检索结果-内蒙古大学图书馆

Interpretable unsupervised neural network structure for data clustering via differentiable reconstruction of ONMF and sparse autoencoder

引用

Neural Networks 2025年 188卷 107504页

作者： Gai, Yongwei Liu, Jinglei School of Computer and Control Engineering Yantai University Shandong Yantai264005 China

Neural networks, while powerful, often face significant challenges in terms of interpretability, particularly in clustering tasks. Traditional methods typically rely on post-hoc explanations or supervised learning, which limit their ability to provide transparent, understandable results. The innovation of this method is the integration of Orthogonal Non-negative Matrix Factorization (ONMF) into a clustering layer, which is directly incorporated into the OSINN neural network model and enhanced by a Sparse Autoencoder (SAE). This integration allows for end-to-end model training, which improves clustering performance and provides interpretability by differentiably reconstructing ONMF and extracting sparse features with SAE. OSINN's main innovation is the differentiable reconstruction of ONMF, which creates a transparent clustering layer that is both end-to-end trainable and easily interpretable. Firstly, OSINN, as a transparent neural network with an embedded clustering layer, allows for pre-training model decision predictions, where the model is first trained on a large set of unlabeled data to learn useful features, and then makes clustering decisions based on these learned features. Secondly, by using unsupervised neural networks for clustering, OSINN can handle more complex data, where the network automatically groups similar data points without needing labeled examples, which is especially useful for tasks involving large, unlabeled datasets. Thirdly, as a differentiable version of ONMF, OSINN excels at data clustering by transforming the ONMF method into a differentiable process, making it easy to integrate into the neural network architecture for end-to-end learning, which in turn enhances both interpretability and performance. Experimental results on MNIST, CIFAR-10, Fashion-MNIST, and CIFAR-100 datasets show that OSINN outperforms existing methods, achieving clustering accuracies of 90%, 24%, 64%, and 44%, respectively. Compared to traditional clustering algor

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fixed-Time Command Filtered Tracking control for Parametric Nonlinear Systems With Unknown Nonlinear control Coefficient and Unknown Disturbances

引用

IEEE Access 2025年 13卷 37839-37849页

作者： Zhang, Xiyu Zhou, Youjun Feng, Chun Deng, Xiongfeng Guangxi Science and Technology Normal University School of Mathematics and Computer Science Laibin546199 China Guang’an Institute of Technology School of Mechanical and Electrical Engineering Guang’an638550 China Anhui Polytechnic University Key Laboratory of Electric Drive and Control Anhui Higher Education Institute Wuhu241000 China

This paper addresses the issue of adaptive fixed-time tracking control (FTTC) for a category of parametric nonlinear systems characterized by unknown nonlinear control coefficient (UNCC) and unknown external disturbances (UEDs). To effectively handle unknown parameters and unknown disturbances, the adaptive parameter estimation method is introduced into the control law design. Meanwhile, some parameter adaptive laws are presented to estimate these unknown parameters. To eliminate repeated differentiation of virtual control laws, a class of nonlinear command filters is introduced. Furthermore, the filtering errors are compensated through the designed adaptive compensation control laws. Subsequently, the Nussbaum gain function technique is further used to deal with the UNCC in the system. Leveraging command-filtering backstepping control (BC) and fixed-time control method, an adaptive command filtered FTTC law is final presented to achieve the fixed time tracking. The theoretical analysis results indicate that the designed control law guarantees the convergence of tracking error to a small neighborhood of zero within a fixed time, while ensuring that all signals within the closed-loop system remain bounded. The proposed control law’s effectiveness is demonstrated through three simulation examples. © 2025 The Authors. This work is licensed under a Creative Commons Attribution 4.0 License.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

The Client-Level GAN-Based Data Reconstruction Attack and Defense in Clustered Federated Learning 18th

The Client-Level GAN-Based Data Reconstruction Attack and D...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Wu, Han Shi, Lei Ye, Junyu Fan, Yuqi Lv, Zengwei School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Engineering Research Center of Safety Critical Industrial Measurement and Control Technology Ministry of Education Hefei230009 China

ISBN: (纸本)9783031714634

Clustered Federated Learning (CFL) is an innovative architecture that effectively tackles the challenge of data heterogeneity in Federated Learning (FL). However, such a setup also introduces vulnerabilities that can be exploited by attackers to execute more severe attacks. This paper compares the efficacy of data reconstruction attacks utilizing Generative Adversarial Nets (GANs) in FL and CFL, respectively. It also proposes a general client-level data reconstruction attack scheme whose key is in that the attackers can eavesdrop the victim’s partial uploaded parameters. Experimental results demonstrate that the sample data generated in this kind of attack within the scenario of CFL exhibit a higher degree of similarity with the targeted data compared to FL. And it is observed that the attacks involving eavesdropping in CFL perform more effectively with a client-level attack accuracy. In addition, we design a lightweight and adaptive local differential privacy (LDP) mechanism to defend against this kind of attack. In this method, under the premise that the differential privacy budget decreases as the number of training round adds, each client dynamically adjusts the probability of adding differential privacy noise and the size of DP’s parameters according to the training accuracy and the resemblance to the reconstructed data generated by attackers. Our defense method can effectively alleviate the loss of training accuracy for each client caused by the accumulation of the differential privacy budget while ensuring the defense effect, and it also reduces clients’ computational burden. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Method for Abnormal Detection and Poisoned Data Recovery in Clustered Federated Learning 18th

A Method for Abnormal Detection and Poisoned Data Recovery...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Chen, Yingying Shi, Lei Xu, Hao Ye, Junyu Xu, Juan School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Engineering Research Center of Safety Critical Industrial Measurement and Control Technology Ministry of Education Hefei230009 China

ISBN: (纸本)9783031714665

Clustered Federated Learning (CFL), as a type of Federated Learning (FL) paradigm, divides the clients into multiple clusters through the clustering process and trains them within the clusters, thus improving the overall model training accuracy. But the clustering process is also the weak link, which can lead to the failure of the whole model training if it is interfered or destroyed by the attacker. In this paper, we study the attack methods and defense strategies for attackers to implement data poisoning by tampering with client data, resulting in overall clustering failure. Our defense approach is designed to identify anomalous clients and recover their poisoned data. In order to resist the malicious behavior of attackers, we propose a dual-threshold pixel difference and watermark authentication defense method for detecting the presence of anomalous clients. The method can accurately identify the abnormal fluctuations in the data and effectively screen out the abnormal clients. Meanwhile, we propose a self-embedding watermarking defense algorithm based on shuffling idea for recovering poisoned data. Among them, our self-embedding watermarking algorithm not only accurately locates and recovers the tampered region of the image, but also improves the watermark security to prevent attackers from cracking it easily. Simulation results show that our proposed algorithm can accurately identify the abnormal client and recover the data. Even if the client’s data is massively tampered with, we can recover the tampered data images with high quality and ensure that the CFL clustering is not corrupted. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Content-decoupled Contrastive Learning-based Implicit Degradation Modeling for Blind Image Super-Resolution Supplementary Material

引用

IEEE Transactions on Image Processing 2025年 34卷 3013-3024页

作者： Yuan, Jiang Ma, Ji Wang, Bo Hu, Weiming North China Electric Power University School of Control and Computer Engineering Beijing102206 China CASIA State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China ShanghaiTech University School of Information Science and Technology Shanghai201210 China

Implicit degradation modeling-based blind super-resolution (SR) has attracted more increasing attention in the community due to its excellent generalization to complex degradation scenarios and wide application range. How to extract more discriminative degradation representations and fully adapt them to specific image features is the key to this task. In this paper, we propose a new Content-decoupled Contrastive Learning-based blind image super-resolution (CdCL) framework following the typical blind SR pipeline. This framework introduces negative-free contrastive learning technique for the first time to model the implicit degradation representation, in which a new cyclic shift sampling strategy is designed to ensure decoupling between content features and degradation features from the data perspective, thereby improving the purity and discriminability of the learned implicit degradation space. In addition, we propose a detail-aware implicit degradation adapting module that can better adapt degradation representations to specific LR features by enhancing the basic adaptation unit's perception of image details, significantly reducing the overall SR model complexity. Extensive experiments on synthetic and real data show that our method achieves highly competitive quantitative and qualitative results in various degradation settings while obviously reducing parameters and computational costs, validating the feasibility of designing practical and lightweight blind SR tools. Codes and models will be available at https://***/Fieldhunter/CdCL. © 1992-2012 IEEE.

关键词： Depression Anxiety disorders Face recognition Schizophrenia Visualization Training Data collection Uncertainty Facial features Emotion recognition

来源：评论

学校读者我要写书评

暂无评论

State Estimation of a Spatial 2-D Linear Diffusion Process With Mobile Sensors

引用

IEEE Transactions on Automation Science and engineering 2025年 22卷 12024-12032页

作者： Zhang, Xiao-Wei Chen, Kui Wu, Huai-Ning Wang, Jin-Liang Wang, Zi-Peng Beijing University of Technology School of Information Science and Technology Beijing100124 China Tiangong University School of Control Science and Engineering Tianjin300387 China Beihang University Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical Engineering Beijing100191 China Beihang University Hangzhou International Innovation Institute Hangzhou311115 China Tiangong University Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems School of Computer Science and Technology Tianjin300387 China Beijing University of Technology School of Information Science and Technology Beijing Institute of Artificial Intelligence Beijing100124 China

This paper studies the state observer design of a spatial two-dimensional (2-D) linear diffusion process described by a linear parabolic partial differential equation (PDE) under mobile sensors. Firstly, we analyze the well-posedness of the PDE system and give the structure form of the state observer with mobile sensors. Subsequently, according to the number of mobile sensors, the 2-D space domain is divided into multiple sub-domains, and the mobile sensors are guided by the projection operator method, which can guarantee that the mobile sensors can only move in their respective 2-D sub-domains. Then, in the light of Lyapunov theory, Poincaré-Wirtinger inequality and Barbalat lemma, we propose an observation-plus-guidance design method to ensure the asymptotic stability of the state estimation error system. In the designed mobile strategy, the actual guidance of mobile sensors is essentially a physical synthesis of two direction guidance laws, where two dimensional guidance laws are designed separately. Moreover, the existence condition of the observer is given by linear matrix inequalities. At last, a numerical example is provided to demonstrate the efficacy of the proposed design scheme. © 2004-2012 IEEE.

关键词： Asymptotic stability

来源：评论

学校读者我要写书评

暂无评论

LLCoach: Generating Robot Soccer Plans Using Multi-role Large Language Models

LLCoach: Generating Robot Soccer Plans Using Multi-role Larg...

引用

27th RoboCup International Symposium, 2024

作者： Brienza, M. Musumeci, E. Suriani, V. Affinita, D. Pennisi, A. Nardi, D. Bloisi, D.D. Department of Computer Control and Management Engineering Sapienza University of Rome Rome Italy School of Engineering University of Basilicata Potenza Italy Department of International Humanities and Social Sciences International University of Rome Rome Italy

ISBN: (纸本)9783031858581

The deployment of robots into human scenarios necessitates advanced planning strategies, particularly when we ask robots to operate in dynamic, unstructured environments. RoboCup offers the chance to deploy robots in one of those scenarios, a human-shaped game represented by a soccer match. In such scenarios, robots must operate using predefined behaviors that can fail in unpredictable conditions. This paper introduces a novel application of Large Language Models (LLMs) to address the challenge of generating actionable plans in such settings, specifically within the context of the RoboCup Standard Platform League (SPL) competitions where robots are required to autonomously execute soccer strategies that emerge from the interactions of individual agents. In particular, we propose a multi-role approach leveraging the capabilities of LLMs to generate and refine plans for a robotic soccer team. The potential of the proposed method is demonstrated through an experimental evaluation, carried out simulating multiple matches where robots with AI-generated plans play against robots running human-built code. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Exploring NetGPT-Enabled Dynamic Resource Management for Mobile D2D in Industrial IoT

引用

IEEE Network 2025年第3期39卷 37-46页

作者： Chen, Baotong Liang, Haiquan Wan, Jiafu Wang, Chuangjian Yan, Xuguo Xia, Xuhui AlQahtani, Salman A. Wuhan University of Science and Technology Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan430081 China Wuhan University of Science and Technology Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan430081 China South China University of Technology School of Mechanical and Automotive Engineering Guangzhou510641 China King Saud University College of Computer and Information Sciences Computer Engineering Department Riyadh17748 Saudi Arabia

AI large model-centered intelligent applications holds promises to revolutionize network quality of service (QoS). therefore, the deployment and utilization of such models in the Industrial Internet of Things (Industrial IoT) are considered as an increasingly pressing priority. In particular, the integration of Generative AI (GenAI) into Industrial IoT, with a focus on establishing a robust NetGPT network architecture that leverages Mobile Edge Computing (MEC) and Device-to-Device (D2D) collaboration has been subjected to significant academic attention. Accordingly, this paper explores the optimization of dynamic network resource management in mobile D2D networks through the innovative application of NetGPT. First, a NetGPT-based system architecture for network resource management is proposed. Thereafter, mobile D2D network model is established with a detailed account of NetGPT training and NetGPT fusion. Finally, the workload scheduling strategy in industrial IoT based on Stackelberg game model is formulated though multi-agent GenAI and present the NetGPT-based orchestration of task co-offloading for mobile network nodes. Deep reinforcement learning is implemented at the edge side to compete and cooperate in addressing complex network problems, which enabling GenAI nodes in a co-offloading and load balancing manner. The implementation of NetGPT-enhanced D2D networks has been conducted in a Mininet simulation environment. Compared to traditional network solutions, our findings show significant improvements in several key performance indicators, including network response latency, task processing capacity, and transmission power. © 1986-2012 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Mobile Crowdsourcing Task Assignment Algorithm Based on ConvNeXt and GRU 18th

Mobile Crowdsourcing Task Assignment Algorithm Based on Con...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Fan, Zequn Pan, Qingxian Gao, Zhaolong Luan, Peng Wei, Kai Li, Jinru School of Computer and Control Engineering Yantai University Yantai264005 China Yantai Institute of Technology Yantai264005 China Yantaishan Hospital Shandong Province Yantai264003 China

ISBN: (纸本)9783031714634

Task assignment is a crucial aspect of mobile crowdsourcing research. The focus is on allocating appropriate perceptual tasks based on task and worker characteristics to optimize perceptual quality. Tasks arrive dynamically in a crowdsourcing system, and the platform cannot assign all tasks at the beginning. This can lead to the task allocation process falling into a local optimal solution. To address the problem, this paper proposes a two-stage prediction algorithm that utilises historical spatio-temporal data of crowdsourcing services. Firstly, the temporal data is converted into image data through Markov Transition Field. Then, the task availability is transformed into a categorisation problem. In the first stage, a ConvNeXt-based network is used to predict the task availability. In the second stage, a GRU-based network is used to predict the task duration. This paper presents the results of several experiments that confirm the effectiveness of the proposed algorithm. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Crowdfunding Readiness Level Assessment for Innovative Projects 18th

Crowdfunding Readiness Level Assessment for Innovative Proje...

引用

18th International Conference on Interdisciplinarity in engineering, INTER-ENG 2024

作者： Cseminschi, Stanislav Ionica, Andreea Cristina Leba, Monica Engineering and Management Doctoral School University of Petrosani Petrosani Romania Management and Industrial Engineering Department University of Petrosani Petrosani Romania Computer and System Control Engineering Department University of Petrosani Petrosani Romania

ISBN: (纸本)9783031813771

The study examines the multifaceted determinants influencing a project's community utility, including technological refinement, team dynamics, market feasibility, and funding sources. Crowdfunding, a prominent path for finan- cial support in the digital landscape, provides non-repayable backing. However, ensuring its effective utilization is crucial for upholding stakeholders' confidence. We propose the development of metrics to evaluate the readiness of innovative projects for crowdfunding initiatives. These metrics empower backers to facilitate the advancement or scalability of manufacturing processes prior to market entry. Based on the findings, we explore the best approaches to advance creative projects in higher education, particularly those that are started by student groups. Through meticulous analysis, we pinpointed areas of vulnerability within each project and proposed strategic directions for future enhancements. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Surveying

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：