Edge Intelligence (EI) combines edge computing and artificial intelligence to deliver low-latency and resource-efficient services. Integrated Sensing and Communication (ISAC) further empowers EI by enhancing edge perception and accelerating intelligent model training. However, integrating ISAC into EI complicates the coordination of dynamically varying sensing, communication, and computation resources, especially under device mobility and unpredictable network conditions, leading to degraded service performance. To address these coordination challenges and sustain high-quality service under mobility and dynamics, we aim to design an adaptive service provision framework that tightly couples real-time perception with intelligent decision-making at the edge. Specifically, we propose an adaptive service provision architecture for ISAC-assisted EI, where Digital Twins (DTs) hosted on edge servers represent edge devices and their contexts to enable accurate perception and intelligent decision-making, thereby enhancing the efficiency of ISAC-enabled services. By dynamically migrating DTs across edge servers based on device mobility and resource availability, the system supports continuous decision-making and seamless service delivery. We further integrate convex optimization for efficient multi-resource coordination and a Time-Varying Contextual Bandit (TVCB) algorithm to enable adaptive, context-aware DT migration in dynamic environments. Extensive simulations demonstrate that our approach significantly improves service quality, reliability, and adaptability in ISAC-assisted EI systems, reducing migration oscillations and overhead while achieving lower latency and higher utility compared with representative baselines.

Edge intelligence deploys artificial intelligence models on edge nodes proximal to data sources, and delivers real-time inference support for resource-constrained devices. To realize this vision, inference offloading differs from conventional computation offloading by tailoring offloading strategies to the intrinsic characteristics of AI inference tasks. In this field, existing researchs generally lack fine-grained model partitioning capabilities and long-term resource adaptability, failing to optimize resource utilization and sustain stable performance in mobile environments. To address these issues, we propose an adaptive inference acceleration framework that dynamically partitions inference models into hierarchical subtasks and offloads these subtasks to heterogeneous edge servers. We formulate a joint optimization problem for task partitioning, offloading and resource allocation, which takes queue stability as the constraint and aims to minimize the long-term average task completion time. To realize the optimal trade-off between latency and stability without future state prediction, we adopt Lyapunov optimization to decompose the long-term stochastic optimization into slot-by-slot solvable deterministic subproblems. For these slot-by-slot subproblems, we design a Q-network Mixing (QMIX)-based multi-agent reinforcement learning method to enable collaborative strategy selection across edge servers. Experimental simulations show that, compared with baseline algorithms including the greedy, genetic and MAD2RL methods, our proposed framework achieves a substantial reduction in task completion time while preserving inference accuracy and queue stability.

Edge intelligence enhances the computational capabilities of resource-limited devices by offloading inference tasks to edge servers. Traditional methods either execute the entire model on the device, resulting in slow inference, or fully offload it to the server, incurring communication delays and privacy risks due to raw data transmission. Model partitioning addresses these challenges by splitting the model for execution on both the device and edge server, transmitting only intermediate inference results. However, current model partitioning methods lack consideration of device mobility, resulting in reduced inference efficiency and task interruptions. To address these limitations, we introduce MobiSplit, a novel mobility-aware framework that dynamically partitions inference models between resource-constrained devices and edge servers. MobiSplit adapts to real-time device mobility, fluctuating network conditions, and computational constraints to minimize inference latency and energy consumption while ensuring robust task execution. Additionally, we propose a distributed auction-based algorithm that empowers edge devices to autonomously determine optimal partitioning and offloading strategies in a scalable and adaptive manner. Extensive simulations demonstrate that MobiSplit enhances inference efficiency, achieving a 60% latency reduction and a 20% energy consumption decrease compared to the best-performing baseline across diverse edge scenarios.

Unmanned Aerial Vehicles (UAVs) with high mobility and flexibility have emerged as key enablers of computer vision (CV) applications. In the field of image recognition, federated learning can be integrated into UAV swarms, enabling distributed computing and efficient data sharing to train and deploy high-performance real-time image recognition models, while preserving the privacy of the UAV local data. However, despite its potential, federated learning in UAV swarms for real-time image recognition faces significant challenges of low convergence speed and insufficient model recognition accuracy posed by volatile environments. On the one hand, unstable UAV communication channels increase model upload latency. On the other hand, dynamic UAV states lead to fluctuations in local update quality. To address these challenges, we propose an accelerated asynchronous federated learning framework for UAV swarms to support real-time image recognition. Our framework introduces a Shapley-based asynchronous update mechanism, which enhances model accuracy by quantifying UAV update contributions and mitigating the effects of model staleness. Furthermore, we propose a fine-grained client selection strategy that accelerates convergence by selecting UAVs with low latency and high contributions to model recognition accuracy. A time-varying multi-armed bandit (MAB) model is employed to capture dynamic UAV states, optimizing client selection and further improving convergence. Numerical results in the simulated volatile environment show that our scheme outperforms benchmark methods in accuracy and convergence speed of the image recognition model.

This article develops a safety-driven distributed cooperative framework (SDDCF) for multiple unmanned aerial vehicles (UAVs) subject to actuator faults in the application of emergency search-and-rescue mission. A capability-triggered decision mechanism is proposed to conquer the challenging situation that the system redundancy cannot satisfy the requirement of fault-tolerant control. By quantitatively analyzing the capability of UAV, a safety threshold is provided, which can be updated adaptively in the light of performance requirement and real-time system capability estimated by a fixed-time fault observer. When the safety threshold is violated, the active performance degradation of the faulty UAVs and communication topology reconfiguration of the multiple UAVs are performed. By virtue of the SDDCF with capability-triggered mechanism, the safety of multiple UAVs system suffering from severe actuator faults is ensured for mission completion. The efficacy of the presented framework is demonstrated by a proof-of-concept emergency search-and-rescue mission in real-world flight experiments. Note to Practitioners—The proposed SDDCF is devoted to reduce the safety risk of multiple UAVs with severe actuator faults in emergency missions, where the mobility and reliability must be balanced carefully. Compared with the existing fault-tolerant control schemes, the SDDCF can ensure the safety even if the actuator faults exceed the system redundancy in a specific mission. Moreover, the practicability of the SDDCF, which can be extended to diverse task scenarios, has been verified in real-world flight experiments. In the future, the abilities of cooperative perception and risk avoidance should be improved to further enhance the safety of multiple UAVs in uncertain environments.

The avoidance of dynamic obstacles is a challenging issue for uncrewed aerial vehicle (UAV) due to its limited perception range.This article presents a framework including cooperative warning and risk-averse safety control for multiple UAVs. When external obstacles are discovered, the evaluation of conditional value-at-risk for the obstacles is performed by the discoverers. Whenever the risk value violates the designed safety threshold, the warning information will be transmitted to the threatened neighbors immediately. Moreover, by incorporating the event-triggered mechanism, the risk-averse safety control scheme is constructed. Consequently, multiple UAVs are able to evade dynamic obstacles from various directions with enhanced safety and reduced conservatism. The effectiveness and superiority of the proposed scheme are substantiated by comparative simulations and real-world flight experiments.

In recent years, there has been a growing focus on multiview data, driven by its rich complementary and consistent information, which has the potential to significantly enhance the performance of downstream tasks. Although many multiview clustering (MVC) methods have achieved promising results by integrating the information of multiple views to learn the consistent representation or consistent graph, these methods typically require complete and entirely accurate correspondences between multiview data, which is challenging to fulfill in practice leading to the problem of partially view-aligned clustering (PVC). To tackle it, we propose a novel method, called dynamic graph guided progressive partial view-aligned clustering (DGPPVC) in this article. To the best of our knowledge, this could be the first work to employ graph convolutional network (GCN) to address the problem of PVC, which explores GCN with dynamic adjacency matrix to reduce unreliable alignments and locate the feature representation with consistent graph structure. In particular, DGPPVC develops an end-to-end framework that encompasses graph construction, feature representation learning, and alignment relationships learning, in which the three parts mutually influence and benefit each other. Moreover, DGPPVC adopts a novel alignment learning strategy that progresses from simplicity to complexity, enabling the step-by-step acquisition of unknown correspondences between different modalities. By giving priority to simple instance pairs, a variant of Jaccard similarities is designed to identify more reliable and complex alignments progressively. During the gradual learning process of alignment relationships, the graph structure matrix is continually and dynamically optimized, thus acquiring a greater variety of graph information between different views. Experiments on several real-world datasets show our promising performance compared with the state-of-the-art methods in partially view-aligned clustering.

Vehicular edge computing (VEC) is critical for the safe and efficient driving of intelligent vehicles, by which they can offload computation-intensive tasks (such as driving environment perception) to edge servers to overcome the limitations of onboard computational resources and cooperate with others. One of the major challenges faced by VEC is that the offloaded intelligent driving tasks generally generate large amounts of data, which can easily stretch and congest the vehicle communication channels. To address the above challenges, we first propose a novel semantic VEC (SVEC) architecture, which can extract the semantic information of tasks and offload them to edge servers, thereby achieving reliable and efficient offloaded task communication and computation adaptively. Considering the scarce channel resources of vehicles and the intelligent tasks with different priorities and modalities, we define a novel user utility model for SVEC and transform the problem of maximizing user utility into a joint optimization problem of semantic feature extraction, task offloading and resource allocation. Furthermore, to cope with the complexity of the solution space of the optimization problem, we propose a diffusion-based multi-agent reinforcement learning algorithm, which improves the ability of agents to explore the solution space through the diffusion process, thereby achieving optimal decisions for semantic feature extraction, task offloading and resource allocation. Simulation results show that the proposed scheme improves the overall performance of SVEC while reducing offload latency and average system cost.

Alzheimer’s disease (AD) is a neurological illness that causes cognitive impairment. Computer-aided diagnosis can help diagnose Alzheimer’s disease early before clinical symptoms appear. Currently, many deep learning methods show good performance in AD diagnosis. Still, most of these methods are based on single/multimodal neuroimaging, leading to a one-sided approach to disease modelling. Combining neuroimaging, cognitive tests, and demographics can significantly improve model performance and reduce the negative impact of noise. This study proposes a multimodal model that introduces contrastive learning, extracting and fusing feature representations separately from cognitive tests and neuroimaging data. After that, contrastive learning based on similarity is employed for both modalities’ features, assisting the network in learning cross-modal features. Moreover, the hybrid attention mechanism of the Transformer encoder is explored for feature fusion. Experimental results on 2082 cases from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset validate the effectiveness of our proposed multimodal model.

Soft tissues sarcomas include striated muscle, fibrous tissue, fat, and other soft tissues. Simultaneously, their mortality rates are comparable to those of esophageal cancer, cervical cancer, and other cancers. Prior to surgical resection of patients, it is frequently necessary to study and diagnose the sarcoma area using MRI images in order to design a better surgical plan. However, artificial approaches for diagnosing the sarcoma region are time-consuming and error-prone. While the advent of artificial intelligence allows for computer-assisted diagnosis of the sarcoma region. Nevertheless, there is currently a scarcity of high-quality soft tissue sarcoma imaging data sets in relevant sectors. Thus, with the aim to investigate how to use multi-modal MRI images of patients with soft tissue sarcomas to segment the sarcoma area, we collect and process 15372 multi-modal MRI images in coronal of 40 patients with soft tissue sarcomas found in the thigh, which we subsequently combine with the help of several clinicians to mark the sarcoma area. The multi-modal MRI imaging data set of soft tissue sarcoma is therefore acquired by a number of preprocessing techniques. The sarcoma area is then segmented using a multi-encoder and single-decoder network that adapts to multiple input modalities. For motivating the network to learn the important semantic features of different modalities, we design a feature fusion strategy mechanism that is applied to the skip connection. Additionally, self-supervised learning is being investigated to address the issue of a small number of data points in the data set. Experiments show that our network can achieve the highest Dice score of 57.76% on our data set. Our code and the dataset are available at https://github.com/syaxx0819/The-Multimodal-Soft-Tissue-Sarcoma-Image-Dataset.

Multi-view data can represent objects from different perspectives and thus provide complementary information for data analysis. A topic of great importance in multi-view learning is to locate a low-dimensional latent subspace, where common semantic features are shared by multiple data sets. However, most existing methods ignore uncorrelated items (i.e., view-specific features) and may cause semantic bias during the process of common feature learning. In this article, we propose a non-negative correlated and uncorrelated feature co-learning (CoUFC) method to address this concern. More specifically, view-specific (uncorrelated) features are identified for each view when learning the common (correlated) feature across views in the latent semantic subspace. By eliminating the effects of uncorrelated information, useful inter-view feature correlations can be captured. We design a new objective function in CoUFC and derive an optimization approach to solve the objective with the analysis on its convergence. Experiments on real-world sensor, image, and text data sets demonstrate that the proposed method outperforms the state-of-the-art multiview learning methods.

With the prevailing development of Cyber-physical-social systems and Internet of Things, large-scale data have been collected consistently. Mining large data effectively and efficiently becomes increasingly important to promote the development and improve the service quality of these applications. Clustering, a popular data mining technique, aims to identify underlying patterns hidden in the data. Most clustering methods assume the static data, thus they are unfavorable for analyzing large, unbalanced dynamic data. In this paper, to address this concern, we focus on incremental clustering by extending the novel [clustering by fast search (CFS) and find of density peaks] method to incrementally handle large-scale dynamic data. Specifically, we first discuss two challenges, i.e., assignment of new arriving objects and dynamic adjustment of clusters, in incremental CFS (ICFS) clustering. We then propose two ICFS clustering algorithms, ICFS with multiple representatives (ICFSMR) and the enhanced ICFSMR (E_ICFSMR) to tackle the two challenges. In ICFSMR, we explore the convex hull theory to modify the representatives identified for each cluster. E_ICFSMR improves the generality and effectiveness of ICFSMR by exploring one-time cluster adjustment strategy after integration of each data chunk. We evaluate the proposed methods with extensive experiments on four benchmark data sets, as well as the air quality and traffic monitoring time series, with comparisons to CFS and other three state-of-the-art incremental clustering methods. Experimental results demonstrate that the proposed methods outperform the compared methods in terms of both effectiveness and efficiency.

The discrete-time one-unit repairable system was studied, whose lifetime, repair delay time, corrective maintenance time and preventive maintenance time are all assumed to be random variables with general discrete distributions. We investigated the relationship of system states including operational state, waiting state for repair, state for preventive maintenance, and state for corrective maintenance. Then the state transition model was built. Furthermore, we established the instantaneous availability model which has the 2-D discrete characteristics, and on the basis, we proposed the optimal maintenance interval model. Finally, numerical examples were given to illustrate the proposed models.