IEEE Transactions on Systems Man Cybernetics-Systems最新文献_第4页

IEEE Transactions on Systems, Man, and Cybernetics: Systems Information for Authors IEEE系统、人与控制论汇刊：作者的系统信息

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-04-16 DOI: 10.1109/TSMC.2026.3679008

引用次数: 0

Understanding Over-Squashing in Dynamic Graphs 理解动态图中的过度压缩

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-02-10 DOI: 10.1109/TSMC.2026.3658409

Chaokai Wu;Xiaofeng Zhang;Jianghong Ma

{"title":"Understanding Over-Squashing in Dynamic Graphs","authors":"Chaokai Wu;Xiaofeng Zhang;Jianghong Ma","doi":"10.1109/TSMC.2026.3658409","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3658409","url":null,"abstract":"Graph neural networks (GNNs) have demonstrated significant success in solving real-world problems using both static and dynamic graph data. While static graphs remain constant, dynamic graphs evolve over time, presenting unique challenges that necessitate integrating GNN computations with sequential models. Despite advancements, existing research has primarily focused on static graphs, with dynamic graphs receiving comparatively less attention. This study extends the investigation of over-squashing—a phenomenon where excessive information compression leads to the loss of distant node information—from static to dynamic graphs. Over-squashing is exacerbated in dynamic graphs due to the combined compression of spatial and temporal information into narrow time windows. To address this issue, we propose the spatial and temporal compensation model for dynamic graphs, which is theoretically validated and incorporates two key modules: the structural similarity-based spatial compensation (SSSC) module and the representation and trend similarity-based temporal compensation (RTSTC) module. The former module mitigates spatial information loss by leveraging structural similarities among nodes, while the latter module addresses temporal information loss by integrating historical data and trends. The extensive experiments on real-world dynamic graph datasets demonstrate that our approach achieves state-of-the-art performance. The datasets and source codes are released at: <uri>https://github.com/wuchaokai/STCDG/</uri>","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3396-3407"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685329","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}

引用次数: 0

Decoding Driving Intentions via a Novel Brain–Computer Interface Paradigm With Low Cognitive Load and High Robustness 基于低认知负荷、高鲁棒性的新型脑机接口范式的驾驶意图解码

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-02-06 DOI: 10.1109/TSMC.2026.3657849

Jianxiang Sun;Zongtan Zhou;Yadong Liu;Daxue Liu;Haoqiang Chen;Yingxin Liu;Dewen Hu

{"title":"Decoding Driving Intentions via a Novel Brain–Computer Interface Paradigm With Low Cognitive Load and High Robustness","authors":"Jianxiang Sun;Zongtan Zhou;Yadong Liu;Daxue Liu;Haoqiang Chen;Yingxin Liu;Dewen Hu","doi":"10.1109/TSMC.2026.3657849","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3657849","url":null,"abstract":"In recent years, brain–computer interface (BCI) based on electroencephalography (EEG) has been increasingly applied in human–vehicle collaborative driving. In this article, we design a novel BCI paradigm, incorporating subliminal steady state visual evoked potential (SSVEP) within the friendly interaction framework of short driving videos, which ensures low cognitive load interaction for drivers while also enhancing the robustness of EEG decoding. To robustly decode these signals, we propose a novel multidomain spatial–frequency–temporal multiscale gating convolutional neural network (SFT-GCNN), which explicitly addresses EEG nonstationarity and subject variability through three key innovations: 1) a channel-wise attention mechanism to extract task-relevant spatial topologies; 2) a multiscale gating convolutional unit (GCU) that adaptively filters noise and captures temporal dynamics across diverse receptive fields; and 3) a multiview fusion strategy integrating spatial, temporal, and spectral features under the joint supervision of cross-entropy (CE) and center loss to enforce intraclass compactness. The proposed decoding method outperforms several benchmark methods, achieving accuracies of 82.91% <inline-formula> <tex-math>$pm ~4.35$ </tex-math></inline-formula>% and 78.23% <inline-formula> <tex-math>$pm ~1.87$ </tex-math></inline-formula>% in the subject-dependent and subject-independent experiments. Furthermore, the subjective fatigue scales and a mean theta-to-alpha ratio (TAR) of 1.13 confirm that the proposed stimulus paradigm does not induce additional visual fatigue to participants. These results demonstrate that our approach effectively balances high decoding robustness with user comfort in practical driving scenarios.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3235-3249"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685503","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}

引用次数: 0

TechRxiv: Share Your Preprint Research With the World! techxiv：与世界分享你的预印本研究！

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-04-16 DOI: 10.1109/TSMC.2026.3678693

引用次数: 0

Anti-Unwinding Active Fault-Tolerant Attitude Tracking Control for Uncertain Spacecraft via Fully Actuated System Approach 基于全驱动系统的不确定航天器抗解绕主动容错姿态跟踪控制

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-02-12 DOI: 10.1109/TSMC.2026.3659255

Shixiang Jia;Li Yuan;Jianbin Qiu;Tong Wang;Min Li

{"title":"Anti-Unwinding Active Fault-Tolerant Attitude Tracking Control for Uncertain Spacecraft via Fully Actuated System Approach","authors":"Shixiang Jia;Li Yuan;Jianbin Qiu;Tong Wang;Min Li","doi":"10.1109/TSMC.2026.3659255","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3659255","url":null,"abstract":"This article proposes an active fault-tolerant control (AFTC) scheme for attitude tracking of uncertain spacecraft with actuator faults and unavailable angular velocity. First, a second-order fully actuated system (FAS) model is derived from the dynamics of the spacecraft. The unwinding phenomenon is solved by controlling the scalar quaternion. Then, the state observer and the FAS-based controller are designed, and the assumption that all the system states and their derivatives are requested to be known is relaxed, which is a typical assumption in the existing FAS approach. The proposed method facilitates the detection and analysis of the fault information for a spacecraft, based on which an AFTC scheme is designed to address uncertain spacecraft attitude tracking under uncertain time-varying inertia parameters, faults, and disturbances. Moreover, angular velocity measurements are not needed. The uniformly bounded stability of the proposed control scheme is theoretically proved. Finally, the numerical simulation results are provided to illustrate the performance of the proposed control scheme.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3445-3455"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685364","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}

引用次数: 0

Graph Tensor Convolutional Network 图张量卷积网络

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-02-06 DOI: 10.1109/TSMC.2026.3655418

Ling Wang;Ye Yuan;Xin Luo

{"title":"Graph Tensor Convolutional Network","authors":"Ling Wang;Ye Yuan;Xin Luo","doi":"10.1109/TSMC.2026.3655418","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3655418","url":null,"abstract":"A dynamic graph (DG) is commonly encountered in many big data-related application scenarios, like cryptocurrency transaction analysis. A dynamic graph convolutional network (GCN) can represent a DG efficiently for addressing various downstream tasks, such as the missing link weight estimation. However, an existing dynamic GCN model mostly consists of a static GCN and a sequence module for exploring the spatiotemporal dependencies, which impairs the inner spatiotemporal connections between obtained features, thus resulting in the loss of representation learning capability. Motivated by this critical issue, this article proposes a graph tensor convolutional network (GTCN) with twofold ideas: 1) leveraging the tensor <inline-formula> <tex-math>$M$ </tex-math></inline-formula>-product to formulate the unified graph tensor convolution (GTC), which can model the spatiotemporal message transmission naturally without any artificial separation or information loss; and 2) introducing a learnable mixing matrix into the GTC for aggregating the historical topology information and node features adaptively. The theoretical proof regarding the proposed GTCN’s representation learning ability indicates its superiority over state-of-the-art models. Experimental results on seven real DGs demonstrate that the proposed GTCN acquires significant accuracy gain over several state-of-the-art models in addressing the task of missing link weight estimation. The code is available at <uri>https://github.com/wangling1820/GTCN</uri>","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3008-3024"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685359","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}

引用次数: 0

A Robustness Indicator-Based Dual-Population Evolutionary Algorithm for Multimodal Multiobjective Optimization 基于鲁棒性指标的多模态多目标优化双种群进化算法

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-03-03 DOI: 10.1109/TSMC.2026.3662059

Caitong Yue;Wenhao Ye;Jing Liang;Mengmeng Li;Kunjie Yu;Ying Bi;Boyang Qu

{"title":"A Robustness Indicator-Based Dual-Population Evolutionary Algorithm for Multimodal Multiobjective Optimization","authors":"Caitong Yue;Wenhao Ye;Jing Liang;Mengmeng Li;Kunjie Yu;Ying Bi;Boyang Qu","doi":"10.1109/TSMC.2026.3662059","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3662059","url":null,"abstract":"In practical scenarios, there may be solutions in the decision space with close objective values but located far apart, a characteristic known as multimodal multiobjective problems (MMOPs). While most multimodal multiobjective evolutionary algorithms (MMEAs) focus on finding global Pareto optimal solution sets (PSs) and local PSs demonstrating satisfactory convergence performance, decision-makers in real-world scenarios are often also interested in local PSs that exhibit strong robustness. In this study, we propose several benchmark functions in which the global and local PSs have varying levels of robustness. Then, we introduce an innovative dual-population evolutionary algorithm, termed GLR-MMEA, designed to simultaneously find both global PSs and local PSs with strong robustness. In GLR-MMEA, the convergence population focuses on identifying global PSs, providing convergence information to the diversity population. Meanwhile, the diversity population manages the detection of both global PSs and local PSs with strong robustness. In the process of updating the diversity population, a robustness indicator is proposed to access the robustness of solutions. Furthermore, a selection mechanism founded on this robustness indicator is applied to identify local PSs with high robustness. The experimental results show that GLR-MMEA performs competitively against other leading MMEAs in working on the selected benchmark functions.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3220-3234"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685507","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}

引用次数: 0

TechRxiv: Share Your Preprint Research With the World! techxiv：与世界分享你的预印本研究！

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-04-16 DOI: 10.1109/TSMC.2026.3678992

引用次数: 0

Near-Optimal Distributed Control of Automated Manufacturing Systems With Assembly Operations Using Petri Nets 使用Petri网的装配操作自动化制造系统的近最优分布式控制

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-02-11 DOI: 10.1109/TSMC.2026.3659271

Chen Chen;Chan Gu;Hesuan Hu

{"title":"Near-Optimal Distributed Control of Automated Manufacturing Systems With Assembly Operations Using Petri Nets","authors":"Chen Chen;Chan Gu;Hesuan Hu","doi":"10.1109/TSMC.2026.3659271","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3659271","url":null,"abstract":"Assembly operations are common in automated manufacturing systems (AMSs). AMSs with assembly operations belong to complex systems due to their complicated structures. The traditional supervisory control techniques (SCTs) are generally not suitable for such large-scale systems. In this article, we propose a distributed control technique for AMSs with assembly operations to achieve a near-optimal liveness enforcement. Specifically, we define a type of decomposable system modeled by decomposable augmented marked graphs (AMGs) and create buffer-linked AMGs (BAMGs) by connecting each subsystem through buffers with specified capacities. Next, we construct the complemented subsystems to ensure structural completeness and simplify their structures to condense their reachability graphs. By conducting liveness analysis of BAMGs employing siphons, we demonstrate that the liveness of BAMGs depends solely on that of each individual subsystem. Finally, we design monitors for simplified subsystems utilizing reachability analysis and achieve distributed control of AMGs. Since the scale of reachable states is greatly reduced in simplified subsystems compared with the original AMGs, our method can save a significant amount of computation. An experimental study demonstrates the effectiveness of the proposed method.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"3340-3354"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685316","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}

引用次数: 0

Robustness Analysis in Networked Automated Manufacturing Systems With Control Delays and Losses Using Predictive Supervisors 具有控制延迟和损失的网络化自动化制造系统的鲁棒性分析

IF 8.7 1区计算机科学

IEEE Transactions on Systems Man Cybernetics-Systems Pub Date : 2026-03-01 Epub Date: 2026-02-06 DOI: 10.1109/TSMC.2026.3655358

Zijian Zhang;Hesuan Hu

{"title":"Robustness Analysis in Networked Automated Manufacturing Systems With Control Delays and Losses Using Predictive Supervisors","authors":"Zijian Zhang;Hesuan Hu","doi":"10.1109/TSMC.2026.3655358","DOIUrl":"https://doi.org/10.1109/TSMC.2026.3655358","url":null,"abstract":"This study proposes a predictive supervisor <inline-formula> <tex-math>$mathcal {S}_{p}$ </tex-math></inline-formula> for the robustness analysis and control of networked automated manufacturing systems (NAMSs) with control delays and losses. Unlike existing predictive supervisor studies for networked discrete event systems (NDESs), which are restricted to the automaton framework and disregard AMSs as controlled plants, our approach extends predictive control to Petri net (PN)-modeled NAMSs, thereby enabling explicit treatment of robustness analysis. By examining whether subnet systems can operate without interruption during resource failures, we formally define the notions of liveness and networked liveness, and classify markings into networked non-robust, networked weakly robust, and networked strongly robust types. Two predictive robustness control strategies, strongly constrained and weakly constrained, are proposed, and necessary and sufficient conditions for the solvability of the robustness control problem are established. To support control implementation, we introduce the predictive reduced reachability graph (PR<inline-formula> <tex-math>${}^{2}$ </tex-math></inline-formula>G), which assists <inline-formula> <tex-math>$mathcal {S}_{p}$ </tex-math></inline-formula> in determining the set of transitions to be forbidden to guarantee robustness. Based on the PR<inline-formula> <tex-math>${}^{2}$ </tex-math></inline-formula>G, we develop a robustness control theorem to achieve robustness under control delays and losses. The proposed framework further generalizes beyond systems of sequential systems with shared resources (S<sup>4</sup>Rs) to broader PN models with minimal modifications.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"56 5","pages":"2982-2995"},"PeriodicalIF":8.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685363","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}

引用次数: 0