IEEE Transactions on Systems Man Cybernetics-Systems最新文献

{"title":"Two-Stage Observer-Based Fault Detection and Isolation for Re-Entrant Manufacturing Systems","authors":"Hao Sun;Qing Gao;Steven X. Ding;Jianbin Qiu;Jinhu Lü","doi":"10.1109/TSMC.2025.3650005","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3650005","url":null,"abstract":"This article investigates the fault detection and isolation (FDI) problem for a class of re-entrant manufacturing systems (RMSs) subject to workstation faults, sensor faults, and measurement disturbances. The system dynamics are first characterized by a hybrid hyperbolic partial differential equation (HHPDE) continuum model. A two-stage observer-based FDI framework is then developed to enable timely and reliable fault diagnosis. In the first stage of this framework, a diagnostic observer equipped with residual evaluation logic is employed, which is capable of detecting the occurrence of faults yet incapable of differentiating between the sensor faults and the workstation faults. Once a fault is detected, the isolation procedure starts as the second stage to distinguish the fault types and localize the fault sources. To be specific, an <inline-formula> <tex-math>$H_{-}/H_{infty }$ </tex-math></inline-formula> observer-based isolation scheme is proposed to effectively decouple the sensor faults from the sensor disturbances, by exploiting the dual performance of disturbance attenuation and fault sensitivity; an adaptive observer-based isolation strategy is devised to identify the workstation faults by capturing the associated structural changes in the system dynamics. Finally, the effectiveness and robustness of the proposed methods are validated through comprehensive numerical simulations.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 4","pages":"2485-2500"},"PeriodicalIF":8.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RBKWOT: Rough-Allowance Borderline K-Mode Clustering, Weighted Oversampling Technique for Class Imbalance Handling","authors":"Anima Pramanik;Sankar K. Pal","doi":"10.1109/TSMC.2025.3627388","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3627388","url":null,"abstract":"The performance of machine learning (ML) algorithms is impacted due to the class imbalance issue. Although there are several techniques developed to take care of this issue, research on handling categorical or mixed imbalanced data has not been explored much. Moreover, the existing class imbalance handling techniques may not preserve the original characteristics of the data. To address these issues, a new technique, namely, the rough-allowance borderline <inline-formula> <tex-math>$K$ </tex-math></inline-formula>-mode clustering-based weighted oversampling technique (RBKWOT), is developed. It consists of four steps: 1) extraction of rough-allowance borderline minority samples; 2) generation of optimum <inline-formula> <tex-math>$K$ </tex-math></inline-formula>-mode clusters; 3) assignment of sampling weights to these clusters; and 4) generation of rules for resampling instances corresponding to each cluster based on its sampling weight. The RBKWOT is capable of reducing the imbalance ratio without incurring any loss of information. It also handles the uncertainty in decision-making for the samples belonging to the boundary region. The efficacy of RBKWOT over some state-of-the-art techniques is demonstrated using 21 categorical, continuous, and mixed data that are acquired from the UCI Machine Learning Repository. Experimental results reveal the superiority of RBKWOT.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 4","pages":"2597-2607"},"PeriodicalIF":8.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Three-Stage Grouping Optimization for Large-Scale Collaborative E-Learning via Knowledge Graph and E-CARGO","authors":"Hua Ma;Xiangru Fu;Wensheng Tang;Ming Chen;Haibin Zhu;Keqin Li","doi":"10.1109/TSMC.2026.3651349","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3651349","url":null,"abstract":"With the popularity of <inline-formula> <tex-math>$e$ </tex-math></inline-formula>-learning, the number of learners enrolling in an online class has increased dramatically. Facing the huge learner size and diverse learner characteristics, existing research does not deeply explore the relationships among learners’ characteristics, making it difficult to accurately form appropriate learning teams to enhance learners’ learning efficiency and quality. We propose a three-stage grouping optimization approach for large-scale collaborative <inline-formula> <tex-math>$E$ </tex-math></inline-formula>-learning via knowledge graph and the environments—classes, agents, roles, groups, and objects (<inline-formula> <tex-math>$E$ </tex-math></inline-formula>-CARGOs). First, this approach constructs a knowledge graph of large-scale <inline-formula> <tex-math>$E$ </tex-math></inline-formula>-learning environments to facilitate accurate learner clustering for reducing computational cost. Second, a multidimensional learner model is proposed to comprehensively evaluate learners’ competencies for team leader selections. Third, the remaining learners are assigned to different learning teams based on their complementarities with team leaders, and this problem is modeled as a role-based collaboration (RBC) problem by the E-CARGO model. Meanwhile, an effective and efficient solution via an optimization package is presented. Finally, experiments demonstrate that the proposed approach accurately achieves global grouping optimization with good execution performance in large-scale collaborative <inline-formula> <tex-math>$e$ </tex-math></inline-formula>-learning scenarios.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 4","pages":"2684-2698"},"PeriodicalIF":8.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust Distributed Predictive Control of Cooperated Path Following for Wheeled Mobile Robots","authors":"Dongdong Qin;Andong Liu;Wen-An Zhang;Li Yu;Yang Tang","doi":"10.1109/TSMC.2026.3654641","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3654641","url":null,"abstract":"This article addresses the problem of cooperative path following for wheeled mobile robots (WMRs) under system constraints and external bounded disturbances within a switching communication network, by proposing a robust distributed model predictive control (DMPC) strategy. First, the cooperative path-following task is decoupled into two subtasks using a modified virtual structure: a cooperative task involving virtual reference robots and an individual path-following task between each actual robot and its corresponding virtual reference. A time-like path parameter is introduced to generate predefined path information for the virtual reference robot in advance, enabling dynamic formation tracking. Subsequently, discrete-time error dynamics subject to external bounded disturbances are derived for each robot, and a centralized predictive control problem is formulated as a baseline. A nominal DMPC strategy is then developed for the disturbance-free case, followed by an extension to a robust DMPC formulation that accounts for nonzero disturbances. In this context, a stability constraint is incorporated to ensure closed-loop stability without relying on neighboring agents’ real-time information. Theoretical analysis confirms the feasibility of the proposed scheme and guarantees the convergence of system trajectories to a disturbance invariant set. Finally, simulation and experimental results validate the effectiveness of the proposed strategy in cooperative path-following scenarios involving WMRs.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 4","pages":"2815-2826"},"PeriodicalIF":8.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148506285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lightweight Log-Linear Learning With Neighborhood Search for Equilibrium Selection in Finite Potential Games","authors":"Zhe Li;Changdi Liu;Shaolin Tan;Wei Wang","doi":"10.1109/TSMC.2026.3651822","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3651822","url":null,"abstract":"In this article, we consider the problem of equilibrium selection in multiplayer finite potential games with large-size action sets. Traditional learning approaches often require players to traverse the entire action set to evaluate the utility of each action, which can be computationally intensive and inefficient. To overcome this limitation, we leverage the idea of neighborhood search into the game-theoretical learning process for the first time by generating neighborhood candidate action sets for exploration and evaluation. As such, we propose a lightweight log-linear dynamics for efficient equilibrium selection in finite potential games. Asymptotic convergence is proved under both asynchronous and independent revision rules with the help of resistance tree theory. Furthermore, through the multisatellite cooperative task allocation (MSCTA) problem, we elaborate on how to encode the players’ actions and how to generate the neighborhood structure. Simulation results demonstrate that the proposed method significantly outperforms the existing game-theoretic learning methods, notably in terms of solution time.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 4","pages":"2720-2734"},"PeriodicalIF":8.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148507312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multiscale Pooling Spatial–Temporal Attention Network: Elevating Cross Session and Small Sample Decoding in Motor Imagery Brain–Computer Interfaces","authors":"Weijie Chen;Ian Daly;Yixin Chen;Xiao Wu;Xinjie He;Xingyu Wang;Andrzej Cichocki;Jing Jin","doi":"10.1109/TSMC.2025.3650196","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3650196","url":null,"abstract":"Motor imagery (MI) is one of the most widely used paradigms in brain–computer interfaces (BCIs), known for its ability to trigger changes in brain activity without the need for an external “cue” stimulus. This unique characteristic has attracted significant attention from neuroscientists and researchers in fundamental science. However, compared to <inline-formula> <tex-math>$P300$ </tex-math></inline-formula> and steady-state visual evoked potential (SSVEP), neural activity related to MI tends to be less stable and exhibits substantial variability between individuals. Consequently, accurately decoding MI, using both traditional machine learning and deep learning, has proven to be a considerable challenge. Moreover, given the difficulty of acquiring electroencephalography (EEG) data and the high data demands of deep learning, enhancing the accuracy of MI decoding with limited sample sizes remains a pressing issue that urgently needs to be addressed. This article addresses the challenges mentioned above by introducing a novel deep neural network designed for accurate MI decoding, which is designed to be effective with both small-sample sizes and larger datasets. This network, named the multiscale pooling spatial–temporal attention network (MPSTANet), integrates mix pooling techniques with spatial–temporal attention mechanisms. MPSTANet first employs local and global spatial attention, along with multiscale temporal attention, to thoroughly extract spatial–temporal information from EEG signals. Next, MPSTANet utilizes feature fusion and the proposed mix pooling technique to preserve as much of the extracted spatial–temporal information as possible. Finally, channel interaction attention (CIA) and 3-D weight attention (3-DWA) are employed to recalibrate the weights of the fused channels and spatial–temporal features, respectively. To validate the performance of our proposed MPSTANet model, we conducted experiments on four public datasets, including both small-sample sizes and subject-independent scenarios. MPSTANet achieved cross-session decoding accuracies of 84.82%, 72.92%, 88.20%, and 46.54% on the BCI Competition IV 2a dataset, the Open BMI dataset, the BCI Competition IV 2b dataset, and the PhysioNet dataset, respectively. Furthermore, MPSTANet demonstrated a significant lead compared to other deep learning models in both small-sample and subject-independent experiments. These results demonstrate the robustness of MPSTANet in MI decoding and its promising potential for BCI applications.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 4","pages":"2225-2239"},"PeriodicalIF":8.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Cognitively “AND”-Biased Adversarial TSK Fuzzy Classifier: Training and Generalization Analysis","authors":"Runshan Xie;Fu-Lai Chung;Shitong Wang","doi":"10.1109/TSMC.2025.3649534","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3649534","url":null,"abstract":"This study attempts to develop a novel cognitive-biased knowledge adversarial learning method for an interpretable Takagi–Sugeno–Kang (TSK) fuzzy classifier to enhance its generalization capability. Based on the cognitive bias that humans occasionally tend to understand “<sc>and</small>” in a rule as a union rather than an intersection for the rule’s interpretability, the concept of the cognitively “<sc>and</small>”-biased adversarial TSK fuzzy classifier based on the cognitively “<sc>and</small>”-biased adversarial attacks is proposed, and accordingly, the cognitively “<sc>and</small>”-biased adversarial training method called CAT for the proposed classifier is derived to earn enhanced generalization capability. This study has three distinct merits: 1) the cognitively “<sc>and</small>”-biased adversarial attacks on the fuzzy operators in fuzzy rules are invented as a novel means of adversarial attacks to mimic the human cognitive bias appearing in the rule’s interpretability; 2) after training the proposed TSK fuzzy classifier with CAT, the resultant fuzzy rules reflect the cognitively biased behaviors in the sense of the transformation level from “<sc>and</small>” to “<sc>or</small>” operations for the first time by the randomly generated uninorm rather than frequently used fuzzy “<sc>and</small>” operators; and 3) CAT has its theoretical guarantee of enhanced generalization and overfitting-avoidance capabilities. Extensive experimental results demonstrate that CAT has satisfactory classification performance and good interpretability.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 4","pages":"2439-2453"},"PeriodicalIF":8.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hyperedge-Based Adaptive Pinning Control in Hypernetworks Under Dynamic Link Attacks","authors":"Wenying Yuan;Wei Gu;Tianliang Zhang;Tianchi Tong;Qian Dong;Jinsheng Sun","doi":"10.1109/TSMC.2025.3649993","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3649993","url":null,"abstract":"Ensuring synchronization in networked systems presents a growing challenge, particularly for complex systems characterized by higher order interactions extending beyond pairwise connections. In this article, we investigate a class of hypernetwork systems in hypergraphs and introduce a novel dynamic link attacks that allow dynamic attack patterns on hyperedges. To address the vulnerability of the higher order systems under these conditions, we propose a hyperedge-based adaptive pinning control strategy to guarantee synchronization in hypernetworks with time-varying couplings. Based on the original hypergraph topology, an augmented hypergraph is constructed by establishing pinning hyperedges between tracking and pinning nodes. Concurrently, a time-varying adaptive coupling mechanism is further designed, which dynamically adjusts the strengths of both standard and pinning hyperedges based on local synchronization errors. Utilizing the Lyapunov function method, sufficient conditions guaranteeing exponential synchronization are derived. Finally, the effectiveness of the proposed strategy is demonstrated through numerical simulations on a nonlinear hypernetwork composed of chaotic Chua’s circuit.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 4","pages":"2474-2484"},"PeriodicalIF":8.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Graph-Based Heterogeneous Multiagent Reinforcement Learning for Distribution System Service Restoration","authors":"Bangji Fan;Xinghua Liu;Yuanzhe Wang;Gaoxi Xiao;Yu Kang;Danwei Wang","doi":"10.1109/TSMC.2025.3649418","DOIUrl":"https://doi.org/10.1109/TSMC.2025.3649418","url":null,"abstract":"Service restoration implemented by multiple distributed energy resources (DERs) is a resilience-enhancing paradigm for modern distribution systems. To address the challenges of complex system modeling and the problem of cooperative control over heterogeneous multiple agents, this article proposes a graph reinforcement learning (G-RL) method based on heterogeneous multiagent systems (MASs). The method leverages graph-structured data to enhance the representation of distribution system states and employs graph attention networks (GATs) to deeply explore the power flow features and spatial characteristics of nodes in the restoration process. Additionally, a multihead self-attention (MHSA) is incorporated to strengthen collaboration among heterogeneous agents, enabling them to focus on relevant information from multiple perspectives during training. Finally, a joint simulation test platform is developed using Python and OpenDSS, and case studies on a 123-bus distribution system are conducted. Experimental results demonstrate that the proposed approach achieves efficient and autonomous service restoration by enhancing spatial feature extraction and improving collaborative decision-making among agents.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 4","pages":"2399-2412"},"PeriodicalIF":8.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid Intelligent Optimization of Path-Constrained Switched Systems With Free Switching Sequences","authors":"Jun Fu;Zexiang Gao;Huan Li;Dali Chen;Xiaochen Zhu;Dongxiao Zhang","doi":"10.1109/TSMC.2026.3656695","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3656695","url":null,"abstract":"In this article, a hybrid intelligent optimization method is proposed for the dynamic optimization of path-constrained switched systems with free switching sequences. This method combines improved particle swarm optimization and differential evolution (IPSO-DE) method with a gradient-based dynamic optimization method, which can simultaneously obtain the global optimal solution, i.e., optimal control input, optimal switching instants, and optimal switching sequences. First, control vector parameterization (CVP), switching time parameterization (STP), and switching sequence smoothing techniques are employed to transform the original problem into a continuous finite-dimensional dynamic one. Second, the path constraints are discretized into a finite number of point constraints, and the IPSO-DE algorithm is proposed to search for the global optimal solution of the continuous dynamic problem with discretized constraints. Then, the obtained optimal solution serves as the initial point to calculate the gradients of the objective function with respect to control input, switching instants, and switching sequences. Third, the gradient-based deterministic method is applied to obtain the global optimal solution that satisfies the first-order optimality condition. Fourth, the finite termination of the hybrid intelligent optimization method is proven. Finally, the effectiveness of the proposed method is verified through three numerical examples.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 4","pages":"2763-2777"},"PeriodicalIF":8.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148506197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}