, representation, and prediction. More specifically, a graph domain disentanglement module is proposed to extract common-specific characteristics on both EEG graph connectivity and graph representation, enabling a more comprehensive network transferability to the unseen individual. Meanwhile, to strengthen stable emotion prediction capability, a domain-adaptive classifier aggregation module is developed to facilitate adaptive emotional prediction for the unseen individual conditioned on the domain weights of the input individuals. Finally, an auxiliary supervision module is imposed to alleviate the domain discrepancy and reduce information loss during the disentanglement learning. Extensive experiments on three public EEG emotion datasets, i.e., SEED, SEED-IV, and MPED, validate the superior generalizability of GDDN compared with the state-of-the-art methods.

Although multimodal physiological data from the central and peripheral nervous systems can objectively respond to human emotional states, the individual differences caused by non-stationary and low signal-to-noise properties bring several challenges to cross-subject emotion recognition tasks. Many previous studies usually focused on learning high correlation information between different modalities, which easily leads to incomplete descriptions of different physiological signals and difficulties in aligning critical emotional information. To tackle these challenges, this paper proposes a novel multimodal emotion recognition model for improving the generalization performance to unseen target domain subjects, termed Completeness-induced Adaptative Broad Learning (CiABL). The proposed CiABL can gradely explore the completeness modality representation that encompasses both modality-relevant and modality-independent information, avoiding the loss of performance due to spurious correlations from different modalities. Subsequently, a well-designed weighted representation distribution alignment mechanism of CiABL can appropriately align the marginal and conditional distributions to reduce the influences of individual differences greatly. Extensive experiments on the SEED and SEED-FRA datasets demonstrate the effectiveness and generalization of the proposed CiABL, which outperforms current state-of-the-art methods. In addition, CiABL can precisely quantify the importance of global features to properly explain the modality contribution and averaged activation patterns of the brain under cross-subject emotion recognition tasks.

EEG emotion recognition has been hampered by the clear individual differences in the electroencephalogram (EEG). Nowadays, domain adaptation is a good way to deal with this issue because it aligns the distribution of data across subjects. However, the performance for EEG emotion recognition is limited by the existing research, which mainly focuses on the global alignment between the source domain and the target domain and ignores much fine-grained information. In this study, we propose a method called Graph-based Unsupervised Subdomain Adaptation (Gusa), which simultaneously aligns the distribution between the source and target domains in a fine-grained way from both the channel and emotion subdomains. Gusa employs three modules, such as the Node-wise Domain Constraints Module to align each EEG channel and obtain a domain-variant representation, the Class-level Distribution Constraints Module, and the Emotion-wise Domain Constraints Module, to collect more fine-grained information, create more discriminative representations for each emotion, and lessen the impact of noisy emotion labels. The studies on the SEED, SEED-IV, and MPED datasets demonstrate that Gusa significantly improves the ability of EEG to recognize emotions and can extract more granular and discriminative representations for EEG.

EEG emotion recognition plays a significant role in various mental health services. Deep learning-based methods perform excellently, but still suffer from interpretability. Although methods such as Gradient-weighted Class Activation Mapping(Grad-CAM) can cope with the above problem, their coarse granularity cannot accurately reveal the mechanism to promote emotional intelligence. In this paper, fine-grained interpretability is proposed, called Concat-aided Grad-CAM. Specifically, the multi-level feature mapping before the fully connected layer is concatenated to obtain the gradients of the target concept so that the discriminant information can be directly located in the high-precision area. Unlike coarse-grained interpretability methods applied in EEG emotion recognition, it can accurately highlight the EEG channels related to emotion rather than an obscure area. In addition, a systematic brain functional network is proposed to reveal the relationship between those channels and to further improve emotion recognition performance. The channels with greater contributions are connected, and those connections are learned by dynamic graph convolutional networks, while the others are independent to eliminate interference. Experiments on two EEG emotion recognition datasets manifest that Concat-aided Grad-CAM can be interpreted by the fine-grained. In addition, it has been shown that the learned brain functional network can improve the performance of the baselines. Significantly, the experiment results achieve state-of-the-art performance in subject-dependent experiments.

This paper investigates adaptive neural network filtering control for uncertain nonlinear systems with general model state and input quantization. The plants under consideration contain quantized states, quantized input, and unknown nonlinear system functions. A universal quantizer is established for both system states and control input. In the control design process, neural networks and the command filter are used to approximate the unknown nonlinear system functions and overcome the discontinuities of virtual control signals, respectively. A new command filtering-based control strategy is proposed using the backstepping design technique. It is testified that the proposed control approach can guarantee that the closed-loop signals are semi-global uniform ultimate boundedness. A simulation example is presented to further demonstrate our proposed scheme’s effectiveness.Note to Practitioners—This work is motivated by the quantized control problem for a class of nonlinear systems with state and input quantization. In modern control engineering applications, quantization plays a crucial role due to the prevalent use of digital processors that operate with finite precision arithmetic. It is valuable and inevitable to minimize information flow, reduce communication burden, and improve system security. However, quantization will introduce significant discontinuous characteristics and strong nonlinearity, which may decrease the system’s performance and even drive the closed-loop system to instability. This paper demonstrates how to use backstepping and adaptive control methods with command filter to complete controller design and deal with the quantization effects. Therefore, it provides a feasible approach for engineering applications.

A prescribed time fuzzy adaptive consensus control method is constructed for multiagent systems with sensor faults and dead-zone input. Sensor faults inevitably occur in actual engineering systems and may distort the state information. Besides, the control effect would be further dramatically affected when systems exist dead-zone input. Thus, a fuzzy adaptive compensation strategy is established by the bounded adaptive optimized method to eliminate the impact of the above constraints. Furthermore, a given performance consensus control method is investigated with the aid of nonlinear transformation. Meanwhile, combined with the prescribed time technology, it further achieves that the systems settling time can be preselected while the performance of the systems is given. Finally, some simulation experiments are adopted to demonstrate the feasibility and effectiveness of the investigated control method.Note to Practitioners—This work studies the consensus problem for multiagent systems, which is important in engineering collaborative applications. Due to measurement noise and electronic damage, sensor faults inevitably happen in industrial applications. Besides, dead-zone input often occurs in actual systems as physical properties of electronic components. Based on the bounded adaptive optimized method, a fuzzy adaptive compensation strategy is constructed to deal with those issues. To further improve the control performance in the collaborative process, prescribed time technology and given performance strategy are applied to construct the control method. The investigated approach can be useful in multiagent systems to achieve more steady consensus operation, which is more in line with the application requirements.

This paper proposes an adaptive fuzzy output feedback control approach for quadrotor unmanned aerial vehicles (QUAV) with stochastic disturbances, besides which we consider the unmeasurable states and unknown nonlinear functions. The QUAV system contains stochastic terms which are not bounded and not differentiable. By combining the It$\hat {\rm \textbf {o}}$differential equation with finite-time theory, a novel stochastic finite-time stability controller for QUAV is raised for the first time. The fuzzy logic system (FLS) is utilized to approximate the unknown nonlinear functions in the model. Dynamic surface control technology is introduced to reduce the complexity of differential. Furthermore, an observer with FLS is designed through the adaptive backstepping technique to estimate the immeasurable states. It is proved that this control approach can ensure that all states of the closed-loop QUAV system are semi-global and finite-time stable in probability. Meanwhile, the errors of system outputs and observer converge to a small neighborhood of origin. The simulation results show the effectiveness of the proposed method.Note to Practitioners—In practical applications, many systems are often affected by internal and external disturbances, and not all of them can be described by mathematical models, so they are called stochastic disturbances. Taking the QUAV as an example, when the system is disturbed by internal parameters, external environment, system input, sensor error, and other stochastic factors, the deterministic system can no longer accurately describe the controlled object. In this paper, the QUAV is regarded as a stochastic system for the first time, and a novel controller is designed to solve the above problems. In addition, the QUAV needs fast action in some applications, such as emergency collision avoidance, which has high requirements for the convergence performance of the controller. Therefore, studying the finite-time control for QUAV systems with stochastic disturbances is necessary. At the same time, this paper also considers the problem that the state is not measurable and the system contains unknown nonlinear equations.

Robust optimization (RO) has been recognized as an effective means to deal with unanticipated events in highly uncertain and risky environments. This paper systematically reviews two types of emerging RO machine scheduling approaches—robust machine scheduling (R-MS) and distributionally R-MS (DR-MS) methods—which usually offer tractable formulations and analytical results for machine scheduling problems under uncertainty. First, after highlighting the advantages of RO methods over the stochastic approach in terms of tractability and robustness, we use the bibliometric method to analyze the literature related to R-MS/DR-MS problems and classify them from the following aspects: (1) uncertain factors, (2) uncertainty descriptions, (3) robustness criteria, (4) machine environments and (5) solution methods. Second, we discuss the uncertainty descriptions, and the robust feasibility and robust optimality criteria. We further provide a state-of-the-art review of R-MS/DR-MS models in different machine environments and discuss the performance of the R-MS/DR-MS models. Third, we review and discuss the existing exact, approximation, online, and heuristic solution methods for solving R-MS/DR-MS models. Finally, we present future research opportunities in two promising areas: green machine scheduling problems and machine learning-enabled algorithms.Note to Practitioners—Machine scheduling plays an essential role in industrial and service systems, such as manufacturing, power generation, transportation and medical systems. However, in practice, scheduling systems usually operate in highly uncertain environments due to noisy measurements, prediction errors, and implementation deviations. To ensure robust feasibility and robust optimality, robust machine scheduling (R-MS) and distributionally R-MS (DR-MS) approaches have been recently proposed to hedge against the uncertainties related to processing time, release time, due date, machine breakdown, etc. This paper provides a comprehensive review of the R-MS/DR-MS models and algorithms in different machine environments from the aspects of uncertainty descriptions, robustness criteria and solution methods. This paper further highlights the challenges of R-MS problems and provides promising and valuable research opportunities in terms of problem formulations and algorithm designs.

A fixed-time fuzzy control (FTFC) scheme is suggested for uncertain nonlinear systems with prescribed performance (PP) and event-triggered communication. First, the original system with PP constraints is transformed into an unconstrained one using a coordinate transformation. Next, fuzzy logic systems (FLSs) are introduced to estimate the uncertain nonlinear functions, and an event-triggered mechanism (ETM) is designed to reduce the update frequency of the control signal. Then, a fixed-time fuzzy controller is proposed to ensure that the tracking error converges within a fixed time. Rigorous theoretical analysis shows that the proposed control scheme can achieve the fixed-time convergence of the tracking error according to the PP requirement. At the same time, communication resources are saved compared to traditional time-triggered control methods. Finally, the validity of the theoretical results is verified by simulation results.

With increasing social globalization, interaction between people from different cultures has become more frequent. However, there are significant differences in the expression and comprehension of emotions across cultures. Therefore, developing computational models that can accurately identify emotions among different cultures has become a significant research problem. This study aims to investigate the similarities and differences in emotion cognition processes in different cultural groups by employing a fusion of electroencephalography (EEG) and eye movement (EM) signals. Specifically, an effective adaptive region selection method is proposed to investigate the most emotion-related activated brain regions in different groups. By selecting these commonly activated regions, we can eliminate redundant features and facilitate the development of portable acquisition devices. Subsequently, the multiple stacked broad learning system (MSBLS) is designed to explore the complementary information of EEG and EM features and the effective emotional information still contained in the residual value. The intracultural subject-dependent (ICSD), intracultural subject-independent, and cross-cultural subject-independent (CCSI) experiments have been conducted on the SEED-CHN, SEED-GER, and SEED-FRA datasets. Extensive experiments manifest that MSBLS achieves superior performance compared with current state-of-the-art methods. Moreover, we discover that some brain regions (the anterior frontal, temporal, and middle parieto-occipital lobes) and Gamma frequency bands show greater activation during emotion cognition in diverse cultural groups.

Multimodal emotion recognition (MER) integrates multiple modalities to identify the user's emotional state, which is the core technology of natural and friendly human–computer interaction systems. Currently, many researchers have explored comprehensive multimodal information for MER, but few consider that comprehensive multimodal features may contain noisy, useless, or redundant information, which interferes with emotional feature representation. To tackle this challenge, this article proposes a sparse interactive attention network (SIA-Net) for MER. In SIA-Net, the sparse interactive attention (SIA) module mainly consists of intramodal sparsity and intermodal sparsity. The intramodal sparsity provides sparse but effective unimodal features for multimodal fusion. The intermodal sparsity adaptively sparses intramodal and intermodal interactive relations and encodes them into sparse interactive attention. The sparse interactive attention with a small number of nonzero weights then act on multimodal features to highlight a few but important features and suppress numerous redundant features. Furthermore, the intramodal sparsity and intermodal sparsity are deep sparse representations that make unimodal features and multimodal interactions sparse without complicated optimization. The extensive experimental results show that SIA-Net achieves superior performance on three widely used datasets.

Self-supervised graph representation learning (GRL) has shown great success in scientific research and real-world applications. Nevertheless, one obstacle in GRL is the demand for graph augmentation (GA), which deeply impacts the representation qualities. On the one hand, GA supplements the data amount and enhances the robustness and quality of the representations. On the other hand, collocating appropriate augmentations claims nontrivial attempts. In this article, a new method to free GA is provided building a novel fuzzy view and two crisp views of the original graph. As all the views are transformed from the original graph, they are semantically similar and naturally considered to possess high-quality positive samples. In this way, the data amount is compensated to a degree without changing the raw node attributes or graph topology. Additionally, to ensure the diversity of the positives, asymmetric renormalization and noise perturbation are adopted. Experiments toward node-level tasks on several real-world datasets demonstrate the competition against several state-of-the-art models.

This article proposes a teacher-guided peer learning approach that employs a continuous action iterated dilemma (CAID) model based on an incremental network. Traditional peer learning approaches often assume static communication relationships between students, which is not consistent with actual society, and this affects the effectiveness of peer learning. Additionally, every student is a highly unique individual, and using a single mathematical model to mimic their behavior would result in research findings with limited applicability. Therefore, this article presents several innovations. First, we propose an incremental network generation algorithm that generates an effective communication network to improve classroom efficiency by enhancing the convergence of information between classmates. Second, considering the multiple unknown nonlinear environmental impacts, we design a student dynamic model based on CAID with multiple layers of nonlinearity to fit the different environmental impacts that different students receive. Finally, based on the incremental network and student dynamic model, we design the Lyapunov function to prove the convergence of the proposed model. This mathematical proof ensures that the proposed model is stable and unaffected by parameters, making it more applicable.

Most of the work on electroencephalogram (EEG)-based emotion recognition aims to extract the distinguishing features from high-dimensional EEG signals, ignoring the complementarity of information between EEG latent space and graph space. Furthermore, the influence of brain connectivity on emotions encompasses both physical structure and functional connectivity, which may have varying degrees of importance for different individuals. To address these issues, this article introduces an adaptive dual-space network (ADS-Net) with multigraph fusion aimed at capturing more comprehensive information by integrating dual-space representations. Specifically, ADS-Net models the spatial correlation of EEG channels in graph topological space, while exploring long-range dependencies and frequency relationships from EEG data in latent space. Subsequently, these representations are adaptively combined through an innovative gated fusion approach to extract complementary corepresentations. Moreover, drawing on the principles of brain connectivity theory, the proposed method constructs a multigraph to indicate the associativity of EEG channels. To further capture individual differences, an adaptive multigraph fusion mechanism is developed for the dynamic integration of physical and functional connectivity graphs. When compared to state-of-the-art methods, the superior experimental results underscore the effectiveness and broad applicability of the proposed method.

The human gait reflects substantial information about individual emotions. Current gait emotion recognition methods focus on capturing gait topology information and ignore the importance of fine-grained temporal features. This article proposes the temporal-tightly graph convolutional network (TT-GCN) to extract temporal features. TT-GCN comprises three significant mechanisms: the causal temporal convolution network (casual-TCN), the walking direction recognition auxiliary task, and the feature mapping layer. To obtain tight temporal dependencies and enhance the relevance among gait periods, the causal-TCN is introduced. Based on the assumption of emotional consistency in the walking directions, the auxiliary task is proposed to enhance the ability of fine-grained feature extraction. Through the feature mapping layer, affective features can be mapped into the appropriate representation and fused with deep learning features. TT-GCN shows the best performance across five comprehensive metrics. All experimental results verify the necessity and feasibility of exploring fine-grained temporal feature extraction.

Information aggregation and propagation over networks via graph neural networks (GNNs) plays an important role in node or graph representation learning, which currently depend on the calculation with a fixed adjacency matrix, facing over-smoothing problem, and difficulty to stack multiple layers for high-level representations. In contrast, Transformer calculates an importance score for each node to learn its embedding via the attention mechanism and has achieved great successes in many natural language processing (NLP) and computer vision (CV) tasks. However, Transformer is inflexible to extend to graphs, as its input and output must have the same dimension. It will also become intractable to allocate attention over a large-scale graph due to distractions. Moreover, most graph Transformers are trained in supervised ways, which consume additional resources to annotate samples with potentially wrong labels and have limited generalization of representations. Therefore, this article attempts to build a new Sparse Graph Transformer with Contrastive learning for graph representation learning, called SGTC. Specifically, we first employ centrality measures to remove the redundant topological information from input graph according to the influences of nodes and edges, then disturb the pruned graph to get two different augmentation views, and learn node representations in a contrastive manner. Besides, a novel sparse attention mechanism is also proposed to capture structural features of graphs, which effectively save memory and training time. SGTC can produce low-dimensional and high-order node representations, which have better generalization for multiple tasks. The proposed model is evaluated on three downstream tasks over six networks, and experimental results confirm its superior performance against the state-of-the-art baselines.

Blind Super-Resolution (BlindSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) images without prior knowledge of the image degradation process. This is a challenging problem in real-world applications, where the degradation can be complex and unknown. Recent unsupervised learning-based BlindSR methods can estimate the image degradation in an unsupervised manner, but they suffer from limited adaptability to different types and intensities of degradation. They tend to capture the average level of degradation across all training samples, resulting in over-smoothing or over-sharpening effects for some images. As a result, the final reconstruction may exhibit the mean effect. Moreover, existing synthetic datasets do not reflect the real-world degradation scenarios, making it difficult to evaluate the performance of BlindSR methods. To address these issues, we propose a novel Degradation Intensity Estimation Module (DIEM) method, which can estimate the pixel-level degradation information of the input image more specifically and use it to guide image reconstruction. Furthermore, we construct a benchmark dataset under real scenarios, which is closer to the real-world BlindSR problem than existing synthetic datasets, and can provide a more reasonable evaluation of BlindSR methods. Extensive experimental results demonstrate that our DIEM-guided BlindSR method can achieve state-of-the-art image reconstruction results. Our code and pre-trained models have been uploaded to GitHub† for validation.

Weakly-supervised fine-grained visual categorization (FGVC) aims to achieve subclass classification within the same large class using only label information. Compared to general images, fine-grained images have similar appearances and features, and are often affected by disturbances such as viewpoint, lighting, and occlusion during data collection, resulting in significant intra-class variance and small inter-class variance. To achieve FGVC, carefully designed models are often needed to explore the locally discriminative regions of the image. This paper revisits high-quality FGVC publications based on deep learning and analyzes from two new perspective: fine-grained image data and backbone. We address two ignored but interesting problems in FGVC. First, we argue that the reasons for exacerbating intra-class variance are not the same in data of animal, plant, and commodity types, and it is necessary to consider the effects of posture, covariate shift, and structural changes. Additionally, the “soft boundary” between subclasses intensifies the difficulty of classification. Second, we highlight that convolutional networks and self-attention networks have different receptive fields and shape biases, leading to performance differences when processing different types of fine-grained data. Overall, our analysis provides new insights into recent advances, challenges, and future directions for FGVC based on deep learning, which can help researchers develop more effective models for FGVC.

Aiming at simplifying the network structure of broad learning system (BLS), this article proposes a novel simplification method called compact BLS (CBLS). Groups of nodes play an important role in the modeling process of BLS, and it means that there may be a correlation between nodes. The proposed CBLS not only focuses on the compactness of network structure but also pays closer attention to the correlation between nodes. Learning from the idea of Fused Lasso and Smooth Lasso, it uses the$L_{1}$-regularization term and the fusion term to penalize each output weight and the difference between adjacent output weights, respectively. The$L_{1}$-regularization term determines the correlation between the nodes and the outputs, whereas the fusion term captures the correlation between nodes. By optimizing the output weights iteratively, the correlation between the nodes and the outputs and the correlation between nodes are attempted to be considered in the simplification process simultaneously. Without reducing the prediction accuracy, finally, the network structure is simplified more reasonably and a sparse and smooth output weights solution is provided, which can reflect the characteristic of group learning of BLS. Furthermore, according to the fusion terms used in Fused Lasso and Smooth Lasso, two different simplification strategies are developed and compared. Multiple experiments based on public datasets are used to demonstrate the feasibility and effectiveness of the proposed methods.

Histopathological tissue classification is a fundamental task in computational pathology. Deep learning (DL)-based models have achieved superior performance but centralized training suffers from the privacy leakage problem. Federated learning (FL) can safeguard privacy by keeping training samples locally, while existing FL-based frameworks require a large number of well-annotated training samples and numerous rounds of communication which hinder their viability in real-world clinical scenarios. In this article, we propose a lightweight and universal FL framework, named federated deep-broad learning (FedDBL), to achieve superior classification performance with limited training samples and only one-round communication. By simply integrating a pretrained DL feature extractor, a fast and lightweight broad learning inference system with a classical federated aggregation approach, FedDBL can dramatically reduce data dependency and improve communication efficiency. Five-fold cross-validation demonstrates that FedDBL greatly outperforms the competitors with only one-round communication and limited training samples, while it even achieves comparable performance with the ones under multiple-round communications. Furthermore, due to the lightweight design and one-round communication, FedDBL reduces the communication burden from 4.6 GB to only 138.4 KB per client using the ResNet-50 backbone at 50-round training. Extensive experiments also show the scalability of FedDBL on model generalization to the unseen dataset, various client numbers, model personalization and other image modalities. Since no data or deep model sharing across different clients, the privacy issue is well-solved and the model security is guaranteed with no model inversion attack risk. Code is available at https://github.com/tianpeng-deng/FedDBL.

Broad learning system (BLS) with semi-supervised learning relieves label dependence and expands application. Despite some efforts and progress, the semi-supervised BLS still needs improvement, especially in handling imbalanced data or concept drift scenarios for self-training-based methods. To this extent, this article proposes a robust semi-supervised BLS guided by ensemble-based self-training (ESTSS-BLS). Distinctive to self-training that assigns the pseudo-label via a single classifier and confidence, the advocated ensemble-based self-training determines the pseudo-label according to the turnout of multiple BLSs. In addition, label purity is proposed to ensure the correctness and credibility of the auxiliary training data, which is a comprehensive evaluation of the voting. During iterative learning, a small portion of labeled data first trains multiple BLSs in parallel. Then, the system recursively updates its data, structure, and meta-parameters using label purity and a data-driven dynamic nodes mechanism that dynamically guides the network's structural adjustments to solve the concept drift problem caused by a large amount of auxiliary training data. The experimental results demonstrate that ESTSS-BLS exhibits exceptional performance compared to existing methods, with the lowest-time consumption and the highest accuracy, precision, recall, F1 score, and AUC. Exhilaratingly, it achieves an accuracy of 87.84% with only 0.1% labeled data on MNIST, and with just 2% labeled data, it matches the performance of supervised learning using all training data on NORB. In addition, ESTSS-BLS also performs stably on medical or biological data, verifying its high adaptability.

The study of nicotine addiction mechanism is of great significance in both nicotine withdrawal and brain science. The detection of addiction-related brain connectivity using functional magnetic resonance imaging (fMRI) is a critical step in study of this mechanism. However, it is challenging to accurately estimate addiction-related brain connectivity due to the low-signal-to-noise ratio of fMRI and the issue of small sample size. In this work, a prior-embedding graph generative adversarial network (PG-GAN) is proposed to capture addiction-related brain connectivity accurately. By designing a dual-generator-based scheme, the addiction-related connectivity generator is employed to learn the feature map of addiction connection, while the reconstruction generator is used for sample reconstruction. Moreover, a bidirectional mapping mechanism is designed to maintain the consistency of sample distribution in the latent space so that addiction-related brain connectivity can be estimated more accurately. The proposed model utilizes prior knowledge embeddings to reduce the search space so that the model can better understand the latent distribution for the issue of small sample size. Experimental results demonstrate the effectiveness of the proposed PG-GAN.

The graph-information-based fuzzy clustering has shown promising results in various datasets. However, its performance is hindered when dealing with high-dimensional data due to challenges related to redundant information and sensitivity to the similarity matrix design. To address these limitations, this article proposes an implicit fuzzy k-means (FKMs) model that enhances graph-based fuzzy clustering for high-dimensional data. Instead of explicitly designing a similarity matrix, our approach leverages the fuzzy partition result obtained from the implicit FKMs model to generate an effective similarity matrix. We employ a projection-based technique to handle redundant information, eliminating the need for specific feature extraction methods. By formulating the fuzzy clustering model solely based on the similarity matrix derived from the membership matrix, we mitigate issues, such as dependence on initial values and random fluctuations in clustering results. This innovative approach significantly improves the competitiveness of graph-enhanced fuzzy clustering for high-dimensional data. We present an efficient iterative optimization algorithm for our model and demonstrate its effectiveness through theoretical analysis and experimental comparisons with other state-of-the-art methods, showcasing its superior performance.

In this article, a fuzzy adaptive fixed-time asymptotic consistent control scheme is developed for a class of nonlinear multiagent systems (NMASs) with a nonstrict-feedback (NSF) structure. In the control process, a fixed-time consistency control method without control singularity is proposed by combining fuzzy logic systems (FLSs) with good approximation capability, fixed-time stability theory, and plus power integration techniques. Then, by using Barbalat's Lemma, the asymptotic stability of tracking errors and the boundedness of the controlled systems are successfully achieved, which means that the tracking errors can converge to zero in a fixed time. Finally, the effectiveness of the designed control scheme is demonstrated by a simulation example.

In this article, an expert system-based multiagent deep deterministic policy gradient (ESB-MADDPG) is proposed to realize the decision making for swarm robots. Multiagent deep deterministic policy gradient (MADDPG) is a multiagent reinforcement learning algorithm proposed to utilize a centralized critic within the actor-critic learning framework, which can reduce policy gradient variance. However, it is difficult to apply traditional MADDPG to swarm robots directly as it is time consuming during the path planning, rendering it necessary to propose a faster method to gather the trajectories. Besides, the trajectories obtained by the MADDPG are continuous by straight lines, which is not smooth and will be difficult for the swarm robots to track. This article aims to solve these problems by closing the above gaps. First, the ESB-MADDPG method is proposed to improve the training speed. The smooth processing of the trajectory is designed in the ESB-MADDPG. Furthermore, the expert system also provides us with many trained offline trajectories, which avoid the retraining each time we use the swarm robots. Considering the gathered trajectories, the model predictive control (MPC) algorithm is introduced to realize the optimal tracking of the offline trajectories. Simulation results show that combining ESB-MADDPG and MPC can realize swarm robot decision making efficiently.

Alzheimer's disease (AD) is characterized by alterations of the brain's structural and functional connectivity during its progressive degenerative processes. Existing auxiliary diagnostic methods have accomplished the classification task, but few of them can accurately evaluate the changing characteristics of brain connectivity. In this work, a prior-guided adversarial learning with hypergraph (PALH) model is proposed to predict abnormal brain connections using triple-modality medical images. Concretely, a prior distribution from anatomical knowledge is estimated to guide multimodal representation learning using an adversarial strategy. Also, the pairwise collaborative discriminator structure is further utilized to narrow the difference in representation distribution. Moreover, the hypergraph perceptual network is developed to effectively fuse the learned representations while establishing high-order relations within and between multimodal images. Experimental results demonstrate that the proposed model outperforms other related methods in analyzing and predicting AD progression. More importantly, the identified abnormal connections are partly consistent with previous neuroscience discoveries. The proposed model can evaluate the characteristics of abnormal brain connections at different stages of AD, which is helpful for cognitive disease study and early treatment.

In this article, the fuzzy adaptive fixed-time bipartite output consistent tracking problem of nonlinear coopetition multi-agent systems (MASs) under a signed directed graph is studied. The fuzzy logic system (FLS) is used in the control scheme to approximate the unknown nonlinear dynamics. Under the framework of adaptive backstepping recursive design, an adaptive fuzzy fixed-time bipartite output consistent control method is proposed. In addition, to further enhance tracking performance, a fixed-time prescribed performance function (FTPPF) is introduced into the control design process, ensuring that the bipartite consensus tracking errors converge within a fixed time to the predefined boundary. By constructing the Lyapunov function, the fixed-time stability of the closed-loop system is proved. Eventually, the feasibility and effectiveness of the proposed adaptive bipartite output consensus control method are verified by the numerical simulation example.

Graph representation learning focuses on abstracting critical information from raw graphs. Unfortunately, there always exist various kinds of uncertainties, such as attribute noise and network topology corruption, in raw graphs. Under the message passing mechanism, certainties are likely to spread throughout the whole graph. Matters like these would induce deep graph models into producing uncertain representations and restrict representation expressiveness. Considering this, we propose a pioneering framework to defend graph uncertainties by improving the robustness and capability of graph neural networks (GNNs). In our framework, we consider that weights and biases are all fuzzy numbers, thus generating representations to assimilate graph uncertainties, which are finally released by defuzzification. To describe the process of the framework, in this article, a graph convolutional network (GCN) is employed to construct a robust graph model, called FuzzyGCN. To verify the effectiveness of FuzzyGCN, it is trained in both supervised and unsupervised ways. In the supervised setting, we find that FuzzyGCN has stronger power and is more immune to data uncertainties when compared with various classical and robust GNNs. In the unsupervised setting, FuzzyGCN surpasses many state-of-the-art models in node classification and community detection over several real-world datasets.

In this article, a novel secure fault-tolerant control (FTC) strategy is proposed to deal with the impact of multiple threats such as sparse sensor attacks, system faults, and unknown disturbances on T–S fuzzy cyber-physical systems (CPSs). First, under the assumption of 2s-detectability, a set of robust local unknown input observers is designed. Specifically, each observer can decouple partial disturbances and perform targeted suppression on undecoupling disturbances simultaneously. Next, the residual-based attack detection strategy and secure global estimation fusion mechanism are developed, leading to the estimation of the state and concerned fault with smaller estimation error. Ulteriorly, a secure fault tolerant controller is proposed to ensure that the system can recover satisfactory performance in time subjected to multiple threats. Finally, the proposed secure FTC method is applied to the control scenario of autonomous vehicles in the network environment, which proves the effectiveness of the developed technology.

The existing results on inverse optimal control are limited to nonlinear systems without quantized signals. To remove this limitation, for strict-feedback nonlinear systems under output quantization, a new adaptive fuzzy inverse method is presented in this article, which achieves the optimal performance without relying on the Hamilton–Jacobi–Bellman equation. Considering that only quantized output is applied to feedback, first of all, a novel quantized state observer is devised. Second, the unknown nonlinearities are approximated by fuzzy logic systems. Third, to overcome the issue that the partial derivatives of virtual controllers do not exist after quantization, the command filtering technology is applied. Then, by combining the tuning functions and the projection operator, an auxiliary intermediate controller and a parameter adaptive law are constructed. Furthermore, an adaptive inverse optimal controller under output quantization is established. It is shown that all signals in the closed-loop system are semiglobally uniformly ultimately bounded, and the inverse optimal practical stabilization is realized. Eventually, the effectiveness of this approach is demonstrated through two examples.

This article studies the optimized backstepping consensus control problem for uncertain nonstrict-feedback nonlinear multiagent systems with intermittent actuator faults and input quantization. A fuzzy approximation-based optimal consensus control scheme is proposed via the reinforcement learning algorithm. Meanwhile, a time-varying constraint function is embedded into the optimized backstepping consensus design to guarantee the consensus errors converge to a preassigned residual set within the prescribed time. To overcome the difficulty of the virtual optimized controller design caused by unknown virtual control coefficients, a class of intermediate variables is designed. A modified variable separation technique is proposed to circumvent the problem of algebraic loop caused by the construction of virtual optimized controllers. Then, based on the reconstruction of unknown bounds, a fault-tolerant controller under the quantization action is developed to compensate for the impact of unknown actuator faults automatically, and achieve semiglobally ultimately uniformly bounded results. In the end, a practical example of a group of single-link manipulators is given to illustrate the validity of the presented method.

This article considers the finite-time consensus control issue of high-order multi-input and multi-output nonlinear multiagent systems. In the process of establishment, this article uses fuzzy logic systems to identify unknown nonlinear dynamics. Then, according to the backstepping recursive technique and finite-time stability criterion, a fuzzy adaptive finite-time consensus control scheme is designed. At the same time, a communication-restricted control scheme is established according to the dynamic event-triggered strategy with a relative threshold to reduce the execution time of the controller and save communication resources. In addition, a novel integral Lyapunov function is established by introducing the adding power integrator technology, which proves the stability and convergence of consensus tracking errors of closed-loop systems. Finally, taking a marine surface vehicle as an example, the availability of the established event-triggered consensus control scheme is described.

This article studies the problem of an adaptive fuzzy predefined-time tracking control approach for a type of uncertain nonstrict-feedback high-order nonlinear systems with input quantization. The considered plants contain unknown nonlinear functions, input quantization, and external disturbances. Based on the backstepping recursive technique and predefined-time stability criterion, a fuzzy adaptive predefined-time control strategy is presented. To address the difficulties posed by the uncertain nonlinearities within the original systems, the fuzzy logic systems are incorporated into estimate the unknown nonlinear functions, while power integrator technology is used to overcome the hurdle presented by high-order terms. Using the predefined-time Lyapunov stability theory, the system stability analysis is provided, and it is proved that all signals in the closed-loop system are bounded within the preset time interval. Ultimately, the effectiveness of the presented control approach is corroborated through numerical simulation.

This study addresses the learning-based resilient adaptive fuzzy optimal consensus control problem for nonlinear uncertain Multiagent Systems (MASs) in the presence of intermittent Denial of Service (DoS) attacks. A key obstacle is the uncertainty in the dynamics of the followers, which makes it challenging to eliminate dependency on the identifier network. To this end, we propose a novel critic-only optimal consensus scheme to eliminate dependency on the identifier network and significantly reduce computational complexity. Moreover, this work requires less prior knowledge and assumes that only the specific subsystems can access the leader's information under certain conditions. To cope with limited information access, we design a distributed adaptive observer to monitor the leader's dynamics. It is proven that all the signals are uniformly ultimately bounded(UUB), and consensus tracking is achieved. Finally, a simulation example is provided to demonstrate the results achieved.

The fixed-time formation control problem for uncertain nonlinear multiagent systems (MASs) with time-varying actuator failures is investigated. Actuator failures would have a huge impact on the system performance, especially when the actuator failures are time-varying, which may even cause system insecurity. In order to cope with time-varying actuator failures, a fixed-time convergence approach is proposed based on adaptive fuzzy control technology. Simultaneously, solving the above problems would aggravate the occupation of communication resources of the system. Therefore, a periodic adaptive event-triggered control scheme is developed, in which the triggering period can be adjusted adaptively. Furthermore, the convergence time of formation errors can be preset by applying the fixed-time control method. The convergence velocity can be accelerated immensely. Eventually, theoretical analysis and simulation illustrate that the proposed method can effectively compensate the time-varying actuator failures, and the MASs can achieve formation within a fixed time by using less communication resources.

Existing adaptive optimal consensus approaches for high-order nonlinear multiagent systems (MASs) are limited by their complicated and computation-intensive identifier–actor–critic structure and ignore the conflict of interest between agents. This article proposes agraphical game-based adaptive fuzzy optimal bipartite containment schemethat removes these restrictions. The optimal containment is formulated as an$N$-player game over the communication topology for high-order nonlinear MASs by defining a cost function that integrates the agent's control inputs, including those of its neighbors, and the local tracking errors. To seek the Nash equilibrium, integral reinforcement learning is adopted, which does not involve the system drift dynamic. This approach eliminates the need for an identifier network and simplifies the control scheme using adaptive critic learning. To drive the online learning mechanism, the Bellman residual error is utilized, and a fuzzy logic system is used to approximate the optimal value functions of the critic networks. The updating laws incorporate an experience stack, resulting in an easy-to-check persistence excitation condition. It is proven that the synchronization error is uniformly ultimately bounded, and the bipartite containment of the outputs of followers is achieved. An illustrative example is presented to verify the effectiveness of the developed control scheme.

This article focuses on the problem of adaptive optimal tracking control of interconnected switched systems on dwell time. The objective is to establish interconnection between switched systems, stabilize each switched system, and achieve optimal performance over the dwell time. An actor-critic learning technique is utilized to design the optimal controller by evaluating the performance via the critic and improving the policy via the actor. During the design of the cost function and optimization process, we employed non-zero-sum game theory to incorporate the interconnection factors among systems. The proposed control scheme designs a novel relaxed stability condition for switched subsystems and validates the effectiveness by using a Lyapunov function with a value function. Finally, the designed control scheme can be verified by simulation.

Blind super-resolution (BlindSR) has recently attracted attention in the field of remote sensing. Due to the lack of paired data, most works assume that the acquired remote sensing images are high-resolution (HR) and use predefined degradation models to synthesize low-resolution (LR) images for training and evaluation. However, these acquired remote sensing images are often degraded by various factors, which still require super-resolution reconstruction to meet practical needs. Using them as ground truth images will limit the model’s ability to restore fine details, resulting in blurry and noisy reconstructions. To overcome these limitations, we propose an unsupervised degradation-aware network which transforms natural images into the degraded domain as real-world remote sensing images. It uses natural images containing rich texture information as a reference for fine-grained restoration of the network, enabling the network to produce clearer reconstructions. Furthermore, we discovered the remarkable capability of patch-wise discriminator to perceive the degradation type of different regions within the acquired remote sensing image. Inspired by this finding, we design a novel degradation representation module (DRM) that can estimate the degradation information from LR images and guide the network to perform adaptive restoration. Comprehensive experimental results demonstrate that our proposed unsupervised blind super-resolution framework (UDASR) achieves state-of-the-art restoration performance. Our code and pre-trained models have been uploaded to GitHub† for validation.

In recent years, the detection of infrared small targets using deep learning methods has garnered substantial attention due to notable advancements. To improve the detection capability of small targets, these methods commonly maintain a pathway that preserves high-resolution (HR) features of sparse and tiny targets. However, it can result in redundant and expensive computations. To tackle this challenge, we propose a sparse infrared-target detector (SpirDet) for the efficient detection of infrared small targets. Specifically, to cope with the computational redundancy issue, we employ a new dual-branch sparse decoder (DBSD) to restore the feature map. First, the fast branch directly predicts a sparse map indicating potential small-target locations. Second, the slow branch conducts fine-grained adjustments at the positions indicated by the sparse map. In addition, we design a lightweight DO-RepEncoder based on reparameterization with the downsampling orthogonality (DO), which can effectively reduce memory consumption and inference latency. Extensive experiments show that the proposed SpirDet significantly outperforms state-of-the-art (SOTA) models while achieving faster inference speed and fewer parameters. For example, on the NUDT-SIRST dataset, SpirDet improves mean intersection over union (MIoU) by 2.09 and has a$3.1\times $frames/s acceleration compared to the previous SOTA model. The code is available athttps://github.com/laCorse/SpirDet-Pytorch.

Low-light remote sensing (RS) images generally feature high resolution and high spatial complexity, with continuously distributed surface features in space. This continuity in scenes leads to extensive long-range correlations in spatial domains within RS images. convolutional neural networks (CNNs), which rely on local correlations for long-distance modeling, struggle to establish long-range correlations in such images. On the other hand, transformer-based methods that focus on global information face high computational complexities when processing high-resolution RS images. From another perspective, the Fourier transform can compute global information without introducing a large number of parameters, enabling the network to more efficiently capture the overall image structure and establish long-range correlations. Therefore, we propose a dual-domain feature fusion network (DFFN) for low-light RS image enhancement. Specifically, this challenging task of low-light enhancement is divided into two more manageable subtasks: the first phase learns amplitude information to restore image brightness, and the second phase learns phase information to refine details. To facilitate information exchange between the two phases, we designed an information fusion affine block that combines data from different phases and scales. In addition, we have constructed two dark light RS datasets to address the current lack of datasets in dark light RS image enhancement. Extensive evaluations show that our method outperforms existing state-of-the-art methods. The code is available athttps://github.com/iijjlk/DFFN.

Change detection (CD) is a process of extracting changes on the Earth’s surface from bitemporal images. Current CD methods that use high-resolution remote sensing images require extensive computational resources and are vulnerable to the presence of irrelevant noises in the images. In addressing these challenges, a comparison-based attention Siamese network (CAS-Net) is proposed. The network utilizes contrastive attention modules (CAMs) for feature fusion and employs a classifier to determine similarities and differences of bitemporal image patches. It simplifies pixel-level CDs by comparing image patches. As such, the influences of image background noises on change predictions are reduced. Along with the CAS-Net, an unmanned aerial vehicle (UAV) similarity detection (UAV-SD) dataset is built using high-resolution remote sensing images. This dataset, serving as a benchmark for CD, comprises 10000 pairs of UAV images with a size of$256 \times 256$. Experiments of the CAS-Net on the UAV-SD dataset demonstrate that the CAS-Net is superior to other baseline CD networks. The CAS-Net detection accuracy is 93.1% on the UAV-SD dataset. The code and the dataset can be found athttps://github.com/WenbaLi/CAS-Net.

Remote sensing change detection (RSCD) aims to identify changes within bi-temporal registered images. However, existing deep learning (DL)-based RSCD networks often suffer from large numbers of parameters, high computational complexity, and low inference speed, making it challenging to achieve efficient inference in real-world deployments. In addition, current models lack robust feature-fitting capabilities, necessitating the development of an efficient and powerful RSCD model to address this issue. Therefore, we propose a novel RSCD network named efficient adjacent feature harmonizer network (EAFH-Net) with fast computational speed and lightweight design. It is based on MobileNetV2, considering that change maps of different sizes contain temporal information of bitemporal features and spatial information at various scales, we introduce a multiscale feature neighbor fusion module (MFNFM) to address the lack of interaction between sophisticated-level and elementary-level features, and spatial and channel feature harmonizer module (SCFHM) to harmonize the spatiotemporal information of the change maps. Moreover, data-driven DL algorithms face another challenge due to insufficient granularity and the need for more practical datasets. Therefore, we present unmanned aerial vehicle (UAV)-CD+, a dataset comprising 2002 pairs of bi-temporal UAV low-altitude images, each sized at$1024\times 1024$. We performed experiments on three publicly accessible datasets in conjunction with UAV-CD+, comparing the results with other state-of-the-art (SOTA) methods. EAFH-Net attains the utmost precision, obtaining 91.74% on LEVIR-CD, 84.28% on SYSU-CD, 95.07% on WHU-CD, 79.12% on CLCD, and 70.12% on UAV-CD+. We have our model code available at the following link:https://github.com/yikuizhai/UCSFH-Net.

In the current era of big data, securing computer networks and preventing cyberattacks have become a major challenge. In this regard, we present a novel approach for addressing the imbalanced problem of network traffic data. Specifically, the proposed method MC-OCBLS, leverages the maximum correntropy criterion (MCC) to develop a one-class broad learning system. The robustness of the one-class classification model is enhanced by maximizing the correlation entropy. Moreover, considering the limited generalization capability of individual models, we propose the boosting ensemble model SMC-OCBLS, which assigns higher weights to misclassified samples and classifiers with lower error rates. To increase the variety of classifiers in the ensemble framework, feature columns are randomly disrupted during training to construct different feature spaces. Training multiple hybrid classifiers using various feature spaces further enhances the accuracy and generalizability of the model. The experimental results demonstrate the superiority of the proposed model over other advanced approaches.

Low-rank tensor representation with the tensor nuclear norm has been rising in popularity in multi-view subspace clustering (MVSC), in which the tensor nuclear norm is commonly implemented using discrete Fourier transform (DFT). Unfortunately, existing DFT-oriented MVSC methods may provide unsatisfactory results since (1) DFT exploits complex arithmetic in the Fourier domain, usually resulting in high tubal tensor rank, and (2) local structural information is rarely considered. To solve these problems, in this paper, we propose a novel double discrete cosine transform (DCT)-oriented multi-view subspace clustering (D2CTMSC) method, in which the first DCT aims to derive the tensor nuclear norm without complex arithmetic while the second DCT aims to explore the local structure of the self-representation tensor, such that the essential low-rankness and sparsity embedding in multi-view features can be thoroughly exploited. Moreover, we design an effective alternating iteration strategy to solve the proposed model. Experimental results on four types of multi-view datasets (News stories, Face images, Scene images, and Generic objects) demonstrate the superiority of the D2CTMSC method compared with DFT-based methods and other state-of-the-art clustering methods.

Recent developments in the field of non-local attention (NLA) have led to a renewed interest in self-similarity-based single image super-resolution (SISR). Researchers usually use the NLA to explore non-local self-similarity (NSS) in SISR and achieve satisfactory reconstruction results. However, a surprising phenomenon that the reconstruction performance of the standard NLA is similar to that of the NLA with randomly selected regions prompted us to revisit NLA. In this paper, we first analyzed the attention map of the standard NLA from different perspectives and discovered that the resulting probability distribution always has full support for every local feature, which implies a statistical waste of assigning values to irrelevant non-local features, especially for SISR which needs to model long-range dependence with a large number of redundant non-local features. Based on these findings, we introduced a concise yet effective soft thresholding operation to obtain high-similarity-pass attention (HSPA), which is beneficial for generating a more compact and interpretable distribution. Furthermore, we derived some key properties of the soft thresholding operation that enable training our HSPA in an end-to-end manner. The HSPA can be integrated into existing deep SISR models as an efficient general building block. In addition, to demonstrate the effectiveness of the HSPA, we constructed a deep high-similarity-pass attention network (HSPAN) by integrating a few HSPAs in a simple backbone. Extensive experimental results demonstrate that HSPAN outperforms state-of-the-art approaches on both quantitative and qualitative evaluations. Our code and a pre-trained model were uploaded to GitHub (https://github.com/laoyangui/HSPAN) for validation.

The fusion of magnetic resonance imaging and positron emission tomography can combine biological anatomical information and physiological metabolic information, which is of great significance for the clinical diagnosis and localization of lesions. In this paper, we propose a novel adaptive linear fusion method for multi-dimensional features of brain magnetic resonance and positron emission tomography images based on a convolutional neural network, termed as MdAFuse. First, in the feature extraction stage, three-dimensional feature extraction modules are constructed to extract coarse, fine, and multi-scale information features from the source image. Second, at the fusion stage, the affine mapping function of multi-dimensional features is established to maintain a constant geometric relationship between the features, which can effectively utilize structural information from a feature map to achieve a better reconstruction effect. Furthermore, our MdAFuse comprises a key feature visualization enhancement algorithm designed to observe the dynamic growth of brain lesions, which can facilitate the early diagnosis and treatment of brain tumors. Extensive experimental results demonstrate that our method is superior to existing fusion methods in terms of visual perception and nine kinds of objective image fusion metrics. Specifically, in the results of MR-PET fusion, the SSIM (Structural Similarity) and VIF (Visual Information Fidelity) metrics show improvements of 5.61% and 13.76%, respectively, compared to the current state-of-the-art algorithm. Our project is publicly available at: https://github.com/22385wjy/MdAFuse.

Feature mining is a challenging work in the field of multivariate time series (MTS) data mining. Traditional methods suffer from three major issues. 1) Learned shapelets may seriously diverge from original subsequences since learning methods do not restrain the learned ones similar to raw sequences, which reduces interpretability. 2) Existing rule mining methods just generate association rules based on feature combination of different variables without considering temporal relations among features, which could not adequately express the essential characteristics of MTS data. 3) Most deep learning methods only mine global and high-level features of MTS data, which affects interpretability. To address these issues, we propose a temporal association rule mining method based on Generative Adversarial Network (GAN) called TAR-GAN. First, a shapelet mining method based on GAN (SGAN) is advanced to discover dataset-level and sample-level shapelets of all variables in MTS data. Second, a Temporal Graph based Rule Mining method (TGRM) is introduced to discover temporal association rules based on the temporal relationships among shapelets of different variables. Meanwhile, a Fast Convolution-based Similarity Measure methods(FCSM) is introduced to measure the similarity between MTS samples and temporal association rules. Furthermore, an adversarial training strategy is introduced to ensure the effectiveness and stability of generated temporal association rules, which could reflect the essential characteristics of MTS data. Extensive experiments on 12 datasets show the effectiveness and efficiency of our method.

Recently, rule-based classification on multivariate time series (MTS) data has gained lots of attention, which could improve the interpretability of classification. However, state-of-the-art approaches suffer from three major issues. 1) few existing studies consider temporal relations among features in a rule, which could not adequately express the essential characteristics of MTS data. 2) due to the concept drift and time warping of MTS data, traditional methods could not mine essential characteristics of MTS data. 3) existing online learning algorithms could not effectively update shapelet-based temporal association rules of MTS data due to its temporal relationships among features of different variables. To handle these issues, we propose an online learning method for temporal association rule on dynamically collected MTS data (OTARL). First, a new type of rule named temporal association rule is defined and mined to represent temporal relationships among features in a rule. Second, an online learning mechanism with a probability correlation-based evaluation criterion is proposed to realize the online learning of temporal association rules on dynamically collected MTS data. Finally, an ensemble classification approach based on maximum-likelihood estimation is advanced to further enhance the classification performance. We conduct experiments on ten real-world datasets to verify the effectiveness and efficiency of our approach.

Feature selection is a highly regarded research area in the field of data mining, as it significantly enhances the efficiency and performance of high-dimensional data analysis by eliminating redundant and irrelevant features. Despite the ease of data acquisition, labeling data remains a laborious and expensive task. To leverage the abundance of unlabeled data, researchers have proposed various feature selection methods that operate with limited labels, including semi-supervised feature selection and unsupervised feature selection. However, a comprehensive review encompassing a thorough overview of feature selection algorithms with limited labels is lacking. To bridge this gap, this paper conducts a comprehensive exploration of feature selection methods specifically tailored to limited-label scenarios. These methods are systematically classified into two primary categories: semi-supervised and unsupervised feature selection. Additionally, by introducing a novel taxonomy and discussing future challenges, this survey aims to provide researchers with a comprehensive and in-depth understanding of feature selection in limited-label scenarios. Moreover, it aims to offer valuable insights that can guide further research and development in this domain.

Imbalanced data biases the classifier towards the majority class. Accompanied with high-dimensional characteristics, classification performance is further degraded. Existing researches for skewed data mainly involve resampling, cost-sensitive learning, and classifier ensemble. However, these approaches have some limitations: 1) resampling suffers from noisy and redundant features in high-dimensional skewed data; 2) cost-sensitive learning is hard to construct an optimal cost matrix for sample misclassification; 3) ensemble with random feature subspace easily leads to information loss; 4) ensemble with sample subspace on small-size data easily leads to insufficient description of sample space and suffers from negative impacts of high-dimensional data. This paper proposes an improved contraction-expansion subspace ensemble (ICESE) for high-dimensional imbalanced data classification. First, a contraction-expansion subspace optimization (CESO) is designed to perform subspace selection and transformation, which is beneficial for enhancing the discrimination and diversity of subspace. Then, to strengthen classification capabilities, a CESO-based multilayer optimization structure is developed to construct the improved subspace. Finally, to mitigate the effects of skewed data, ICESE performs a resampling scheme on the improved subspace for constructing a rebalanced subset to base classifier. Experimental results on 24 high-dimensional imbalanced data sets demonstrate that our ICESE outperforms different mainstream ensemble systems in terms of F-score and G-mean.

Imbalanced data poses a substantial challenge to conventional classification methods, which often disproportionately favor samples from the majority class. To mitigate this issue, various oversampling techniques have been deployed, but opportunities for optimizing data distributions remain underexplored. By exploiting the ability of metric learning to refine the sample distribution, we propose a novel approach, Imbalance Large Margin Nearest Neighbor (ILMNN). Initially, ILMNN is applied to establish a latent feature space, pulling intra-class samples closer and distancing inter-class samples, thereby amplifying the efficacy of oversampling techniques. Subsequently, we allocate varying weights to samples contingent upon their local distribution and relative class frequency, thereby equalizing contributions from minority and majority class samples. Lastly, we employ Kullback-Leibler (KL) divergence as a safeguard to maintain distributional similarity to the original dataset, mitigating severe intra-class imbalances. Comparative experiments on various class-imbalanced datasets verify that our ILMNN approach yields superior results.

Broad learning system (BLS) is a simple yet efficient learning algorithm that only needs to train a three-layer feedforward neural network. Although various BLS variants have been designed for supervised learning, none have been used for unsupervised learning. This paper proposes BLS-AE, a novel data clustering scheme that seamlessly combines BLS and auto-encoder. Then, graph regularization is introduced into BLS-AE to increase the capability of learning intrinsic structures in data and adaptation to various data simultaneously, which is termed BLSg-AE. Moreover, different concatenation styles of feature and enhancement nodes are investigated for reusing the learned features, followed by designing two special strategies (i.e., pruning optimization and incremental learning) to reduce the parameter scale significantly and improve performance, which is termed xBLSg-AE. To address the performance instability issue caused by random subspace in a single xBLSg-AE, the x-cascade broad learning system graph regularization multi-auto-encoder (xBLSg-MAE) algorithm is proposed. Extensive experiments are conducted on multiple real data sets to demonstrate that the proposed methods are more effective and robust than competing approaches.

Due to the advantages of fast training speed and competitive performance, Broad Learning System (BLS) has been widely used for classification tasks across various domains. However, the random weight generation mechanism in BLS makes the model unstable, and the performance of BLS may be limited when dealing with some complex datasets. On the other hand, the instability of BLS brings diversity to ensemble learning, and ensemble methods can also reduce the variance and bias of the single BLS. Therefore, we propose an ensemble learning algorithm based on BLS, which includes three modules. To improve the stability and generalization ability of BLS, we utilize BLS as the base classifier in an AdaBoost framework first. Taking advantage of the incremental learning mechanism of BLS, we then propose a selective ensemble method to raise the accuracy and diversity of the BLS ensemble method. In addition, based on the former selective Adaboost framework, we suggest a hierarchical ensemble algorithm, which combines sample and feature dimensions to further improve the fitting ability of the ensemble BLS. Extensive experiments have demonstrated that the proposed method performs better than the original BLS and other state-of-the-art models, proving the effectiveness and versatility of our proposed approaches.

Recognizing novel sub-categories with scarce samples is an essential and challenging research topic in computer vision. Existing literature addresses this challenge by employing local-based representation approaches, which may not sufficiently facilitate meaningful object-specific semantic understanding, leading to a reliance on apparent background correlations. Moreover, they primarily rely on high-dimensional local descriptors to construct complex embedding space, potentially limiting the generalization. To address the above challenges, this article proposes a novel model, Robust Saliency-aware Distillation (RSaD), for few-shot fine-grained visual recognition. RSaD introduces additional saliency-aware supervision via saliency detection to guide the model toward focusing on the intrinsic discriminative regions. Specifically, RSaD utilizes the saliency detection model to emphasize the critical regions of each sub-category, providing additional object-specific information for fine-grained prediction. RSaD transfers such information with two symmetric branches in a mutual learning paradigm. Furthermore, RSaD exploits inter-regional relationships to enhance the informativeness of the representation and subsequently summarize the highlighted details into contextual embeddings to facilitate the effective transfer, enabling quick generalization to novel sub-categories. The proposed approach is empirically evaluated on three widely used benchmarks, demonstrating its superior performance.

Multimodal image fusion plays an essential role in medical image analysis and application, where computed tomography (CT), magnetic resonance (MR), single-photon emission computed tomography (SPECT), and positron emission tomography (PET) are commonly-used modalities, especially for brain disease diagnoses. Most existing fusion methods do not consider the characteristics of medical images, and they adopt similar strategies and assessment standards to natural image fusion. While distinctive medical semantic information (MS-Info) is hidden in different modalities, the ultimate clinical assessment of the fusion results is ignored. Our MsgFusion first builds a relationship between the key MS-Info of the MR/CT/PET/SPECT images and image features to guide the CNN feature extractions using two branches and the design of the image fusion framework. For MR images, we combine the spatial domain feature and frequency domain feature (SF) to develop one branch. For PET/SPECT/CT images, we integrate the gray color space feature and adapt the HSV color space feature (GV) to develop another branch. A classification-based hierarchical fusion strategy is also proposed to reconstruct the fusion images to persist and enhance the salient MS-Info reflecting anatomical structure and functional metabolism. Fusion experiments are carried out on many pairs of MR-PET/SPECT and MR-CT images. According to seven classical objective quality assessments and one new subjective clinical quality assessment from 30 clinical doctors, the fusion results of the proposed MsgFusion are superior to those of the existing representative methods.

Separable nonlinear models (SNLMs) are of great importance in system modeling, signal processing, and machine learning because of their flexible structure and excellent description of nonlinear behaviors. The online identification of such models is quite challenging, and previous related work usually ignores the special structure where the estimated parameters can be partitioned into a linear and a nonlinear part. In this brief, we propose an efficient first-order recursive algorithm for SNLMs by introducing the variable projection (VP) step. The proposed algorithm utilizes the recursive least-squares method to eliminate the linear parameters, resulting in a reduced function. Then, the stochastic gradient descent (SGD) algorithm is employed to update the parameters of the reduced function. By considering the tight coupling relationship between linear parameters and nonlinear parameters, the proposed first-order VP algorithm is more efficient and robust than the traditional SGD algorithm and alternating optimization algorithm. More importantly, since the proposed algorithm just uses the first-order information, it is easier to apply it to large-scale models. Numerical results on examples of different sizes confirm the effectiveness and efficiency of the proposed algorithm.

In deep learning, finding flat minima of loss function is a hot research topic in improving generalization. The existing methods usually find flat minima by sharpness minimization algorithms. However, these methods suffer from insufficient flexibility for optimization and generalization due to their ignorance of loss value. This article theoretically and experimentally explores the sharpness minimization algorithms for neural networks. First, a novel scale-invariant sharpness which is called scale-adaptive central moment sharpness (SA-CMS) is proposed. This sharpness is not only scale-invariant but can characterize the nature of loss surface clearly. Based on the proposed sharpness, this article further derives a new regularization term by integrating the different orders of the sharpness. Particularly, a host of sharpness minimization functions such as local entropy can be covered by this regularization term. Then the central moment sharpness generating function is introduced as a new objective function. Moreover, theoretical analyses indicate that the new objective function has a smoother landscape and prefer converging to flat local minima. Furthermore, a computationally efficient two-stage algorithm is developed to minimize the objective function. Compared with other algorithms, the two-stage loss-sharpness minimization (TSLSM) algorithm offers a more flexible optimization target for different training stages. On a variety of learning tasks with both small and large batch sizes, this algorithm is more universal and effective, and meanwhile achieves or surpasses the generalization performance of the state-of-the-art sharpness minimization algorithms.

In this article, a novel coupled policy improvement mechanism is developed for improving policy iteration (PI) algorithms. In contrast to the common PI, the developed dual parallel policy iteration (DPPI) with coupled policy improvement mechanism consists of two parallel PIs. At each PI step, the performances of the two parallel policies are evaluated and the better one is defined as the dominant policy. Then, the dominant policy is used to guide the parallel policy improvement in a soft manner by constraining the Kullback-Liebler (KL) divergence between the dominant policy and the policy to be updated. It is proven that the convergence of DPPI can be guaranteed under the designed coupled policy improvement mechanism. Moreover, it is clearly shown that under certain conditions, the Q -functions of the two new policies obtained in each parallel policy improvement are larger than those of all the previous dominant policies, which is conductive to accelerate the PI process and improve the policy learning efficiency to some extent. Furthermore, by combining DPPI with the twin delay deep deterministic (TD3) policy gradient, we propose a reinforcement learning (RL) algorithm: parallel TD3 (PTD3). Experimental results on continuous-action control tasks in the MuJoCo and OpenAI Gym platforms show that the proposed PTD3 outperforms the state-of-the-art RL algorithms.

Machine learning aims to generate a predictive model from a training dataset of a fixed number of known classes. However, many real-world applications (such as health monitoring and elderly care) are data streams in which new data arrive continually in a short time. Such new data may even belong to previously unknown classes. Hence, class-incremental learning (CIL) is necessary, which incrementally and rapidly updates an existing model with the data of new classes while retaining the existing knowledge of old classes. However, most current CIL methods are designed based on deep models that require a computationally expensive training and update process. In addition, deep learning based CIL (DCIL) methods typically employ stochastic gradient descent (SGD) as an optimizer that forgets the old knowledge to a certain extent. In this article, a broad learning system-based CIL (BLS-CIL) method with fast update and high retainability of old class knowledge is proposed. Traditional BLS is a fast and effective shallow neural network, but it does not work well on CIL tasks. However, our proposed BLS-CIL can overcome these issues and provide the following: 1) high accuracy due to our novel class-correlation loss function that considers the correlations between old and new classes; 2) significantly short training/update time due to the newly derived closed-form solution for our class-correlation loss without iterative optimization; and 3) high retainability of old class knowledge due to our newly derived recursive update rule for CIL (RULL) that does not replay the exemplars of all old classes, as contrasted to the exemplars-replaying methods with the SGD optimizer. The proposed BLS-CIL has been evaluated over 12 real-world datasets, including seven tabular/numerical datasets and six image datasets, and the compared methods include one shallow network and seven classical or state-of-the-art DCIL methods. Experimental results show that our BIL-CIL can significantly improve the classification performance over a shallow network by a large margin (8.80%-48.42%). It also achieves comparable or even higher accuracy than DCIL methods, but greatly reduces the training time from hours to minutes and the update time from minutes to seconds.

In this article, we propose a multiscale cross-connected dehazing network with scene depth fusion. We focus on the correlation between a hazy image and the corresponding depth image. The model encodes and decodes the hazy image and the depth image separately and includes cross connections at the decoding end to directly generate a clean image in an end-to-end manner. Specifically, we first construct an input pyramid to obtain the receptive fields of the depth image and the hazy image at multiple levels. Then, we add the features of the corresponding dimensions in the input pyramid to the encoder. Finally, the two paths of the decoder are cross-connected. In addition, the proposed model uses wavelet pooling and residual channel attention modules (RCAMs) as components. A series of ablation experiments shows that the wavelet pooling and RCAMs effectively improve the performance of the model. We conducted extensive experiments on multiple dehazing datasets, and the results show that the model is superior to other advanced methods in terms of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and subjective visual effects. The source code and supplementary are available at https://github.com/CCECfgd/MSCDN-master.

Traditional partition-based clustering is very sensitive to the initialized centroids, which are easily stuck in the local minimum due to their nonconvex objectives. To this end, convex clustering is proposed by relaxing$K$-means clustering or hierarchical clustering. As an emerging and excellent clustering technology, convex clustering can solve the instability problems of partition-based clustering methods. Generally, convex clustering objective consists of the fidelity and the shrinkage terms. The fidelity term encourages the cluster centroids to estimate the observations and the shrinkage term shrinks the cluster centroids matrix so that their observations share the same cluster centroid in the same category. Regularized by the$\ell_{p_n}$-norm ($p_n\in\{1,2,+\infty\}$), the convex objective guarantees the global optimal solution of the cluster centroids. This survey conducts a comprehensive review of convex clustering. It starts with the convex clustering as well as its nonconvex variants and then concentrates on the optimization algorithms and the hyperparameters setting. In particular, the statistical properties, the applications, and the connections of convex clustering with other methods are reviewed and discussed thoroughly for a better understanding the convex clustering. Finally, we briefly summarize the development of convex clustering and present some potential directions for future research.

Active learning (AL) aims to sample the most valuable data for model improvement from the unlabeled pool. Traditional works, especially uncertainty-based methods, are prone to suffer from a data bias issue, which means that selected data cannot cover the entire unlabeled pool well. Although there have been lots of literature works focusing on this issue recently, they mainly benefit from the huge additional training costs and the artificially designed complex loss. The latter causes these methods to be redesigned when facing new models or tasks, which is very time-consuming and laborious. This article proposes a feature-matching-based uncertainty that resamples selected uncertainty data by feature matching, thus removing similar data to alleviate the data bias issue. To ensure that our proposed method does not introduce a lot of additional costs, we specially design a unsupervised fusion feature matching (UFFM), which does not require any training in our novel AL framework. Besides, we also redesign several classic uncertainty methods to be applied to more complex visual tasks. We conduct rigorous experiments on lots of standard benchmark datasets to validate our work. The experimental results show that our UFFM is better than the similar unsupervised feature matching technologies, and our proposed uncertainty calculation method outperforms random sampling, classic uncertainty approaches, and recent state-of-the-art (SOTA) uncertainty approaches.

Broad learning system (BLS), which emerges as a lightweight network paradigm, has recently attracted great attention for recognition problems due to its good balance between efficiency and accuracy. However, the supervision mechanism in BLS and its variants generally relies on the strict binary label matrix, which imposes limitations on approximation and fails to adequately align with the data distribution. To address this issue, in this article, two novel flexible label-induced BLS models with the manifold manner are proposed, whose notable characteristics are as follows. First, two proposed label relaxation strategies can both enlarge the margins between different categories and simultaneously enhance the diversity within labels. Second, the integration of manifold geometrical criterion enables the models to capture local feature structures, ensuring the obtained flexible labels align better with the similarity between samples. Third, the proposed models can be optimized efficiently with the alternating direction method of multipliers. Each iteration benefits from a closed-form solution, facilitating the optimization process. Extensive experiments and thorough theoretical analysis are intended to show the advantages of our proposed models compared to other state-of-the-art recognition algorithms.

Automatic recognition of 3-D objects in a 3-D model by convolutional neural network (CNN) methods has been successfully applied to various tasks, e.g., robotics and augmented reality. Three-dimensional object recognition is mainly performed by analyzing the object using multi-view images, depth images, graphs, or volumetric data. In some cases, using volumetric data provides the most promising results. However, existing recognition techniques on volumetric data have many drawbacks, such as losing object details on converting points to voxels and the large size of the input volume data that leads to substantial 3-D CNNs. Using point clouds could also provide very promising results; however, point-cloud-based methods typically need sparse data entry and time-consuming training stages. Thus, using volumetric could be a more efficient and flexible recognizer for our special case in the School of Medicine, Shanghai Jiao Tong University. In this article, we propose a novel solution to 3-D object recognition from volumetric data using a combination of three compact CNN models, low-cost SparseNet, and feature representation technique. We achieve an optimized network by estimating extra geometrical information comprising the surface normal and curvature into two separated neural networks. These two models provide supplementary information to each voxel data that consequently improve the results. The primary network model takes advantage of all the predicted features and uses these features in Random Forest (RF) for recognition purposes. Our method outperforms other methods in training speed in our experiments and provides an accurate result as good as the state-of-the-art.

Multiview multi-instance multilabel learning (M3L) is a popular research topic during the past few years in modeling complex real-world objects such as medical images and subtitled video. However, existing M3L methods suffer from relatively low accuracy and training efficiency for large datasets due to several issues: 1) the viewwise intercorrelation (i.e., the correlations of instances and/or bags between different views) are neglected; 2) the diverse correlations (e.g., viewwise intercorrelation, interinstance correlation, and interlabel correlation) are not jointly considered; and 3) high computation burden for training process over bags, instances, and labels across different views. To resolve these issues, a novel framework called fast broad M3L (FBM3L) is proposed with three innovations: 1) utilization of viewwise intercorrelation for better modeling of M3L tasks while existing M3L methods have not considered; 2) based on graph convolutional network (GCN) and broad learning system (BLS), a viewwise subnetwork is newly designed to achieve joint learning among the diverse correlations; and 3) under BLS platform, FBM3L can learn multiple subnetworks jointly across all views with significantly less training time. Experiments show that FBM3L is highly competitive (or even better than) in all evaluation metrics [up to 64% in average precision (AP)] and much faster than most M3L (or MIML) methods (up to 1030 times), especially on large multiview datasets (≥260 K objects).

Broad learning system (BLS) is a novel neural network with efficient learning and expansion capacity, but it is sensitive to noise. Accordingly, the existing robust broad models try to suppress noise by assigning each sample an appropriate scalar weight to tune down the contribution of noisy samples in network training. However, they disregard the useful information of the noncorrupted elements hidden in the noisy samples, leading to unsatisfactory performance. To this end, a novel BLS with adaptive reweighting (BLS-AR) strategy is proposed in this article for the classification of data with label noise. Different from the previous works, the BLS-AR learns for each sample a weight vector rather than a scalar weight to indicate the noise degree of each element in the sample, which extends the reweighting strategy from sample level to element level. This enables the proposed network to precisely identify noisy elements and thus highlight the contribution of informative ones to train a more accurate representation model. Thanks to the separability of the model, the proposed network can be divided into several subnetworks, each of which can be trained efficiently. In addition, three corresponding incremental learning algorithms of the BLS-AR are developed for adding new samples or expanding the network. Substantial experiments are conducted to explicate the effectiveness and robustness of the proposed BLS-AR model.

A novel neural network, namely, broad learning system (BLS), has shown impressive performance on various regression and classification tasks. Nevertheless, most BLS models may suffer serious performance degradation for contaminated data, since they are derived under the least-squares criterion which is sensitive to noise and outliers. To enhance the model robustness, in this article we proposed a modal-regression-based BLS (MRBLS) to tackle the regression and classification tasks of data corrupted by noise and outliers. Specifically, modal regression is adopted to train the output weights instead of the minimum mean square error (MMSE) criterion. Moreover, the$\ell_{2,1}$-norm-induced constraint is used to encourage row sparsity of the connection weight matrix and achieve feature selection. To effectively and efficiently train the network, the half-quadratic theory is used to optimize MRBLS. The validity and robustness of the proposed method are verified on various regression and classification datasets. The experimental results demonstrate that the proposed MRBLS achieves better performance than the existing state-of-the-art BLS methods in terms of both accuracy and robustness.

A graph neural network (GNN) is a powerful architecture for semi-supervised learning (SSL). However, the data-driven mode of GNNs raises some challenging problems. In particular, these models suffer from the limitations of incomplete attribute learning, insufficient structure capture, and the inability to distinguish between node attribute and graph structure, especially on label-scarce or attribute-missing data. In this article, we propose a novel framework, called graph coneighbor neural network (GCoNN), for node classification. It is composed of two modules: GCoNN$_{\Gamma}$and GCoNN$_{\mathop{\Gamma}\limits^{\circ}}$. GCoNN$_{\Gamma}$is trained to establish the fundamental prototype for attribute learning on labeled data, while GCoNN$_{\mathring{\Gamma}}$learns neighbor dependence on transductive data through pseudolabels generated by GCoNN$_{\Gamma}$. Next, GCoNN$_{\Gamma}$is retrained to improve integration of node attribute and neighbor structure through feedback from GCoNN$_{\mathring{\Gamma}}$. GCoNN tends to convergence iteratively using such an approach. From a theoretical perspective, we analyze this iteration process from a generalized expectation–maximization (GEM) framework perspective which optimizes an evidence lower bound (ELBO) by amortized variational inference. Empirical evidence demonstrates that the state-of-the-art performance of the proposed approach outperforms other methods. We also apply GCoNN to brain functional networks, the results of which reveal response features across the brain which are physiologically plausible with respect to known language and visual functions.

In this article, the game-based backstepping control method is proposed for the high-order nonlinear multi-agent system with unknown dynamic and input saturation. Reinforcement learning (RL) is employed to get the saddle point solution of the tracking game between each agent and the reference signal for achieving robust control. Specifically, the approximate optimal solution of the established Hamilton-Jacobi-Isaacs (HJI) equation is obtained by policy iteration for each subsystem, and the single network adaptive critic (SNAC) architecture is used to reduce the computational burden. In addition, based on the separation operation of the error term from the derivative of the value function, we achieve the different proportions of the two agents in the game to realize the regulation of the final equilibrium point. Different from the general use of the neural network for system identification, the unknown nonlinear dynamic term is approximated based on the state difference obtained by the command filter. Furthermore, a sufficient condition is established to guarantee that the whole system and each subsystem included are uniformly ultimately bounded. Finally, simulation results are given to show the effectiveness of the proposed method.

Optimizing a performance objective during control operation while also ensuring constraint satisfactions at all times is important in practical applications. Existing works on solving this problem usually require a complicated and time-consuming learning procedure by employing neural networks, and the results are only applicable for simple or time-invariant constraints. In this work, these restrictions are removed by a newly proposed adaptive neural inverse approach. In our approach, a new universal barrier function, which is able to handle various dynamic constraints in a unified manner, is proposed to transform the constrained system into an equivalent one with no constraint. Based on this transformation, a switched-type auxiliary controller and a modified criterion for inverse optimal stabilization are proposed to design an adaptive neural inverse optimal controller. It is proven that optimal performance is achieved with a computationally attractive learning mechanism, and all the constraints are never violated. Besides, improved transient performance is obtained in the sense that the bound of the tracking error could be explicitly designed by users. An illustrative example verifies the proposed methods.

Consensus clustering can derive a more promising and robust clustering result by integrating multiple partitions strategically. However, there are several limitations in the existing approaches: 1) most of the methods compute the ensemble-information matrix heuristically and lack of sufficient optimization; 2) the information from the original dataset is rarely considered; and 3) the noise in both label space and feature space is ignored. To address these issues, we proposed a novel consensus clustering method with co-association matrix optimization (CC-CMO), which aims at improving the co-association matrix by taking abundant information from both label space and feature space into consideration. In label space, CC-CMO derives a weighted partition matrix capturing the intercluster correlation and further designs a least squares regression (LSR) model to explore the global structure of data. In feature space, CC-CMO minimizes the reconstruction error with doubly stochastic normalization in the projective subspace to eliminate noise features as well as learn the local affinity of data. To improve the co-association matrix by jointly considering the subspace representation, global structure, and local affinity of data, we explicitly propose a unified optimization framework and design an alternating optimization algorithm for the optimal co-association matrix. Extensive experiments on a variety of real-world datasets demonstrate the superior performance of CC-CMO to the state-of-the-art consensus clustering approaches.

This article investigates the event-driven finite-horizon optimal consensus control problem for multiagent systems with symmetric or asymmetric input constraints. Initially, in order to overcome the difficulty that the Hamilton-Jacobi-Bellman equation is time-varying in finite-horizon optimal control, a single critic neural network (NN) with time-varying activation function is applied to obtain the approximate optimal control. Meanwhile, for minimizing the terminal error to satisfy the terminal constraint of the value function, an augmented error vector containing the Bellman residual and the terminal error is constructed to update the weight of the NN. Furthermore, an improved learning law is proposed, which relaxes the tricky persistence excitation condition and eliminates the requirement of initial stability control. Moreover, a specific algorithm is designed to update the historical dataset, which can effectively accelerate the convergence rate of network weight. In addition, to improve the utilization rate of the communication resource, an effective dynamic event-triggering mechanism (DETM) composed of dynamic threshold parameters (DTPs) and auxiliary dynamic variables (ADVs) is designed, which is more flexible compared with the ADV-based DETM or DTP-based DETM. Finally, to support the effectiveness of the proposed method and the superiority of the designed DETM, a simulation example is provided.

The training of the standard broad learning system (BLS) concerns the optimization of its output weights via the minimization of both training mean square error (MSE) and a penalty term. However, it degrades the generalization capability and robustness of BLS when facing complex and noisy environments, especially when small perturbations or noise appear in input data. Therefore, this work proposes a broad network based on localized stochastic sensitivity (BASS) algorithm to tackle the issue of noise or input perturbations from a local perturbation perspective. The localized stochastic sensitivity (LSS) prompts an increase in the network's noise robustness by considering unseen samples located within a Q -neighborhood of training samples, which enhances the generalization capability of BASS with respect to noisy and perturbed data. Then, three incremental learning algorithms are derived to update BASS quickly when new samples arrive or the network is deemed to be expanded, without retraining the entire model. Due to the inherent superiorities of the LSS, extensive experimental results on 13 benchmark datasets show that BASS yields better accuracies on various regression and classification problems. For instance, BASS uses fewer parameters (12.6 million) to yield 1% higher Top-1 accuracy in comparison to AlexNet (60 million) on the large-scale ImageNet (ILSVRC2012) dataset.

High-dimensional class imbalanced data have plagued the performance of classification algorithms seriously. Because of a large number of redundant/invalid features and the class imbalanced issue, it is difficult to construct an optimal classifier for high-dimensional imbalanced data. Classifier ensemble has attracted intensive attention since it can achieve better performance than an individual classifier. In this work, we propose a multiview optimization (MVO) to learn more effective and robust features from high-dimensional imbalanced data, based on which an accurate and robust ensemble system is designed. Specifically, an optimized subview generation (OSG) in MVO is first proposed to generate multiple optimized subviews from different scenarios, which can strengthen the classification ability of features and increase the diversity of ensemble members simultaneously. Second, a new evaluation criterion that considers the distribution of data in each optimized subview is developed based on which a selective ensemble of optimized subviews (SEOS) is designed to perform the subview selective ensemble. Finally, an oversampling approach is executed on the optimized view to obtain a new class rebalanced subset for the classifier. Experimental results on 25 high-dimensional class imbalanced datasets indicate that the proposed method outperforms other mainstream classifier ensemble methods.

In this article, we propose bionic swarm control based on second-order communication topology (SOCT) inspired by the migration of birds, which solves the difficulty in constructing communication topologies and high-computational complexity in controlling large-scale swarm systems. To realize bionic swarm control, there are three problems supposed to be solved. First, the adjacency matrix and the Laplacian matrix in traditional methods cannot be applied to SOCT directly, which should be redesigned. Second, sub-swarm systems formed based on 2-order communication topology (2-OCT) and independently distributed with each other also need to be put forward to reduce computational complexity. At last, the followers in 1-order communication topology (1-OCT) are set as the leaders of sub-swarm systems in 2-OCT. As a result, coupling in large-scale swarm systems would be reduced. The bionic swarm controller is designed through the backstepping method. In this case, the stability of bionic swarm controller is proven by the designed Lyapunov function. The simulations show the efficiency of the designed bionic swarm controller. And the tracking-containment control based on SOCT with 42 swarm members is realized.

Image outpainting is a challenge for image processing since it needs to produce a big scenery image from a few patches. In general, two-stage frameworks are utilized to unpack complex tasks and complete them step-by-step. However, the time consumption caused by training two networks will hinder the method from adequately optimizing the parameters of networks with limited iterations. In this article, a broad generative network (BG-Net) for two-stage image outpainting is proposed. As a reconstruction network in the first stage, it can be quickly trained by utilizing ridge regression optimization. In the second stage, a seam line discriminator (SLD) is designed for transition smoothing, which greatly improves the quality of images. Compared with state-of-the-art image outpainting methods, the experimental results on the Wiki-Art and Place365 datasets show that the proposed method achieves the best results under evaluation metrics: the Fréchet inception distance (FID) and the kernel inception distance (KID). The proposed BG-Net has good reconstructive ability with faster training speed than those of deep learning-based networks. It reduces the overall training duration of the two-stage framework to the same level as the one-stage framework. Furthermore, the proposed method is adapted to image recurrent outpainting, demonstrating the powerful associative drawing capability of the model.

This article investigates the adaptive optimal tracking problem for a class of nonlinear affine systems with asymmetric Prandtl-Ishlinskii (PI) hysteresis nonlinearities based on actor-critic (A-C) learning mechanisms. Considering the huge obstacles arising from the uncertainty of hysteresis nonlinearity in actuators, we develop a scheme for the conflict between the construction of Hamilton functions and hysteresis nonlinearity. The actuator hysteresis forces the input into a hysteresis delay, thus preventing the Hamilton function from getting the current moment's input instantly and thus making optimization impossible. In the first step, an inverse model is constructed to compensate for the hysteresis model with a shift factor. In the second step, we compensate for the control input by designing a feedback controller and incorporating the estimation and approximation errors into the Hamilton error. Optimal control, the other part of the actual control input, is obtained by taking partial derivatives of the Hamiltonian function after the nonlinearities have been circumvented. At the end, a simulation is given to validate the developed solution.

The anomaly detection techniques for cloud service focus on alerting the operation engineers about the anomalous running state. However, their shortcoming of anomaly interpretability is an obstacle to understanding and further removing the anomalies. To overcome the abovementioned challenge, we propose a tree-like attention-based detection framework CauseFormer that provides both the metric and sample interpretations. Firstly, we develop stepwise attention based on the multi-head attention mechanism, which imitates the rule-based tree formation process. This network block extracts the higher-order features and generates the metric contribution that can be regarded as metric interpretation. Meanwhile, we design the hyper-circle loss function rather than cross-entropy-based approaches to optimize the representation. Then we introduce the majority voting rule into the classifier. This neighbor classification criterion raises the alarms of anomalies and achieves the sample interpretation. Finally, we conduct extensive experiments in four datasets collected from cloud application cases. The experimental results reveal the superiority of CauseFormer in improving detection accuracy and embodying practical interpretability.

Anomaly detection is indispensable for achieving higher availability and reliability in the cloud computing. The traditional autoencoder-based method only models the historical normal samples and then identifies the current online anomaly samples by the fixed threshold of anomaly score. Although more advances have been made in recent years, two main challenges remain: (i) ignoring the historical anomaly samples, (ii) poor self-adaptive ability for online detection. To address the above challenges, we propose a unified detector, namely BroadCAE, which integrates autoencoder with contrastive learning and broad network. Specifically, the reconstruction loss is first replaced by contrastive loss, which equally formulates both normal and anomaly samples. These samples belonging to the same class become closer in a lower-dimensional space. Conversely, different classes of samples are far away from each other. Next, we apply the anomaly-score-based pseudo thresholds to train the dynamic threshold selection, which generates the threshold according to the coming sample. The broad network in dynamic threshold selection takes the place of the deep network, which overcomes catastrophic forgetting and adapts to new online samples. Finally, validation experiments are conducted on four benchmark datasets. Our BroadCAE outperforms the comparative baseline methods by averaging over 4% of the f1-score.

In this article, an adaptive reinforcement learning (RL) control problem is explored for a class of nonstrict-feedback discrete-time systems. First, different from the existing results, considering the noncausal problem which may exist in the backstepping design procedure, a universal system transformation method is first proposed for a class of nonstrict-feedback discrete-time systems. Second, by defining a compensation term to compensate the controller and utilizing the property of radial-basis-function neural network (RBFNN), an RL-based direct adaptive control strategy is developed via a backstepping method to achieve optimal control, and the multigradient recursive (MGR) algorithm is employed to estimate the weight vector. Finally, the stability of the control system is guaranteed and all signals in the closed-loop system are semiglobal uniformly ultimately bounded (SGUUB) on the basis of the Lyapunov theory. In addition, a universal system transformation is first proposed which breaks through the limitations on the controller design for the discrete-time nonstrict-feedback nonlinear system by using the traditional method. The validity of this strategy is verified by two simulation examples that include a course keeping system of the marine vessel.

For a class of nontriangular structural multiagent systems, this article presents a neuro-adaptive prescribed performance consensus control scheme. By using mean value theorem to isolate the virtual variables and neural networks to approximate the ideal controller, the system model is reconstructed, based on which the virtual controllers are able to be derived. The algebraic-loop problem is circumvented utilizing the properties of basis function. With the proposed performance functions, an error transformation is presented, based on which the controller scheme is developed. It is ensured that the follower agents synchronize at a predefined speed, and synchronization error converges to a specified range within a given time. Two Simulations demonstrate the effectiveness of the presented control method.

Humans are able to compliantly interact with the environment by adapting its motion trajectory and contact force. Robots with the human versatility can perform contact tasks more efficiently with high motion precision. Motivated by multiple capabilities, we develop an approximation-based admittance control strategy that adapts and tracks the trajectory with guaranteed performance for the robots interacting with unknown environments. In this strategy, the robot can adapt and compensate its feedforward force and stiffness to interact with the unknown environment. In particular, a reference trajectory is generated through the admittance control to achieve a desired interaction level. To improve the interaction performance, a tracking error bound for both the transient and steady states is prespecified, and a controller is designed to ensure the tracking control performance. In the presence of unknown robot dynamics, neural networks are integrated into tracking controller to compensate uncertainties. The stability and convergence conditions of the closed-loop system are analysed by the Lyapunov theory. The effectiveness of the proposed control method is demonstrated on the Baxter robot.

At present, the dynamic encoding–decoding scheme is utilized in the impulsive consensus control of multiagent systems (MASs) to solve the limited bandwidth problem. However, the unknown nonlinear dynamics and deception attacks will generate some uncertainties inevitably in the encoding–decoding, which may cause the quantizer saturation and then influence the consensus performance. Therefore, the impulsive consensus control problem of uncertain nonlinear MASs based on encoding–decoding under deception attacks is investigated in this article. To address the system uncertainty, an adaptive algorithm with neural networks is designed. Under the proposed estimator for each follower, the designed adaptive law for every follower only needs the information from its own sensor and estimator instead of the quantized information from its neighbors. Then a more general scenario of uncertain deception attack is considered, in which the uncertain deception attacks can occur in the both parts of hybrid impulsive control protocol. An attack observer is introduced to handle this more complex attack by compensating impacts of deception attacks. Next the sufficient conditions for secure consensus of MASs with limited bandwidth are derived. Moreover, although some uncertainties exist in the encoding–decoding, the quantizer saturation can be eliminated by adjusting the parameters of controller. Finally, the validity of given theorems is demonstrated by the simulation experiments.

Developing a distributed output feedback consensus tracking control scheme for nonlinear multiagent systems (MASs) with interconnected dynamics and unmeasurable states holds significant practical importance. Current approaches to this challenge often rely on fuzzy logic systems (FLSs) or neural networks (NNs) for direct compensation of interconnected terms. However, these methods frequently result in incomplete compensation, posing obstacles to achieving true distributed control. In this study, the cyclic-small-gain condition is utilized to address the challenge of unknown interconnected dynamics. This approach effectively decouples the physical coupling among MASs, enabling the realization of distributed control. Further, direct compensation using the cyclic-small-gain condition introduces the potential singularity problem, which we effectively overcome by employing the inequality technique. Based on the presented control scheme, the existing control results for the MASs with interconnected dynamics are extended from stabilization control to trajectory tracking. As proved, the synchronization and observer errors eventually converge to a tunable zero region, enabling each agent to effectively track the leader. Additionally, the proposed control scheme employs a direct adaptive law design approach with a significantly reduced number of adaptive laws. Simulation results validate the theoretical scheme.

The issue of practical fixed-time control is investigated for a category of uncertain nonlinear systems with input dead-zone constraint. Many practical control systems are subject to the constraint of communication resources and input dead zone, which affects the system’s performance and even results in system instability. To handle the above problems, an extended radial basis function neural networks (ERBFNNs) adaptive event-triggered control method is developed to enable the online compensation of input dead zone and schedule the update of control signals. On this foundation, based on the fixed-time stability theorem, a practical fixed-time event-triggered controller is established by the backstepping technique. Technically, the controller can guarantee that the tracking error converges into a small and adjustable set in a fixed time under different initial states, and the boundary of convergence time is dependent on the adjustable design parameters. Meanwhile, all the closed-loop signals are bounded, the communication resources are saved, and the Zeno behavior is also avoided. Finally, some simulation examples are given to illustrate the validity of the presented strategy.

This article focuses on the singularity-free predefined time control design problem of the quantized nonstrict feedback (NSF) nonlinear systems. Radial basis function neural networks (NNs) are introduced to model the unknown nonlinear dynamics. With the property of the NN basis function, the algebraic loop problem posed by the NSF control structures is addressed. The input quantization is addressed by using the nonlinear decomposition technique. A nonlinear filter with predefined time stability is constructed to decrease the computational complexity. Further, by introducing the designed predefined time filter into the backstepping recursive framework, a predefined time dynamic surface control algorithm is developed, in which the improved adding power integration technique is introduced to prevent control singularities. The Lyapunov theory demonstrates the predefined time stability of the closed-loop quantized nonlinear systems. By the developed control algorithm, the controlled system can effectively track the specified command signal. Both the tracking and filtering errors can reach a small neighborhood around zero within the preset time. The validity and superiority of the proposed control algorithm are illustrated by an actual system simulation.

This article investigates the adaptive optimal output-feedback consensus tracking problem for nonlinear multiagent systems (MASs). Although adaptive optimal output-feedback control schemes for nonlinear systems have been developed recently, most results do not consider the two-way interaction between the state observer and its associated subsystem. To address this issue, we formulate the state-observer and the subsystem as a two-player Stackelberg game framework, where the state-observer acts as the follower-player and the subsystem acts as the leader-player. Such a framework helps us to reveal the two-way interaction between the subobserver and the subsystem. Based on this, we design the optimal auxiliary input of the state-observer and the optimal subsystem controller. We implement the optimal policy pair using integral reinforcement learning (IRL) and adaptive critic learning, which provides a critic-only structure. We prove that the Stackelberg-Nash equilibrium is reached and that the closed-loop signals are ultimately uniformly bounded (UUB). We demonstrate the effectiveness of the proposed scheme using a numerical simulation example.

Despite the significant progress in unsupervised domain adaptation (UDA), the performance of UDA methods is still far inferior to that of the fully supervised ones. In practical scenarios, it is usually feasible to acquire labels on a small portion of the target data through active learning (AL), which aims to train an effective model with as few queried instances as possible. However, due to the domain shift, the instances selected by existing AL algorithms can be uninformative, redundant, or outlying. To address this issue, we propose a novel approach, namely, clustering environment-aware learning (CEAL), for active domain adaptation (ADA). CEAL selects potentially the most valuable instances under domain shift by exploring the informativeness and representativeness of target samples in a clustering environment-aware manner. Specifically, for the informativeness, we not only leverage the knowledge of individual points but also their nearby neighbors, by measuring the proposed clustering environment aware informativeness score (CEAIS), thus ensuring that the selected samples are highly informative. For the representativeness, we design two schemes called point distance release (PDR) and informativeness score difference exclusion (ISDE) to guarantee the diversity and validity of the selected samples. Furthermore, we fully utilize the large amount of unlabeled data from target domain via pseudo labeling and adopt information maximization to improve the reliability of the target pseudo labels, thereby further improving the performance of the model. The effectiveness of our method is empirically verified on various benchmark datasets against recent state-of-the-art algorithms.

Graph neural networks (GNNs) have been widely applied in various decision-crucial fields, where accurate predictions with high interpretability are desired. Thus, numerous post-hoc explainers for GNNs have been proposed. However, some prioritize human-intelligible explanations through graph rules, such as the connection rule, which undermines the explanation’s faithfulness to the model. This paper proposes an innovative method, FACExplainer, that re-examines the role of spatial information within GNNs for generating model-faithful explanations. FACExplainer employs activation maps from the last graph convolution to narrow down a compact search space. Our approach further identifies the subgraph that maximizes mutual information as the explanation, eliminating the need for domain-specific knowledge about the downstream task. Empirical analysis of FACExplainer on seven benchmark datasets with three classical GNNs reveals significantly improved explanation quality while consuming less time when compared to leading explainers. The source code of FACExplainer is freely available at https://github.com/HuaYangttt/Facexplainer/.

In modern precision medicine, it is an important research topic to predict cancer drug response. Due to incomplete chemical structures and complex gene features, however, it is an ongoing work to design efficient data-driven methods for predicting drug response. Moreover, since the clinical data cannot be easily obtained all at once, the data-driven methods may require relearning when new data are available, resulting in increased time consumption and cost. To address these issues, an incremental broad Transformer network (iBT-Net) is proposed for cancer drug response prediction. Different from the gene expression features learning from cancer cell lines, structural features are further extracted from drugs by Transformer. Broad learning system is then designed to integrate the learned gene features and structural features of drugs to predict the response. With the capability of incremental learning, the proposed method can further use new data to improve its prediction performance without retraining totally. Experiments and comparison studies demonstrate the effectiveness and superiority of iBT-Net under different experimental configurations and continuous data learning.

Summary With the popularity of mobile Internet networks and mobile terminal equipment, mobile crowdsensing (MCS) has become a popular and economical way of data collection, sharing, and query services. However, the existing privacy‐preserving query schemes MCS‐based less consider the sensing user's privacy leakage at data aggregation phase and querier's privacy leakage at query service phase simultaneously. In this article, we propose a novel privacy‐preserving aggregation and query scheme applied in metro passenger flow via MCS, which achieves the metro passenger flow acquisition and query service and protects the sensing user's identity and location privacy as well as the querier's query privacy. We exploit Paillier cryptosystem and pseudonym mechanism to prevent the privacy leakage, and utilize secure kNN algorithm to protect the query privacy. Meanwhile, we achieve the sensing user accountability based on digital signature algorithm and credible management. The privacy analysis demonstrates that our scheme satisfies the privacy‐preserving and security requirements. The performance evaluation and experimental result show the efficiency of our scheme in practice.

Abstract The dehiscence of the Xanthoceras sorbifolium (X. sorbifolium) may lead to seeds jump out and economic loss. The shape and the degree of the crack will provide the relevant elements for the study of the X. sorbifolium dehiscence and duly picked. Therefore, an improved level set method is proposed for X. sorbifolium crack segmentation. The problems of intensity inhomogeneity and so on, which pose challenges for accurate crack segmentation. The local Gaussian distribution fitting method has a good segmentation effect, but it is sensitive to the initial contour and does not use gradient information, which affects the accurate location of the edge. Aiming at the above problems and the scene of crack segmentation, this paper firstly adopts histogram threshold method to obtain the initial contour automatically. Secondly, the energy function is constructed by combining local and edge information. Finally, the double‐well potential function is used to reduce the oscillation and distortion of the method. In this paper, the experiment results show that the average boundary precision is 88.25% and average segmentation time of each image is 12.7s of the proposed method. After comprehensive analysis of IoU and boundary recall, the method in this paper achieves better results.

Self-similarity is valuable to the exploration of non-local textures in single image super-resolution (SISR). Researchers usually assume that the importance of non-local textures is positively related to their similarity scores. In this paper, we surprisingly found that when repairing severely damaged query textures, some non-local textures with low-similarity which are closer to the target can provide more accurate and richer details than the high-similarity ones. In these cases, low-similarity does not mean inferior but is usually caused by different scales or orientations. Utilizing this finding, we proposed a Global Learnable Attention (GLA) to adaptively modify similarity scores of non-local textures during training instead of only using a fixed similarity scoring function such as the dot product. The proposed GLA can explore non-local textures with low-similarity but more accurate details to repair severely damaged textures. Furthermore, we propose to adopt Super-Bit Locality-Sensitive Hashing (SB-LSH) as a preprocessing method for our GLA. With the SB-LSH, the computational complexity of our GLA is reduced from quadratic to asymptotic linear with respect to the image size. In addition, the proposed GLA can be integrated into existing deep SISR models as an efficient general building block. Based on the GLA, we constructed a Deep Learnable Similarity Network (DLSN), which achieves state-of-the-art performance for SISR tasks of different degradation types (e.g., blur and noise). Our code and a pre-trained DLSN have been uploaded to GitHub†for validation.

When a multi-modal affective analysis model generalizes from a bimodal task to a trimodal or multi-modal task, it is usually transformed into a hierarchical fusion model based on every two pairwise modalities, similar to a binary tree structure. This easily leads to large growth in model parameters and computation as the number of modalities increases, which limits the model's generalization. Moreover, many multi-modal fusion methods ignore that different modalities contribute differently to affective analysis. To tackle these challenges, this article proposes a general multi-modal fusion model that supports trimodal or multi-modal affective analysis tasks, called Multi-modal Interactive Attention Network (MIA-Net). Instead of treating different modalities equally, MIA-Net takes the modality that contributes the most to emotion as the main modality and the others as auxiliary modalities. MIA-Net introduces multi-modal interactive attention modules to adaptively select the important information of each auxiliary modality one by one to improve the main-modal representation. Moreover, MIA-Net enables quick generalization to trimodal or multi-modal tasks through stacking multiple MIA modules, which maintains efficient training and only requires linear computation and stable parameter counts. Experimental results of the transfer, generalization, and efficiency experiments on the widely-used datasets demonstrate the effectiveness and generalization of the proposed method.

The fast finite-time event-triggered consensus control is investigated for a category of uncertain nonlinear multiagent systems (MASs) with full-state constraints. The uncertainty of the system is estimated by the radial basis function neural networks (RBFNNs). Furthermore, to achieve the fast finite-time stability and not violate the full-state constraints, a fast finite-time event-triggered consensus control method is proposed. The proposed control method can achieve the fast finite-time stability of the system, and all the followers can track the output signal of the leader. Meanwhile, the system states do not exceed the boundaries of the full-state constraints, and the communication resources of the system can be saved. Finally, some simulation examples are provided to verify the feasibility of the proposed approach.

This article proposes semantic embedding for image transformers (SEiTs) to explore semantic features of facial morphology in the action unit (AU) detection task. The conventional approaches typically rely on external information (e.g., facial landmarks) to obtain the location of facial components, whereas the SEiT can learn morphological features intrinsically from the face image. The pre-training task, namely semantic masked facial image modeling (SMFIM), aims to actively obtain facial morphological information. The pixels of the input facial image are randomly erased with semantic masks (e.g., nose, eyes, eyebrows, mouth, and lip). The embedding model tries to predict the presence of facial components for the input image that can learn semantic representations of the face simultaneously. The learned semantic embeddings are fed to transformer blocks, which enable global interaction between semantic elements. The SEiT integrates facial morphological information and global interaction characters, appropriate for AU detection. The experiments are conducted on the Binghamton-Pittsburgh 4D (BP4D) dataset and Denver intensity of spontaneous facial action (DISFA) dataset, and the results demonstrate the effectiveness of the proposed SEiT.

Multiparty learning is an indispensable technique to improve the learning performance via integrating data from multiple parties. Unfortunately, directly integrating multiparty data could not meet the privacy-preserving requirements, which then induces the development of privacy-preserving machine learning (PPML), a key research task in multiparty learning. Despite this, the existing PPML methods generally cannot simultaneously meet multiple requirements, such as security, accuracy, efficiency, and application scope. To deal with the aforementioned problems, in this article, we present a new PPML method based on the secure multiparty interactive protocol, namely, the multiparty secure broad learning system (MSBLS) and derive its security analysis. To be specific, the proposed method employs the interactive protocol and random mapping to generate the mapped features of data, and then uses efficient broad learning to train the neural network classifier. To the best of our knowledge, this is the first attempt for privacy computing method that jointly combines secure multiparty computing and neural network. Theoretically, this method can ensure that the accuracy of the model will not be reduced due to encryption, and the calculation speed is very fast. Three classical datasets are adopted to verify our conclusion.

Emotion recognition based on text-audio modalities is the core technology for transforming a graphical user interface into a voice user interface, and it plays a vital role in natural human-computer interaction systems. Currently, mainstream multimodal learning research has designed various fusion strategies to learn intermodality interactions but hardly considers that not all modalities play equal roles in emotion recognition. Therefore, the main challenge in multimodal emotion recognition is how to implement effective fusion algorithms based on the auxiliary structure. To address this problem, this article proposes an adaptive interactive attention network (AIA-Net). In AIA-Net, text is treated as a primary modality, and audio is an auxiliary modality. AIA-Net adapts to textual and acoustic features with different dimensions and learns their dynamic interactive relations in a more flexible way. The interactive relations are encoded as interactive attention weights to focus on the acoustic features that are effective for textual emotional representations. AIA-Net performs well in adaptively assisting the textual emotional representation with the acoustic emotional information. Moreover, multiple collaborative learning (co-learning) layers of AIA-Net achieve multiple multimodal interactions and the deep bottom-up evolution of emotional representations. Experimental results on three benchmark datasets demonstrate the great effectiveness of the proposed method over the state-of-the-art methods.

This paper focuses on the problem of optimal fuzzy output-feedback tracking control for dynamic positioning of marine vessels simultaneously with model uncertainties, unknown disturbances, unavailable velocities and thruster saturations. The control scheme is built by integrating a fuzzy velocity observer, a finite-time disturbance observer, a dynamic auxiliary system, the optimal control strategy with the dynamic surface control. The fuzzy velocity observer is constructed to obtain the unavailable velocities without requiring the certain model dynamics. The finite-time disturbance observer is established to estimate the unknown disturbances. The dynamic auxiliary system is designed to compensate for thruster saturations effects. By incorporating these methods, a disturbance rejection adaptive controller is designed with dynamic surface control. The optimal compensation term is inserted to minimize the cost function of the tracking error system by adaptive dynamic programming. It is shown that the optimal control consisting of the adaptive controller and the optimal compensation term guarantees that all signals in the closed-loop dynamic positioning system are bounded. Finally, simulation results demonstrate the effectiveness of the proposed optimal control scheme.

Label distribution learning (LDL), leveraging the label significance (LS), is more appropriate for solving label ambiguity problems than multilabel learning (MLL). However, directly obtaining the LS of LDL is extremely expensive and challenging. Thus, label enhancement (LE) algorithms are effectively proposed to acquire inherent LS from MLL for training the LDL models. Nevertheless, most existing LE models will suffer from low accuracy and low efficiency with following issues: ignoring mapping relationship between feature and label space, resulting in inaccurate enhanced data; designing independently apart from LDL models, resulting in an inability of unified LE-LDL learning; and requiring to optimize numerous parameters iteratively, resulting in worse training efficiency. Consequently, a novel unified LE-LDL learning framework, namely stacked graph-regularized polynomial-based fuzzy broad learning system (SGP-FBLS), is proposed by following three innovations: polynomial-based fuzzy system is introduced to enhance feature mapping ability while improving the learning performance effectively; graph regularized-based optimization objective function (GP-FBLS) is presented by considering interinstance correlation and label correlation to mine potential LS, thereby improving the accuracy of subsequent LDL tasks; and a weight stacked strategy is innovatively proposed to directly transmit LS and weighted parameters from GP-FBLS to SGP-FBLS without retraining, achieving the most satisfactory performance while significantly improving the training efficiency. Finally, comparative studies on 19 practical datasets demonstrate the effectiveness and superiority of proposed methods.

This article considers the prescribed performance output-feedback cooperative control of multiagent systems with nonparametric uncertainties. Scale and performance functions are proposed to construct a barrier function, based on which the adaptive prescribed performance control scheme is developed. Therein, the fuzzy observers are employed to estimate the unavailable states. The proposed scheme has the following characteristics: first, the tracking errors are always limited to a specified boundary. Second, the tracking error converges to a specified accuracy within a given time, and the settling time and tracking accuracy are determined only by the user and no longer depend on the initial conditions. Third, the distributed fuzzy controller design uses only the output information from agent and its neighbor. The effectiveness and practicality of the proposed method are demonstrated by two simulation examples.

This article investigates the fault detection problem of unmanned marine vehicles (UMVs) under the influence caused by replay attacks. First, the dynamics of UMV are modeled by a Takagi--Sugeno (T--S) fuzzy system with an unknown membership function, which includes the nonlinear coupling of the internal state of the system, the environmental multisource disturbance as well as the potential thruster failure on UMV. Then, the possible replay attack from the sensor to the shore-based center is considered, and a switching-type attack tolerant fault detection filter is designed. Sufficient conditions are given to ensure that the filtering augmented system is stable and with stochastic finite frequency$H_{\infty }$and$H_{-}$performances, which reflect the robustness to the disturbance and sensitivity to the fault. On this basis, through a series of mathematical processing, the linear solvable conditions for the design of fault detection filters are obtained. Finally, the effectiveness of the proposed algorithm is verified by simulations.

Collaborative multiview clustering methods can efficiently realize the view fusion by exploring complementary and consistent information among multiple views. However, these studies ignore all the differences between multiple views in fusion. In fact, in the multiview clustering, the data are diverse from view to view. The larger the difference between any two views is, the more the fusion of these views is required. Moreover, a global tradeoff parameter is generally adopted to restrain the penalty related to the disagreement of all views, which is often defined empirically. Inspired by the idea of transfer learning, a series of novel collaborative multiview clustering algorithms are proposed to tackle these challenges. In the most basic one, each view performs clustering independently and learns from others to improve its own clustering performance, in which a global learning factor is defined to control the interaction between multiple views. The fuzzy memberships are regarded as the important knowledge to provide guidance between views, and the consensus constraint is defined to ensure the consistent partitions of all views. In addition, the local adaptive learning factors between any two views instead of a global fixed one are adopted in an improved version to emphasize the difference between views, and the adjustment strategy for the learning factor is further designed to guarantee the stability of multiview clustering without the influence of initial values. Finally, to identify the significance of different views to the clustering, the extended versions are excavated with the assignment of view weights and the maximum entropy regularization technique is employed to optimize the weights. Experiments on various real-world multiview datasets verify the superiority of the presented approaches.

In this article, the research on fixed-time tracking control problem of multiple-input multiple-output nonlinear systems with nonstrict feedback control structure is carried out. By means of the fuzzy logic systems, the unknown system nonlinear dynamics are identified, and the “algebraic loop problem” is solved. Then, through the combination of adaptive backstepping recursive technology and adding power integration technology, a nonsingular fixed-time adaptive tracking control scheme is presented. Under the action of the presented control scheme, the system can track the specified reference signal within a fixed time independent of the initial state of the system, and the tracking control error can converge to zero asymptotically. Next, on the basis of the fixed-time Lyapunov stability theory, the practical fixed-time stability of the closed-loop system is theoretically demonstrated. Finally, two simulations verify the validity and practicability of the proposed control scheme.

Kernel clustering has the ability to get the inherent nonlinear structure of the data. But the high computational complexity and the unknown representation of the kernel space make it unavailable for the data clustering in distributed peer-to-peer (P2P) networks. To solve this issue, we propose a new series of random feature-based collaborative kernel clustering algorithms in this article. In the most basic algorithm, each node in a distributed P2P network first maps its data into a low-dimensional random feature space with the approximation of the given kernel by using the random Fourier feature mapping method. Then, each node independently searches the clusters with its local data and the collaborative knowledge from its neighbor nodes, and the distributed clustering is performed among all network nodes until reaching the global consensus result, i.e., all nodes have the same cluster centers. In addition, an improved version is designed with assignment of feature weights, which is optimized by the maximum-entropy technique to extract important features for the cluster identification. What’s more, to relief the impact of different kernel functions and related parameters on clustering results, the combination of multiple kernels rather than a single kernel is adopted for the low-dimensional approximation, and the optimized weights are assigned to provide the guidance on the choice of the kernels and their parameters and discover significant features at the same time. Experiments on synthetic and real-world datasets show that the proposed methods achieve similar and even better results than the traditional kernel clustering methods on various performance metrics, including the average classification rate, the average normalized mutual information, and the average adjusted rand index. More importantly, the low-dimensional random features approximated to kernels and the distributed clustering mechanism adopted in these methods bring the greatly lower temporal complexity.

This article investigates the event-triggered predefined time output feedback control design problem for nonlinear interconnected systems with nonstrict feedback control structures. Compared with the existing event-triggered output feedback control design schemes, the most significant contribution of this article is that the system stability time can be preset directly. Fuzzy logic systems (FLSs) and FLSs-based state observer deal with unknown nonlinear dynamics and unmeasured states. Combining with dynamic surface control technology and event-triggered mechanism based on switching threshold strategy, an event-triggered predefined time decentralized output feedback control method is proposed, in which a predefined time filter is designed to solve the computational complexity problem. In addition, the algebraic loop problem and control singular problem are also solved, respectively, by applying the property of fuzzy basis function and L’Hospital’s rule. Utilizing the predefined time Lyapunov stability theory, the system stability analysis is given. Finally, the effectiveness and practicability of the proposed control method are verified by practical system simulation cases.

This article investigates the containment control for state-constrained multiagent systems. Existing results assume that the dynamic of the multiple leaders is known as prior knowledge. First, a distributed adaptive observer is used to estimate the leader's unknown parameters. The local reference signal and its high-order derivatives are generated by an$n$th-order filter, which will be employed in the backstepping design procedures. Second, a log-type nonlinear state-dependent barrier function is established to cope with the time-varying asymmetric full-state constraints. The constrained system is equivalently transformed into a nonconstrained one. Finally, a distributed adaptive fuzzy containment control scheme is developed for the nonconstrained system. Only one adaptive law is required in each distributed controller, and no feasibility conditions and partial-derivative terms are involved in the virtual and actual controllers. In addition, the time derivatives of the candidate Lyapunov functions are guaranteed to be negative semidefinite by introducing a series of reduced-order smooth functions. It is proved that the containment error converges to a user-predefined interval, and all the signals in the closed-loop system are bounded. The time-varying asymmetric full-state constraints imposed on the followers are not violated. Two illustrative examples demonstrate the effectiveness of the suggested approach.

This article researches the adaptive fuzzy tracking control problem for uncertain nonlinear systems with multiple actuators and sensors faults. Compared with previous studies, all states of the system cannot be measured accurately in this article due to the existence of multiple sensors faults, and it brings significant difficulties to the design of the control scheme. Moreover, multiple actuators faults and external disturbance can also bring challenges to controller design. To solve these problems, we design different adaptive update laws to relieve the effects of unknown actuators faults, sensors faults, and external disturbance, respectively. Furthermore, the actual states can be estimated by combining sensors outputs with adaptive parameters. On this basis, the unknown nonlinear functions are approximated through the combining of fuzzy logic systems and the estimation of states. Then, a novel adaptive fuzzy tracking control algorithm is completed by the backstepping method. By employing the Lyapunov function, the presented novel fault-tolerant control algorithm can guarantee all signals of the system are bounded in spite of the occurrence of multiple faults. Finally, we verify the availability of the novel algorithm by comparing the control performance of the two algorithms.

Existing approaches to optimal control of uncertain switched systems require heavy computations for approximating and learning the optimal solution of the Hamilton–Jacobi–Bellman equation. To overcome this problem, a fuzzy adaptive inverse optimal control strategy is first developed for switched systems, which minimizes not only the cost function but also circumvents solving the Hamilton–Jacobi–Bellman equation. Specifically, an alternative practical inverse approach is developed by two Lyapunov functions method, based on which the inverse optimality regarding a meaningful cost function is achieved. In addition, a new condition of admissible edge-dependent average dwell time is developed by applying the extended multiple Lyapunov functions method. Guided by this weaker condition, the stability of the considered switched system is proved. Finally, simulations are carried out to verify the developed method.

Categorical data are widely available in many real-world applications, and to discover valuable patterns in such data by clustering is of great importance. However, the lack of a decent quantitative relationship among categorical values makes traditional clustering approaches, which are usually developed for numerical data, perform poorly on categorical datasets. To solve this problem and boost the performance of clustering for categorical data, we propose a novel fuzzy clustering model in this article. At first, by approximating the maximum a posteriori (MAP) estimation of a discrete distribution of data partition, a new fuzzy clustering objective function is designed for categorical data. The Bayesian dissimilarity measure is formulated in this objective to tackle the subtle relationships between categorical values efficiently. Then, to further enhance the performance of clustering, a novel Kullback–Leibler divergence-based graph regularization is integrated into the clustering objective to exploit the prior knowledge on datasets, for example, the information about correlations of data points. The proposed model is solved by the alternative optimization and the experimental results on the synthetic and real-world datasets show that it outperforms the classical and relevant state-of-the-art algorithms. We also present the parameter analysis of our approach, and conduct a comprehensive study on the effectiveness of the Bayesian dissimilarity measure and the KL divergence-based graph regularization.

Recent years have witnessed a drastic surge in graph representation learning, which usually produces low-dimensional and crisp representations from graph topology and high-dimensional node attributes. Nevertheless, a crisp representation of a node or graph actually conceals the uncertainty and interpretability of features. In citation networks, for example, the reference between the two papers is always involved with fuzziness denoting the correlation degrees, that is, one connection may simultaneously belong to strong and weak references in different beliefs. The uncertainty in node connections and attributes inspires us to delve into fuzzy representations. This article, for the first time, proposes an unsupervised fuzzy representation learning model for graphs and networks to improve their expressiveness by making crisp representations fuzzy. Specifically, we develop a fuzzy graph convolution neural network (FGCNN), which could aggregate high-level fuzzy features, leveraging fuzzy logic to fully excavate feature-level uncertainties, and finally generate fuzzy representations. The corresponding hierarchical model composed of multiple FGCNNs, called deep fuzzy graph convolution neural network (DFGCNN), is able to generate fuzzy node representations which are more expressive than crisp ones. Experimental results of multiple network analysis tasks validate that the proposed fuzzy representation models have strong competitiveness against the state-of-the-art baselines over several real-world datasets.

This article investigates a class of switched nonlinear systems with output hysteresis, where the switching signal is arbitrary. The considered output hysteresis nonlinearity is captured by the Bouc-Wen model, which causes an uncertain gain that imposes a significant challenge on our control design. To overcome this problem, we propose an adaptive fuzzy optimal control scheme. In our scheme, the Nussbaum gain technique is used to compensate for output hysteresis, and, at each iteration, the actor-critic structure is progressively feedback and adjusted to design the optimal controller. Finally, our proposed design scheme can guarantee the stability of the nonlinear switched systems, which is demonstrated in the simulation results.

This article studies the problem of trajectory optimization for autonomous ground vehicles with the consideration of irregularly placed on-road obstacles and multiple maneuver phases. By introducing a series of event sequences, a new multiphase constrained optimal control formulation is constructed to describe the automatic overtaking process. Although existing trajectory optimization techniques can be applied to address the constructed problem, they may suffer from poor or premature convergence issues due to the complexity of the mission formulation. Thus, to offer an effective alternative, a novel desensitized trajectory optimization method is designed and implemented to explore the optimal overtaking maneuver for the AGVs. The proposed method applies a double layer structure, where an enhanced intelligent optimization method is used in the outer layer such that the main inner optimization routine can be boosted by starting at a better reference solution. The algorithm convergence as well as the solution optimality conditions are theoretically analyzed. Numerical results are provided to illustrate the validity of the established formulation. Comparative case studies were executed to demonstrate the quality of the obtained solution and the enhanced performance of the proposed trajectory optimization method.

Cluster ensemble improves the robustness and stability of clustering performances by utilizing multiple solutions. Although traditional cluster ensemble methods have achieved promising performances, they are not adaptive enough to cope with data sets that have multiple levels of complexities. Besides, these methods may contain noisy and redundancy members which have negative effects. To mitigate the above issues, in this paper, we propose a multi-objective filter refinement scheme (MOFRS). First, we perform various clustering methods on different representations of data to generate diverse solutions. Second, we propose a solution filter to select a proper method and reduce the number of initial partitions for a given data set. Third, four stability indices are designed to split instances into stable and unstable groups. Fourth, objective functions based on diversity and quality are utilized to quantify the goodness of base clustering solutions. Finally, we design an improvement oriented multi-objective evolutionary algorithm to optimize these objective functions. Extensive experimental results conducted on 27 real-world data sets show that MOFRS outperforms most cluster ensemble selection methods, and achieves statistically significant improvements, compared with full ensemble methods.

Ensemble clustering has an advantage in producing a more promising and robust clustering result by combining multiple partitions strategically. The quality of both base partitions and co-association matrix plays an essential role in improving the consensus partition. However, the current ensemble clustering methods have several limitations: 1) The noise in high-dimensional feature space is ignored; 2) The independent base partition generation process does not pay attention to ambiguous samples; 3) The co-association matrix and the weights of base partitions commonly lack of theoretical optimization. In order to address these issues, we propose an adaptive ensemble clustering framework with boosting BLS-based autoencoder (BoostAEC). In the generation step, a boosting BLS-based autoencoder (BoostBLSAE) is designed to generate base partitions sequentially, which learns compressed feature subspaces for ambiguous samples and adaptively evaluates the corresponding weights of reliability. In the integration step, we construct a fuzzy membership function to capture the inter-cluster correlation and explicitly propose a consensus objective function to optimize the unified co-association matrix by considering the weighted base partitions. Extensive experiments on various real-world datasets demonstrate the superior performance of BoostAEC to the state-of-the-art ensemble clustering methods.