IEEE Transactions on Cybernetics最新文献

{"title":"Toward In-Depth Mastery of Statistical Properties: Novel Stationary Moment Analysis With Application to Continuous Industrial Anomaly Detection","authors":"Siwei Lou;Chunjie Yang;Weibin Wang;Hanwen Zhang;Yuchen Zhao;Ping Wu","doi":"10.1109/TCYB.2025.3556598","DOIUrl":"10.1109/TCYB.2025.3556598","url":null,"abstract":"Anomaly detection is a cornerstone of industrial safety, enabling real-time monitoring of process operations by identifying deviations from normal conditions through statistical analysis. In real-world industrial scenarios, the nonstationary properties of multivariate time-series data present a common and substantial challenge. Existing methods for extracting stationary sources <inline-formula> <tex-math>$(mathcal {SS}s)$ </tex-math></inline-formula> mainly rely on weak stationarity (i.e., mean and variance), but their performance is limited by the long-tailed distributions common in industrial datasets. Higher-order moments, in contrast, provide a more comprehensive statistical description, capturing complex data characteristics that the mean and variance overlook. To bridge this significant gap, we propose a continuous stationary moment analysis (Co-SMA) anomaly detection framework. Its core innovation is the SMA algorithm, which introduces a novel objective function to minimize cumulative sum of the differences in multiorder moments between each epoch and the overall data, effectively fulfilling the <inline-formula> <tex-math>$mathcal {SS}$ </tex-math></inline-formula> estimation task. Furthermore, to overcome the inefficiencies of traditional model updating methods, we develop an event-triggered model updating framework based on the model bias index and first-order perturbation theory. Within this framework, we introduce a convex hull coverage metric, which enables the model to be adjusted efficiently according to the data distribution drift. The framework also incorporates iterative refinement of detection statistics and thresholds, establishing a dynamic adjustment mechanism that ensures optimal performance across diverse operating conditions. The theoretical basis of Co-SMA’s properties is rigorously established. Experimental evaluations on numerical simulations and real-world datasets from the ironmaking process demonstrate Co-SMA’s superior capabilities in <inline-formula> <tex-math>$mathcal {SS}$ </tex-math></inline-formula> estimation and anomaly detection.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 7","pages":"3417-3430"},"PeriodicalIF":9.4,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143862070","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":"Distributed Secure State Estimation and Attack Detection for Dynamical Systems With Attacks on a Time-Varying Sensor Set","authors":"Guangran Lyu, Xiao He","doi":"10.1109/tcyb.2025.3557269","DOIUrl":"https://doi.org/10.1109/tcyb.2025.3557269","url":null,"abstract":"","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"32 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143862072","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":"Group Role Three-Way Assignment for Managing Uncertainty in Role Negotiation","authors":"Shiyu Wu;Shenglin Li;Haibin Zhu;Rui Chen;Libo Zhang","doi":"10.1109/TCYB.2025.3558402","DOIUrl":"10.1109/TCYB.2025.3558402","url":null,"abstract":"Role-based collaboration (RBC) is an innovative collaborative approach designed to enhance collaboration. Role negotiation (RN) is a critical step in RBC, during which the role set and the number of agents required for each role, i.e., role requirements, are determined. This process establishes the foundational input for group role assignment (GRA), where roles are assigned to agents to optimize group performance. Uncertainties in RN, such as task volume fluctuations, create dynamic agent requirements. However, existing RBC models typically assume RN to be static, thus failing to adequately address the substantial challenges. Three-way decision (3WD) is a robust decision-making methodology well-suited for managing uncertainty. To address the uncertainties in role requirements, this article introduces truncated discrete distribution to quantify role requirements, and presents a novel group role three-way assignment (GR3A) model. Compared with traditional RBC, our model offers an additional variable partial substitute choice that offers agents little salary during nonengagement periods but can transition to full involvement as required according to the prior agreement. GR3A is a dual-objective nonlinear optimization problem, for which a linearization strategy is proposed to achieve the optimal resolution. Additionally, sufficient and necessary conditions for these assignment problems are put forward to enhance the efficacy of the proposed solutions. To our knowledge, this study innovatively introduces a truncated discrete distribution and 3WD into the RBC framework. Empirical validation through simulations demonstrates the effectiveness and efficacy of the proposed method within the RBC context.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 6","pages":"2924-2936"},"PeriodicalIF":9.4,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143862078","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 Constructive Approach for Neural Network Approximation Sets in Adaptive Control of Strict-Feedback Systems","authors":"Yu-Fa Liu, Yong-Hua Liu, Jin-Wa Wu, Ante Su, Chun-Yi Su, Renquan Lu","doi":"10.1109/tcyb.2025.3559235","DOIUrl":"https://doi.org/10.1109/tcyb.2025.3559235","url":null,"abstract":"","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"18 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143857738","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":"Correlation Information Enhanced Graph Anomaly Detection via Hypergraph Transformation","authors":"Changqin Huang;Chengling Gao;Ming Li;Yongzhi Li;Xizhe Wang;Yunliang Jiang;Xiaodi Huang","doi":"10.1109/TCYB.2025.3558941","DOIUrl":"10.1109/TCYB.2025.3558941","url":null,"abstract":"Graph anomaly detection (GAD) has attracted increasing interest due to its critical role in diverse real-world applications. Graph neural networks (GNNs) offer a promising avenue for GAD, leveraging their exceptional capacity to model complex graph structures and relationships. However, existing GNN-based models encounter challenges in addressing the GAD’s fundamental issue—anomaly camouflage, where anomalies mimic normal instances, leading to indistinguishable features. In this article, we propose a novel approach, termed correlation information enhanced GAD (CIE-GAD). Specifically, drawing on the observation that the distribution of homophilic and heterophilic edges differs between abnormal and normal samples, we construct a hypergraph to learn the co-occurrence relationships among adjacent edges. By enhancing the extraction of sample correlation information, we effectively tackle feature similarity caused by anomaly camouflage, thereby enhancing the performance of GAD. Furthermore, we develop a spectral convolution mechanism based on node-level attention fusion, enabling the capture of multifrequency signals. This module performs adaptive fusion tailored to the unique frequency information requirements of each node, mitigating the local heterophily problem. Extensive experiments on various real-world GAD datasets demonstrate that the proposed CIE-GAD outperforms state-of-the-art methods. Notably, our approach achieves AUC-PR improvements of up to 3.47%, with an average gain of 1.5%, demonstrating its effectiveness in detecting anomalies in graph data.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 6","pages":"2865-2878"},"PeriodicalIF":9.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849808","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":"Knowledge Learning-Based Dimensionality Reduction for Solving Large-Scale Sparse Multiobjective Optimization Problems","authors":"Shuai Shao;Ye Tian;Yajie Zhang;Xingyi Zhang","doi":"10.1109/TCYB.2025.3558354","DOIUrl":"10.1109/TCYB.2025.3558354","url":null,"abstract":"Large-scale sparse multiobjective optimization problems (LSMOPs) are of great significance in the context of practical applications, such as critical node detection, feature selection, and pattern mining. Since many LSMOPs are pursued based on large datasets, they involve a large number of decision variables, resulting in a huge search space that is challenging to explore efficiently. To rapidly approximate sparse Pareto optimal solutions, some evolutionary algorithms have been proposed to reduce the dimensionality of LSMOPs. However, their adaptability to different LSMOPs remains limited due to their reliance on fixed dimensionality reduction schemes, which can potentially lead to local optima and inefficient utilization of function evaluations. To address this issue, a knowledge learning-based dimensionality reduction approach is proposed in this article. First, in the early stages of evolution, the impact of different dimensionality reduction schemes on the sparse distribution of the population is evaluated. Then, the multilayer perceptron is employed to learn the accumulated knowledge from the evolutionary process, thereby constructing a mapping model between the sparse features of the evolutionary process and the candidate dimensionality reduction schemes. Finally, the model recommends the best dimensionality reduction scheme in each generation, achieving a good balance between exploration and exploitation. Experimental evaluations on both benchmark and real-world LSMOPs demonstrate that an evolutionary algorithm incorporating the proposed knowledge learning-based dimensionality reduction approach outperforms most existing evolutionary algorithms.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 7","pages":"3471-3484"},"PeriodicalIF":9.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849807","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":"Quality Control in Extrusion-Based Additive Manufacturing: A Review of Machine Learning Approaches","authors":"Adailton Gomes Pereira;Gustavo Franco Barbosa;Moacir Godinho Filho;Sidney Bruce Shiki;Andrea Lago da Silva","doi":"10.1109/TCYB.2025.3558515","DOIUrl":"10.1109/TCYB.2025.3558515","url":null,"abstract":"Additive manufacturing (AM) revolutionizes product creation with its unique layer-by-layer construction method but faces obstacles in widespread industrial use due to quality assurance and defect challenges. Integrating machine learning (ML) into AM quality control (QC) systems presents a viable solution, utilizing ML’s ability to autonomously detect patterns and extract important data, reducing the reliance on manual intervention. This study conducts an in-depth literature review to scrutinize the role of ML in augmenting QC mechanisms within extrusion-based AM processes. Our primary objective is to pinpoint ML models that excel in monitoring manufacturing activities and facilitating instantaneous defect corrections via parameter adjustments. Our analysis highlights the efficacy of convolutional neural networks (CNNs) models in defect detection, leveraging camera-based systems for an in-depth examination of printed parts. For 1-D data processing, support vector machines (SVMs) and long short-term memory (LSTM) networks have shown significant application and effectiveness. Furthermore, the study classifies various sensors and defects that can effectively benefit from ML-driven QC approaches. Our findings accentuate the essential role of ML, especially CNNs, in detecting and rectifying production flaws and also detail the synergy between different sensor technologies in creating a comprehensive monitoring framework. By integrating ML with a multisensor approach and employing real-time corrective strategies, such as dynamic parameter adjustments and the use of advanced control systems, this research underscores ML’s transformative potential in elevating AM QC. Thus, our contribution lays the groundwork for harnessing ML technologies to ensure superior quality parts production in AM, paving the way for its broader industrial adoption.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 6","pages":"2522-2534"},"PeriodicalIF":9.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849734","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":"Distributed Practical Fixed-Time Resource Allocation Algorithm for Disturbed Multiagent Systems: An Integrated Framework","authors":"Qingxiang Ao;Cheng Li;Ben Niu;Zhiliang Zhao;Jiaxin Yuan;Sen Chen;Xiaole Yang","doi":"10.1109/TCYB.2025.3558787","DOIUrl":"10.1109/TCYB.2025.3558787","url":null,"abstract":"The practical fixed-time resource allocation problem is investigated for multi-input-multi-output nonlinear uncertain multiagent systems with disturbed dynamics, subject to global equality and local inequality constraints. Due to the coexistence of distributed high-order dynamics system within agents and decision-making constraints, decision variables in resource allocation optimization problems cannot be directly obtained from the system. Existing strategies are insufficient to solve such complex fixed-time optimization control problems with coupled decision-making constraints. To address these challenges, a novel integrated framework is proposed, fusing symbolic-function-based fixed-time control theory with gradient consistency. The proposed algorithm is implemented through an output-feedback backstepping design process, which involves two stages. First, in the output-feedback design stage, a fixed-time high-order extended state observer estimates the uncertain dynamics and disturbances. Second, in the backstepping design stage, a time-switching controller is developed. This controller’s virtual control law has two components: the first employs the proportional-integral control method to satisfy the equality constraints, while the second uses gradient information from the <inline-formula> <tex-math>$epsilon $ </tex-math></inline-formula>-exact penalty function to address the inequality constraints. Using the Lyapunov stability criterion, the proposed algorithm can ensure that all signals remain practical fixed-time stable, and that the error between the outputs of all agents and the optimal solution is maintained within a neighborhood of the origin. Finally, simulations are presented to demonstrate the effectiveness of the approach.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 6","pages":"2820-2832"},"PeriodicalIF":9.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849810","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":"Asynchronous Control of Cyber–Physical Systems With Quantized Measurements and Stochastic Multimode Attacks","authors":"Yuan Wang;Huaicheng Yan;Ju H. Park;Yunsong Hu;Hao Shen","doi":"10.1109/TCYB.2025.3555396","DOIUrl":"10.1109/TCYB.2025.3555396","url":null,"abstract":"This article is concerned with the observer-dependent asynchronous control problem in cyber-physical systems (CPSs) vulnerable to multimode attacks, with a specific focus on addressing the significant challenge posed by the surreptitious nature of attack behaviors. First, in view of band-limited communication channels in CPSs, the quantizer is used to quantize the measured output. Second, owing to the open and shared network of CPSs, the data transmission process is more susceptible to attacks. A multichannel transmission framework is constructed under the assumption that each transmitted data element is susceptible to potential attacks. The switching dynamics among various attack forms launched by the adversary on the transmission channel are governed by a semi-Markov chain. The analysis of multimode attacks with stealth characteristics is conducted within the framework of a hidden semi-Markov jump mode, which is achieved by establishing a dual-layer stochastic process comprising a multimode sequence and an observed mode sequence. Leveraging emission probability, we design an observed-mode-dependent controller capable of stabilizing the system even in the absence of direct access to the actual attack patterns and in the presence of information loss. The simulations involving a single-channel unmanned ground vehicle system and a mass-spring–damper system with two channels are provided to validate the feasibility and efficacy of our proposed methodology.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 7","pages":"3390-3402"},"PeriodicalIF":9.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849811","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":"Distributed Resilient Secondary Control Strategy Considering Economic Dispatch for DC Microgrids: A Dynamic Event-Triggered Mechanism","authors":"Daduan Zhao, Yan Li, Xiangyang Cao, Yue Sun, Chenghui Zhang","doi":"10.1109/tcyb.2025.3554751","DOIUrl":"https://doi.org/10.1109/tcyb.2025.3554751","url":null,"abstract":"","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"10 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849812","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}