This article first proposes a discrete-time sliding flexible performance preset boundary (DT-SFPPB)-based control algorithm for input saturated discrete-time nonlinear systems (IS-DTNSs). Compared to the existing discrete-time prescribed performance control (DT-PPC) algorithms, the PPB of them present a “trumpet” shape, resulting in fundamental conservation of the transient performance, and whenever the initial error is altered, it is essential to recheck whether the new error meets the original constraint condition, if not, a new PPB with a larger measure has to be reselected. By designing a novel DT-SFPPB associated with the initial error, which can always envelope the initial error with an arbitrarily preset initial measure, indicating that the proposed approach can be utilized for IS-DTNSs with arbitrary initial error without compromising the initial transient performance. Furthermore, the coupling effect between performance preset and input saturation is also considered, by designing a novel equilibrium boundary related to saturation, so that the proposed approach can achieve the synergy between performance preset and input security, i.e., the designed DT-SFPPB can flexibly expand when input saturation occurs to avoid vulnerability, and when the control input is within the safe boundary, it rapidly reverts to the original PPB to guarantee the specified performance metrics. The findings demonstrate that the developed approach guarantees that the system output tracks the desired signal with the specified performance metrics, and all of the tracking errors are always enveloped within their corresponding DT-SFPPBs. The devised approach is exemplified by means of simulation examples.

This article first proposes a sliding flexible prescribed performance boundary-guided reinforcement learning (SFPPB-RL) control approach for input-constrained nonlinear systems (ICNSs). By designing a sliding flexible prescribed performance boundary, which not only can adaptively adjust the initial boundary according to the initial error, but also dynamically adjust the constraint relaxation according to the coupling correlation between the input constraint and the performance constraint, a novel prescribed performance control (PPC) approach is proposed. Compared with the existing "horn" shape performance boundary-based PPC methods, the limitation of having to repeatedly debug design parameters or sacrifice initial transient performance to meet different initial error requirements is eliminated. Meanwhile, the coupling effect between the input constraint and the performance constraint is also considered, and the balance between input safety and control performance is achieved by constructing an auxiliary system. Furthermore, combining identifier-critic-actor structure-based RL strategy and backstepping technique, a sliding flexible PPB-guided reinforcement learning (SFPPB-RL) optimal control algorithm is developed, which minimizes the cost function while ensuring input safety and prescribed performance indicators. The validity of the proposed algorithm is demonstrated via simulations.

Single domain generalization aims to develop a robust model trained on a source domain to generalize well on unseen target domains. Recent progress in single domain generalization has focused on expanding the scope of training data through style (e.g., backgrounds) augmentation. However, existing methods are difficult to generate data with large style shifts due to the lack of precise correlation measures between the generated and original data, and they struggle to effectively capture the consistency between the generated and original data when learning feature representations. In this article, we propose a novel Mutual Information-guided Style Augmentation (MISA) based single domain generalization method. Specifically, MISA incorporates a style diversity module, which uses the matrix-based Rényi’s \(\alpha\) -order entropy functionals to compute an approximate mutual information value between the augmented and original data, minimizing it to guide style generator learning. Moreover, MISA combines the merits of the random convolution and affine transformation to further improve the texture diversity of the augmented data. Additionally, MISA introduces a representation learning module, which minimizes the approximate mutual information value between the prediction logits of the original sample and its corresponding residual component to capture the consistency between the generated and original data for feature representation optimization. Using five real-world datasets, the extensive experiments have demonstrated the effectiveness of MISA, in comparison with state-of-the-art methods.

Understanding gene-drug associations is essential in drug discovery, where advances in artificial intelligence and data-driven methods have revolutionized the identification of novel therapeutic applications, molecular pathways, and potential drug targets for existing medications. However, current computational methods are hindered by data sparsity and limited capacity to model the complex interactions between genes and drugs. To address these challenges, we propose a novel computational framework-disentangled contrastive learning with dynamic intent adaptation (DIACL)-for predicting unknown gene-drug associations. DIACL leverages disentangled contrastive learning to decompose the latent factors driving drug-gene interactions, yielding more robust and interpretable feature representations. Additionally, we introduce a dynamic intent representation mechanism and an adaptation graph augmentation strategy to enhance the model's ability to capture fine-grained interaction details. Extensive experiments on benchmark datasets demonstrate that DIACL significantly outperforms state-of-the-art methods in terms of prediction accuracy and generalization capability. Our findings highlight DIACL's potential as a scalable and efficient tool for accelerating drug discovery and advancing precision medicine by identifying therapeutic targets.

Protein representation learning plays a crucial role in obtaining a comprehensive understanding of biological regulatory mechanisms and in developing proteins and drugs for therapeutic purposes. However, labeled proteins, such as sequenced and functionally annotated data, are incomplete and few. Thus, contrastive learning has emerged as the preferred technique for learning meaningful representations from unlabeled data samples. In addition, at present, natural proteins cannot be fully described by extracting protein knowledge from a single domain. Therefore, Pro-CoRL, a pro tein co ntrastive models framework based on multi-knowledge r epresentation l earning, was proposed in this study. In particular, Pro-CoRL smooths the objective function using convex approximation, thereby improving the stability of training. Extensive experiments on predicting protein–protein interaction types and clustering protein families have confirmed the high accuracy and robustness of Pro-CoRL.

Stable learning aims to leverage the knowledge in a relevant source domain to learn a prediction model that can generalize well to target domains. Recent advances in stable learning mainly proceed by eliminating spurious correlations between irrelevant features and labels through sample reweighting or causal feature selection. However, most existing stable learning methods either only weaken partial spurious correlations or discard part of true causal relationships, resulting in generalization performance degradation. To tackle these issues, we propose the Dual Feature Learning (DFL) algorithm for stable learning, which consists of two phases. Phase 1 first learns a set of sample weights to balance the distribution of treated and control groups corresponding to each feature, and then uses the learned sample weights to assist feature selection to identify part of irrelevant features for completely isolating spurious correlations between these irrelevant features and labels. Phase 2 first learns two groups of sample weights again using the subdataset after feature selection, and then obtains high-quality feature representations by integrating a weighted cross-entropy model and an autoencoder model to further get rid of spurious correlations. Using synthetic and four real-world datasets, the experiments have verified the effectiveness of DFL, in comparison with eleven state-of-the-art methods.

The surge in accessible high-throughput molecular data presents computational challenges for the precision medicine in cancer. Genetic mutations have the potential to act as reliable biomarkers indicating responses to targeted drugs. Accurate prediction of mutation-drug associations is critically important for drug development and cancer treatment. We propose a novel graph convolutional network method, MDAGCN, to predict the mutation-drug associations with specific types (sensitive/resistant) in cancer. To enhance both the efficiency and accuracy of training, we begin by constructing a feature and topological graph using the k-Nearest Neighbors algorithm, incorporating the structural relationship and feature data associated with mutation-drug interactions. Experimental results show that MDAGCN outperforms state-of-the-art methods in different experimental settings. Moreover, we show the effectiveness of graph sampling technique for training signed graphs. MDAGCN is a comprehensive end-to-end framework that could be broadly applicable to cancer pharmacogenomics. This framework has the potential to facilitate the mapping from the discovering novel mutation-drug associations to in-depth analysis of drug sensitivity and resistance.

This article first presents a dual flexible prescribed performance control (DFPPC) approach of input saturated high-order nonlinear systems (IS-HONSs). Compared to the existing PPC approaches of IS-HONSs, under which the performance constraint boundaries (PCBs) are usually fixed and bounded, resulting in a restriction of the initial error in the algorithm implementation; in addition, the coupling relationship between performance constraints and input saturation is usually ignored, resulting in the methods are very fragile when input saturation occurs. By designing the novel tensile model-based PCBs that depend on output and input constraints, the proposed DFPPC method provides sufficient resilience for both the initial conditions and the input saturation, so that the proposed DFPPC method can not only be suitable for multiple types of initial errors by adjusting the parameters, including , , and , where , and denote the initial PCBs; but also can achieve a good balance between input saturation and performance constraints, i.e., when the control input reaches or exceeds the saturation threshold, the PCBs can adaptively extend to avoid the singularity, and when the control input returns to the saturation threshold range, the PCBs are then adaptively restored to the original PCBs. The results show that the proposed DFPPC algorithm guarantees semi-global boundedness for all closed-loop signals, while ensuring that the system output accurately tracks the desired signal, and it consistently maintains the tracking error within the PCBs. The developed algorithm is illustrated by means of simulation instances.

The issue of sliding flexible prescribed performance control (SFPPC) of input saturated nonlinear systems (ISNSs) is first studied in this article. Compared to the traditional PPC and the finite-time PPC algorithms for ISNSs, under which the performance constraint boundaries (PCBs) present the symmetrical or asymmetric “horn” shape, which leads to a large jitter in the tracking error before the system reaches steady state; and once the parameters are selected, the PCBs are fixed, when the initial state (or reference signal) changes, it is necessary to reverify whether the initial error still satisfies the initial constraint condition. By designing a new pair of sliding flexible PCBs (SFPCBs) associated with the initial error, a novel SFPPC algorithm is presented in this article, which presents two main advantages: 1) the SFPCBs can slide adaptively with the initial tracking error without increasing the measure of the initial PCBs, implying that the proposed SFPPC algorithm can be applied to ISNSs with arbitrary initial errors without sacrificing the initial control performance; 2) the proposed SFPPC algorithm achieves a tradeoff between performance constraint and input saturation, i.e., the SFPCBs can adaptively increase when the control input exceeds the maximum allowable threshold, effectively avoiding singularity, and when the control input is within the saturation threshold range, the SFPCBs can adaptively revert back to the original PCBs. The results demonstrate that the proposed SFPPC approach can guarantee that the system output tracks the desired signal, and the tracking error always kept within the SFPCBs that depend on initial error, input, and output constraints. The developed algorithm is exemplified by means of simulation instances.

Panoramic driving systems are crucial for autonomous driving but face challenges in real-time performance and reliability. This paper proposes an end-to-end, multi-tasking MtpNet that reduces latency and enhances detection accuracy. The convolution was upgraded using the Efficient Layer Aggregation Network, and precise multi-task loss functions and more effective training strategies were devised. Our results demonstrate improved performance in small object detection, partial occlusion handling, and drivable area segmentation. The recall of the traffic object detection is 1.3% higher than that of the state-of-the-art model, reaching 94.1%, the mAP50is 6.4% higher, reaching 89.8%, and the mIoU of the drivable area segmentation is 2.7% higher, reaching 95.9%. Additionally, the accuracy of lane detection reached 88.7%. The visual comparison using three datasets TuSimple, CityScapes, and CULane demonstrates that MtpNet has good detection segmentation and strong robustness under various conditions. Codes are available at https://github.com/ErLinErYi/mtpnet

The decoder is a key component in deep networks for the semantic segmentation of street views. The existing methods rely on the limited receptive field for feature extraction without considering the contextual information, which could lead to errors in understanding complex scenes. Moreover, a balance of contextual information and computational cost must be considered to meet the needs of real-world applications. To address these problems, we introduce a Spatial Plaid Attention Decoder network, which uses a lightweight decoder with Spatial Plaid Attention to perform highly efficient operations for semantic segmentation. With approximately 4 million parameters (9.75% of the UPerNet), our decoder achieves state-of-the-art performance on public datasets such as Cityscapes and ADE20K, with 84.84% and 54.0% mIoU, respectively. In addition, our method reduces the total Flops by 34.95% and 32.85%, respectively. We demonstrate how contextual information helps the network in object recognition and how object features and contextual features contribute to the scene segmentation and recognition.

Leveraging trace-rich features within embedded spaces has been established as effective in image manipulation localization (IML). Nevertheless, the feature of manipulated traces frequently comprises substantial redundant information only loosely related to IML tasks. This complexity has hindered existing methods in fully comprehending the essence of trace features. In light of this challenge, we introduce a novel decoupling representation learning network (DRN) tailored for IML. The DRN excels at decoupling intricate multidomain information and transforming it into representations directly pertinent to IML objectives. This is achieved through a meticulously designed frequency decoupling representation learning module (FDM) and spatial decoupling representation learning module (SDM). Specifically, the FDM operates by acquiring distinct low and high-frequency components to effectively decouple redundant information. The decoupled high-frequency components are then harnessed as intricate trace complements, enhancing the overall aggregation process. In addition, the redundant information is expertly separated into authentic and manipulated representations through the use of channel activation maps in SDM. Through extensive experimentation on three public benchmarks including CASIA, NIST, and Coverage, our method consistently demonstrates superior performance and enhanced robustness compared with existing state-of-the-art methods.

Single domain generalization aims to learn a model that generalizes well to unseen target domains by using a related source domain. However, most existing methods only focus on improving the generalization performance of the model during training, making it difficult to achieve satisfactory performance when deployed in the target domain with large domain shifts. In this paper, we propose a Practical Single Domain Generalization (PSDG) method, which first leverages the knowledge in a source domain to establish a model with good generalization ability in the training phase, and subsequently updates the model to adapt to target domain data using knowledge in the unlabeled target domain during the testing phase. Specifically, during training, PSDG leverages a newly proposed style (e.g., background features) generator named StyIN to generate novel domain data. Moreover, PSDG introduces style-diversity regularization to constantly synthesize distinct styles to expand the coverage of training data, and introduces object-consistency regularization to capture consistency between the currently generated data and the original data, making the model filter style knowledge during training. During testing, PSDG uses a sample-aware and sharpness-aware minimization method to seek for a flat entropy minimum surface for further model optimization by using the knowledge in the unlabeled target domain. Using three real-world datasets the experiments have demonstrated the effectiveness of PSDG, in comparison with several state-of-the-art methods.

Recent image manipulation detection approaches primarily rely on sophisticated Convolutional Neural Network (CNN)-based models for region localization, while they tend to ignore: 1) the feature correlations that exist between manipulated and non-manipulated regions. 2) the significance of multi-scale representations in detecting manipulated regions of varying sizes, consequently hampering the overall performance of image manipulation detection. To address these limitations, we propose a novel approach, called Cascade Hierarchical Graph Convolutional Network (Cas-HGCN), which comprehensively learns the feature correlations between manipulated and non-manipulated regions at different scales using the Feature Correlations Modeling (FCM) module. Specifically, the FCM module treats the grids in the hierarchical image/feature maps as nodes, constructs a fully-connected graph by connecting each node, and leverages it to learn and refine feature correlations across different scales in a cascading manner. This process results in high discriminability for distinguishing manipulated and non-manipulated regions. Extensive experiments conducted on three public datasets, namely CASIA, NIST, and Coverage, demonstrate the promising detection accuracy achieved by Cas-HGCN without the need for pre-training on large datasets, surpassing the performance of existing state-of-the-art competitors.

Text-based person re-identification (ReID) has enabled canonical applications in searching for and tracking targets from large-scale surveillance images with textual descriptions. Yet, existing text-based person ReID systems employ centralized model training that gathers images captured by different institutes' cameras into one place, which poses severe privacy threats to sensitive institutional information. This work is then devoted to exploring privacy-preserving text-based person ReID and proposes the framework of FedSH by tailoring the federated learning paradigm for distributed searching knowledge extraction. Specifically, FedSH resolves the local model generalization and entity boundary obscuring limitations, caused by inner-institute data homogeneity and inter-institute data heterogeneity, via building multi-granularity feature representation and a semantically self-aligned network. Meanwhile, it reduces the communication burden introduced by the embedding for multiple modals by updating common representation subspaces during federated learning. Experimental results on two public benchmarks demonstrate that our method can achieve at most 16.47% and 16.02% person ReID performance improvement by the Rank-1 metric, compared with 6 State-of-The-Art (SoTA) baselines and 6 ablation studies. We believe that our work will inspire the community to investigate the potential of implementing Federated Learning in real-world image retrieval and ReID scenarios.

LncRNA-protein interactions are ubiquitous in organisms and play a crucial role in a variety of biological processes and complex diseases. Many computational methods have been reported for lncRNA-protein interaction prediction. However, the experimental techniques to detect lncRNA-protein interactions are laborious and time-consuming. Therefore, to address this challenge, this paper proposes a reweighting boosting feature selection (RBFS) method model to select key features. Specially, a reweighted apporach can adjust the contribution of each observational samples to learning model fitting; let higher weights are given more influence samples than those with lower weights. Feature selection with boosting can efficiently rank to iterate over important features to obtain the optimal feature subset. Besides, in the experiments, the RBFS method is applied to the prediction of lncRNA-protein interactions. The experimental results demonstrate that our method achieves higher accuracy and less redundancy with fewer features.

Almost all existing causal feature selection methods are proposed without considering the problem of sample selection bias. However, in practice, as data-gathering process cannot be fully controlled, sample selection bias often occurs, leading to spurious correlations between features and the class variable, which seriously deteriorates the performance of those existing methods. In this article, we study the problem of causal feature selection under sample selection bias and propose a novel Progressive Causal Feature Selection (PCFS) algorithm which has three phases. First, PCFS learns the sample weights to balance the treated group and control group distributions corresponding to each feature for removing spurious correlations. Second, based on the sample weights, PCFS uses a weighted cross-entropy model to estimate the causal effect of each feature and removes some irrelevant features from the confounder set. Third, PCFS progressively repeats the first two phases to remove more irrelevant features and finally obtains a causal feature set. Using synthetic and real-world datasets, the experiments have validated the effectiveness of PCFS, in comparison with several state-of-the-art classical and causal feature selection methods.

BACKGROUND: Target drugs play an important role in the clinical treatment of virus diseases. Virus-encoded proteins are widely used as targets for target drugs. However, they cannot cope with the drug resistance caused by a mutated virus and ignore the importance of host proteins for virus replication. Some methods use interactions between viruses and their host proteins to predict potential virus-target host proteins, which are less susceptible to mutated viruses. However, these methods only consider the network topology between the virus and the host proteins, ignoring the influences of protein complexes. Therefore, we introduce protein complexes that are less susceptible to drug resistance of mutated viruses, which helps recognize the unknown virus-target host proteins and reduce the cost of disease treatment. RESULTS: Since protein complexes contain virus-target host proteins, it is reasonable to predict virus-target human proteins from the perspective of the protein complexes. We propose a coverage clustering-core-subsidiary protein complex recognition method named CCA-SE that integrates the known virus-target host proteins, the human protein-protein interaction network, and the known human protein complexes. The proposed method aims to obtain the potential unknown virus-target human host proteins. We list part of the targets after proving our results effectively in enrichment experiments. CONCLUSIONS: Our proposed CCA-SE method consists of two parts: one is CCA, which is to recognize protein complexes, and the other is SE, which is to select seed nodes as the core of protein complexes by using seed expansion. The experimental results validate that CCA-SE achieves efficient recognition of the virus-target host proteins.

This paper studies a convincingly secure transmission framework under an allowable outage probability for practical finite-alphabet inputs, where a full-duplex receiver (Bob) is taken into account to emit the artificial noise for deteriorating the eavesdropper’s decoding performance. We develop a secure-reliable mechanism to take the place of prior secrecy rate (SR) maximization strategy, where a closed form expression is invoked for substituting the non-closed SR expression upon exploiting the multi-exponential decay fitting approach. Hence, the intractable expectation operation over a large number of noise samples is circumvented. Moreover, a pair of critical probabilities of the reliable transmission and secure outage are first analyzed, and then a low-complexity optimization scheme is formulated. Apart from designing the transmission scheme for classically secure networks consisting of a transmitter, Bob and an eavesdropper, we further carry out an investigation on conceiving a secure-reliable strategy against multiple Eves for improving the system’s extensibility. To this end, analytical expressions of both the reliability outage and secrecy outage probabilities for multiple-Eve scenarios are also derived. Furthermore, a pragmatic iterative solution is conceived for addressing the corresponding max-min optimization problem. Finally, the simulation results validate the significance of our considered secure-reliable transmission in terms of the average SR performance attained.

Because of discrepant deteriorations of the intended receiver and the unintended receiver, artificial noise (AN) can be invoked in conjunction with the precoder to wireless transmissions for enhancing the secrecy rate (SR) performance as long as we elaborately frame them. This paper studies a secure transmission strategy by jointly designing the precoder and AN beamformer at the relay network, where a passive eavesdropper and finite-alphabet inputs are taken into account. We propose a pair of solutions for low-order modulation and high-order modulation, respectively. To solve the first optimization problem, we propose a low-complexity algorithm with the aid of the invoked cut-off rate. Interestingly, we find that the phase of an optimum precoder for maximizing the SR has a correlation to both the channels spanning from the transmitter to the relays and spanning from the relays to the legitimate receiver. Furthermore, we reveal that the AN beamformer vector has at most one non-zero component, which only locates at the position corresponding to the minimum element of the channel between the relays and the intended receiver. According to these findings, the SR maximization problem over the two vectors is simplified as one only related to a pair of scalars. As for the high-order modulation, a new solution is further proposed for circumventing the predicament that the computational complexity exponentially increases as the size of the adopted modulation increases, where we not only eliminate two-layer summation over the legitimate symbols but also conceive a concave maximization SR problem. Finally, simulation results demonstrate the efficiency of the proposed algorithms in terms of the SR performance.