IEEE Transactions on Cybernetics最新文献_第5页

Novel SMC for Discrete Interval Type-2 Fuzzy Semi-Markovian Switching Models With Incomplete Semi-Markovian Kernel. 具有不完全半马尔可夫核的离散区间2型模糊半马尔可夫切换模型的新颖SMC。

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-07-03 DOI: 10.1109/TCYB.2025.3579728

Wenhai Qi, Jichao Zhang, Guangdeng Zong, Shun-Feng Su, Jinde Cao, Ruey-Huei Yeh

引用次数: 0

Performance-Driven Distillation and Confident Pseudo Labeling for Semi-Supervised Industrial Soft-Sensor Application. 性能驱动蒸馏和自信伪标记在半监督工业软测量中的应用。

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-07-03 DOI: 10.1109/TCYB.2025.3580633

Bochun Yue, Kai Wang, Hongqiu Zhu, Chunhua Yang, Weihua Gui

{"title":"Performance-Driven Distillation and Confident Pseudo Labeling for Semi-Supervised Industrial Soft-Sensor Application.","authors":"Bochun Yue, Kai Wang, Hongqiu Zhu, Chunhua Yang, Weihua Gui","doi":"10.1109/TCYB.2025.3580633","DOIUrl":"https://doi.org/10.1109/TCYB.2025.3580633","url":null,"abstract":"In industrial soft-sensor applications, labeled samples are often scarce and unable to fully represent the dynamic changes in industrial processes. Although semi-supervised methods offer a potential solution to this issue, existing feature-construction-based methods cannot ensure the effectiveness of the feature, and pseudo-label-based methods lack an established confidence evaluation standard. To address these challenges, this article first proposes a novel performance-driven distillation strategy, which designs an innovative siameseLSTM structure for training multiple teacher models. By assigning higher weights to high-performance teacher models and simultaneously leveraging the guidance of the soft sensing task, the student model is guided to learn more effective feature representations. Additionally, a new pseudo label confidence evaluation strategy is introduced, which aims to enhance the generalization of the base soft-sensor model by selecting samples with high-confidence pseudo labels. Finally, By combining the above two strategies, a semi-supervised soft-sensor framework is proposed for the soft sensing of industrial quality variables. The effectiveness of the proposed framework is validated through two real-world datasets from different stages of the alumina production process. Compared with some existing advanced soft sensor frameworks, the prediction results on different datasets show that the root-mean-square error (RMSE) and mean absolute error (MAE) are reduced by an average of 10.76% and 11.18%, respectively, while the correlation coefficient (R2) is averagely increased by 0.1203.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"PP ","pages":""},"PeriodicalIF":9.4,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144560025","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

Understanding the Dimensional Need of Noncontrastive Learning. 理解非对比学习的维度需求。

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-07-03 DOI: 10.1109/TCYB.2025.3577745

Zhexiao Cao, Lei Huang, Tian Wang, Yinquan Wang, Jingang Shi, Aichun Zhu, Tianyun Shi, Hichem Snoussi

{"title":"Understanding the Dimensional Need of Noncontrastive Learning.","authors":"Zhexiao Cao, Lei Huang, Tian Wang, Yinquan Wang, Jingang Shi, Aichun Zhu, Tianyun Shi, Hichem Snoussi","doi":"10.1109/TCYB.2025.3577745","DOIUrl":"https://doi.org/10.1109/TCYB.2025.3577745","url":null,"abstract":"Noncontrastive self-supervised learning methods offer an effective alternative to contrastive approaches by avoiding the need for negative samples to avoid representation collapse. Noncontrastive learning methods explicitly or implicitly optimize the representation space, yet they often require large representation dimensions, leading to dimensional inefficiency. To provide negative samples, contrastive learning methods often require large batch sizes, thus regarded as sample inefficient, while noncontrastive learning methods require large representation dimensions, thus regarded as dimension inefficient. Although we have some understanding of the noncontrastive learning method, theoretical analysis of such phenomenon still remains largely unexplored. We present a theoretical analysis of the dimensional need for noncontrastive learning. We investigate the transfer between upstream representation learning and downstream tasks' performance, demonstrating how noncontrastive methods implicitly increase interclass distances within the representation space and how the distance affects the model performance of evaluation performance. We prove that the performance of noncontrastive methods is affected by the output dimension and the number of latent classes, and illustrate why performance degrades significantly when the output dimension is substantially smaller than the number of latent classes. We demonstrate our findings through experiments on image classification experiments, and enrich the verification in audio, graph and text modalities. We also perform empirical evaluation for image models on extensive detection and segmentation tasks beyond classification that show satisfactory correspondence to our theorem.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"PP ","pages":""},"PeriodicalIF":9.4,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144560026","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

Efficient Multidimensional Pipelined Chaotic Bulk-Codewords-Encryption for Cloud Control Systems 云控制系统的高效多维流水线混沌大码字加密

IF 11.8 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-07-02 DOI: 10.1109/tcyb.2025.3579036

Yasir Ali, Tayyab Manzoor, Huan Yang, Lijie You, Ruifeng Ma, Chenhang Yan, Taiqi Wang, Yuanqing Xia

引用次数: 0

Optimization-Free Smooth Control Barrier Function for Polygonal Collision Avoidance 多边形避碰的无优化平滑控制障碍函数

IF 11.8 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-07-02 DOI: 10.1109/tcyb.2025.3578441

Shizhen Wu, Yongchun Fang, Ning Sun, Biao Lu, Xiao Liang, Yiming Zhao

引用次数: 0

A Partial Joint Optimization Algorithm for Autonomous Air Combat Based on Hierarchical Reinforcement Learning 基于层次强化学习的自主空战局部联合优化算法

IF 11.8 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-07-02 DOI: 10.1109/tcyb.2025.3579745

Chenxu Qian, Xuebo Zhang, Lun Li, Yisong Wang, Minghui Zhao, Yongchun Fang

引用次数: 0

Disturbance Observer-Based Adaptive Chainlike Filter Approach for Prescribed-Time Consensus Tracking of Nonlinear Multiagent Systems via Dynamic State and Input Triggering 基于扰动观测器的非线性多智能体系统动态与输入触发的定时一致性跟踪自适应链状滤波方法

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-06-26 DOI: 10.1109/TCYB.2025.3576352

Hyeong Jin Kim;Sung Jin Yoo

{"title":"Disturbance Observer-Based Adaptive Chainlike Filter Approach for Prescribed-Time Consensus Tracking of Nonlinear Multiagent Systems via Dynamic State and Input Triggering","authors":"Hyeong Jin Kim;Sung Jin Yoo","doi":"10.1109/TCYB.2025.3576352","DOIUrl":"10.1109/TCYB.2025.3576352","url":null,"abstract":"This article addresses the problem of adaptive prescribed-time distributed consensus tracking with dynamic full-state and input triggering for a class of uncertain state-constrained strict-feedback multiagent systems with external disturbances. The primary contribution lies in developing of a novel prescribed-time disturbance observer-based adaptive chainlike filter, capable of generating smooth estimates of intermittently triggered state-feedback signals while compensating for external disturbances and unknown nonlinearities within a predefined convergence time. The multiagent systems are nonlinearly transformed to address state constraints, without needing feasibility conditions on virtual control laws in the recursive design. The dynamic triggering variables are introduced using a prescribed-time adjustment function and distributed tracking errors. Based on the state variables of the adaptive chainlike filters, a prescribed-time distributed consensus tracking strategy is established to guarantee the prescribed-time convergence of filtering errors, disturbance observation errors, leader estimation errors, and consensus tracking errors, without requiring continuous state-feedback measurements. The shared use of neural networks across chainlike filters, disturbance observers, and controllers reduces computational complexity. The practical prescribed-time stability and satisfaction of state constraints in the closed-loop system are proven through a rigorous technical lemma. Finally, simulation results validate the effectiveness and robustness of the proposed control scheme.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 8","pages":"4001-4014"},"PeriodicalIF":9.4,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144500742","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

Leader-Following Consensus of Time-Scale-Type Heterogeneous Nonlinear MASs via Periodic Event-Triggered Control 基于周期事件触发控制的时标型非均质非线性质量的领导-跟随一致性

IF 11.8 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-06-26 DOI: 10.1109/tcyb.2025.3579049

Yin Sheng, Wei Tang, Qiang Xiao, Zhigang Zeng, Nikhil R. Pal

引用次数: 0

Bipartite Synchronization for Coupled Fractional-Order Reaction-Diffusion Neural Networks With Multiple Weights 多权耦合分数阶反应扩散神经网络的二部同步

IF 11.8 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-06-26 DOI: 10.1109/tcyb.2025.3573856

Jin-Liang Wang, Ya-Nan Li, Xin-Yu Zhao, Rui-Guo Li, Tingwen Huang

引用次数: 0

Lifeisgood: Learning Invariant Features via In-Label Swapping for Generalizing Out-of-Distribution in Machine Fault Diagnosis Lifeisgood：基于标签内交换的机器故障诊断中非分布泛化的不变量特征学习

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-06-26 DOI: 10.1109/TCYB.2025.3578712

Zhenling Mo;Zijun Zhang;Kwok-Leung Tsui

{"title":"Lifeisgood: Learning Invariant Features via In-Label Swapping for Generalizing Out-of-Distribution in Machine Fault Diagnosis","authors":"Zhenling Mo;Zijun Zhang;Kwok-Leung Tsui","doi":"10.1109/TCYB.2025.3578712","DOIUrl":"10.1109/TCYB.2025.3578712","url":null,"abstract":"In machine fault diagnosis, conventional data-driven models trained by empirical risk minimization (ERM) often fail to generalize across domains with distinct data distributions caused by various machine operating conditions. One major reason is that ERM primarily focuses on informativeness of data labels and lacks sufficient attention on invariance of data features. To enable invariance on top of informativeness, a learning framework, learning invariant features via in-label swapping for generalizing out-of-distribution (Lifeisgood), is proposed in this study. Lifeisgood is inspired by a simple intuition that invariance can be assessed by checking changes in loss due to swapping certain entries of features with the same labels. Lifeisgood also enjoys a theoretical guarantee on improving testing domain performance under certain conditions based on a swapping 0-1 loss proposed in this work. To circumvent the training difficulties associated with the swapping 0-1 loss, a swapping cross-entropy loss is derived as a surrogate and theoretical justifications for such a relaxation are also provided. As a result, Lifeisgood can be employed conveniently to develop data-driven fault diagnosis models. In the experiments, Lifeisgood outperformed the majority of state-of-the-art methods in terms of average accuracy and exceeded the second-best by 25% in terms of the frequency of beating the generic ERM. The code is available at: <uri>https://github.com/mozhenling/doge-lifeisgood</uri>","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 8","pages":"3699-3712"},"PeriodicalIF":9.4,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144500747","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