检索结果-内蒙古大学图书馆

International Conference on Intelligent Transportation

作者： Shengyue Yao Jingru Yu Yi Yu Jia Xu Xingyuan Dai Honghai Li Fei-Yue Wang Yilun Lin Urban Computing Shanghai AI Lab Shanghai China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Research and Development Center of Transport Industry of Autonomous Driving Technology RIOH High and Technology Group Institute of Automation Chinese Academy of Sciences Beijing China Macau Institute of Systems Engineering Macau University of Science and Technology Macau China

With a growing complexity of the intelligent traffic system (ITS), an integrated control of ITS that is capable of considering plentiful heterogeneous intelligent agents is desired. However, existing control methods based on the centralized or the decentralized scheme have not presented their competencies in considering the optimality and the scalability simultaneously. To address this issue, we propose an integrated control method based on the framework of Decentralized Autonomous Organization (DAO). The proposed method achieves a global consensus on energy consumption efficiency (ECE), meanwhile to optimize the local objectives of all involved intelligent agents, through a consensus and incentive mechanism. Furthermore, an operation algorithm is proposed regarding the issue of structural rigidity in DAO. Specifically, the proposed operation approach identifies critical agents to execute the smart contract in DAO, which ultimately extends the capability of DAO-based control. In addition, a numerical experiment is designed to examine the performance of the proposed method. The experiment results indicate that the controlled agents can achieve a consensus faster on the global objective with improved local objectives by the proposed method, compare to existing decentralized control methods. In general, the proposed method shows a great potential in developing an integrated control system in the ITS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Byzantine-robust federated learning considering distributed Non-IID data in privacy-sensitive scenarios

引用

Information Fusion 2025年 124卷

作者： Zongpu Wei Jinsong Wang Zening Zhao Zhao Zhao School of Computer Science and Engineering Tianjin University of technology Tianjin 300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin 300384 China National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin 300457 China

For federated learning (FL), its decentralized training approach is vulnerable to the targeted or untargeted attacks from Byzantine clients, which results in decreased model accuracy. In privacy-sensitive scenarios, the Byzantine clients identification is extremely difficult, due to the fact that gradient information is encrypted. To preserve privacy while identifying Byzantine clients in these scenarios, many schemes on identifying malicious local gradients over ciphertexts are proposed. However, existing works suffer from the problems of inefficiency in non-independent identically distributed (Non-IID) data and potential privacy leakage. To address the issues, we propose a privacy-preserving and byzantine-robust FL scheme (ProFL), which can resist encrypted malicious gradients effectively and protect the privacy of gradients. In ProFL, the linearly homomorphic encryption (LHE) technique is adopted to safeguard the gradient parameters. Specifically, ProFL designs two secure protocols that effectively mitigate potential threats in existing methods while maintaining computation complexity within a linear range. A robust aggregation method based on Manhattan distance is proposed to effectively enhance the robustness of federated aggregation in Non-IID data scenarios. The security and convergence proof of ProFL is given. Finally, extensive evaluations demonstrate that ProFL outperforms other privacy-preserving and byzantine-robust FL schemes in defending against various poisoning attacks.

关键词： Byzantine attack Defense strategy Federated learning Linearly homomorphic encryption Privacy preserving

来源：评论

学校读者我要写书评

暂无评论

ANN Based Sensor and Actuator Fault Detection in Nuclear Reactors 8

ANN Based Sensor and Actuator Fault Detection in Nuclear Rea...

引用

8th International Conference on control, Mechatronics and Automation, ICCMA 2020

作者： Banerjee, Shohan Deng, Jiamei Gorse, Chris Vajpayee, Vineet Becerra, Victor Shimjith, S.R. Engineering and Computing Leeds Beckett University School of Built Environment Leeds United Kingdom University of Portsmouth School of Energy and Electronic Engineering Portsmouth United Kingdom Bhabha Atomic Research Centre and Homi Bhabha National Institute Reactor Control System Design Section Mumbai India

ISBN: (纸本)9781728192109

In the nuclear power plants (NPPs), fault detection and diagnosis (FDD) methods are very important to improve the safety and reliability of plants. Researchers have established various FDD methods such as model-based methods, data-driven methods, and signal-based methods. In practical applications, model-based methods are very difficult to achieve. Thus, various data-driven methods and signal-based methods have been applied for monitoring key subsystems in NPPs. In this paper, a brief overview of the Artificial Neural Network (ANN) based FDD method is presented. Simulated data have been generated to train the ANNs as per requirement and to compare with the plant signal during a fault. A technique has been proposed analyzing two sensors data (power sensor and coolant sensor) to determine the sensor and actuator fault in a closed-loop in presence of robust (Proportional-Integral-Derivative) PID controller. Results are produced with credible MATLAB simulation. © 2020 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Graph-Neural-Network-Based Transaction Link Prediction Method for Public Blockchain in Heterogeneous Information Networks

引用

Blockchain: Research and Applications 2025年

作者： Zening Zhao Jinsong Wang Jiajia Wei School of Computer Science and Engineering Tianjin University of Technology Tianjin 300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin 300384 China National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin 300457 China

Public blockchain has outstanding performance in transaction privacy protection because of its anonymity. The data openness brings feasibility to transaction behavior analysis. At present, the transaction data of the public chain are huge, including complex trading objects and relationships. It is difficult to extract attributes and predict transaction behavior by traditional methods. To solve the problems, we extract the transaction features to construct the Ethereum transaction heterogeneous information network (HIN), and propose graph-neural-network-based transaction prediction method for public blockchain in HINs, which can divide the network into subgraphs according to connectivity and make the prediction results of transaction behavior more accurate. Experiments show that the execution time consumption of the proposed transaction subgraph division method is reduced by 70.61% on average compared with the search method. The accuracy of the proposed behavior prediction method also improve compared with the traditional random walk method, with an average accuracy of 83.82%.

关键词： Blockchain Link prediction Heterogeneous information networks Graph neural networks Random walk

来源：评论

学校读者我要写书评

暂无评论

An Efficient Bitcoin Network Topology Discovery Algorithm for Dynamic Display

引用

Blockchain: Research and Applications 2025年

作者： Zening Zhao Jinsong Wang Miao Yang Haitao Wang School of Computer Science and Engineering Tianjin University of Technology Tianjin 300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin 300384 China National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin 300457 China

The Bitcoin network comprises numerous nodes, necessitating users to invest significant network requests and time in comprehending its network topology. In this paper, we propose a Bitcoin network topology discovery algorithm that utilizes lightweight probe nodes to facilitate rapid transmission of network protocols. Building upon this, we introduce a node layer clustering algorithm based on filtering stable network nodes, enabling parallel discovery of the network topology. Additionally, we present an adaptive method for dynamically displaying the layered structure of the network topology. Experimental results demonstrate that our proposed method reduces communication overhead by approximately 72.16% when achieving a 95% similarity in network topology. Furthermore, the algorithm is applicable for discovering the network topology in other blockchain networks with similar structures.

关键词： Blockchain network topology discovery Bitcoin stability coefficient dynamic updates

来源：评论

学校读者我要写书评

暂无评论

TGAC: traffic graph adaptive convolutional neural network-based decentralized application encrypted traffic classification

引用

Journal of Supercomputing 2025年第8期81卷

作者： Ren, Chunni Wang, Jinsong Zhao, Zening School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin300457 China

The rise of blockchain technology has accelerated the development of decentralized applications (DApps), bringing user and network security threats. Efficient decentralized application (DApp) identification is essential for safeguarding user privacy and ensuring blockchain network stability. However, the similarity in communication interfaces and traffic encryption complicates classification. Existing methods also face limitations in feature processing and extraction, leading to lower accuracy. To address these challenges, this paper presents TGAC (traffic graph adaptive convolutional neural network), a DApp identification method based on a graph adaptive convolutional neural network. The method constructs traffic topology graphs by leveraging temporal traffic data, and designs a GAC (graph adaptive convolutional neural network) model to extract key information. It learns local node representations through graph convolution layers and introduces adaptive weights to enhance node features. The method’s effectiveness was validated using a real decentralized encrypted traffic dataset, achieving a classification accuracy of 99.4%, representing a 5% improvement over existing methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Collaborative Scheduling of computing Tasks for Edge computing

Collaborative Scheduling of Computing Tasks for Edge Computi...

引用

2021 China Automation Congress, CAC 2021

作者： Liu, Yue Xiong, Gang Zhu, Fenghua Chen, Shichao Zhang, Liguo Liu, Xudong School of Artificial Intelligence and Automation Beijing University of Technology The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation The Cloud Computing Center Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Qingdao Academy of Intelligent Industries Chinese Academy of Sciences Beijing China Faculty of Information and Technology Beijing University of Technology Beijing China

ISBN: (纸本)9781665426473

In the face of the rapid development of the IoT, the traditional cloud computing, while providing services for mobile intelligent devices, also brings problems such as network bandwidth occupation and communication delay. Edge computing can solve these problems to some extent. But too many offloaded tasks may result in an edge server becoming overloaded and execution delay of tasks increasing, the computing resources of idle edge devices are also not fully utilized. In order to make full use of the computing resources of idle edge devices in the local network and reduce the execution delay for computing tasks, this paper takes the average delay time for all end devices as the optimization objective and proposes an end-edge cooperative scheduling (EECS) model to schedule tasks for edge computing. The scheduling algorithm used in EECS model is improved based on MCT algorithm. We use the EdgeCloudSim to verify the EECS model and scheduling algorithm. The simulation results show that the average completion time of computing tasks in EECS model, compared with only single edge server (SEE) task computing model, can be reduced by up to three times. In addition, the system load can be balanced to a certain extent in local network. © 2021 IEEE

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Calibration of agent-based model using reinforcement learning 1

Calibration of agent-based model using reinforcement learnin...

引用

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Song, Bing Xiong, Gang Yu, Songmin Ye, Peijun Dong, Xisong Lv, Yisheng Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex Systems Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Chinese Academy of Sciences Beijing China Fraunhofer Institute for Systems and Innovation Research Breslauer Germany

ISBN: (纸本)9781665433372

In the research and application of Agent-Based Models (ABM), parameter calibration is an important content. Based on the existing state transfer equations that link the micro-parameters and macro-states of the multi-agent system, this paper further proposes to introduce Reinforcement Learning when calibrating the parameters. The state transfer of the agent after learning is used to calibrate the micro-parameters of ABM, and the interaction between each agent and multiple other agents is expressed as the parameters of the agent. The application case study of population migration demonstrates that our method can achieve high accuracy and low computational complexity. © 2021 IEEE.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

When measurements fail: using an interactive SLAM solution to fight bad odometry

When measurements fail: using an interactive SLAM solution t...

引用

IEEE Instrumentation and Measurement Technology Conference

作者： Robert Milijaš Juraj Oršulić Stjepan Bogdan Laboratory for Robotics and Intelligent Control Systems Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

ISBN: (数字)9781728144603

ISBN: (纸本)9781728144610

In this paper we use the underlying pose graph structure of graph SLAM to allow the user to inspect and intervene into the Simultaneous Localization and Mapping (SLAM) process. With post-processing the map by inserting custom constraints into the optimization problem, the user can improve the quality of the map obtained as the final SLAM result. We refer to this inspection and intervention process as interactive SLAM. The mathematical background, which allows such interventions, is laid out, and a software implementation is used to improve the quality of a map created at the Faculty of Electrical engineering and computing, University of Zagreb.

关键词： SLAM Robotics Interactive SLAM supersonic low altitude missile robotics maps software implementation ELECTRICAL engineering odometry

来源：评论

学校读者我要写书评

暂无评论

Modality Unified Attack for Omni-Modality Person Re-Identification

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5577-5587页

作者： Bian, Yuan Liu, Min Yi, Yunqi Wang, Xueping Ma, Yunfeng Wang, Yaonan Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China

Deep learning based person re-identification (re-id) models have been widely employed in surveillance systems. Recent studies have demonstrated that black-box single-modality and cross-modality re-id models are vulnerable to adversarial examples (AEs), leaving the robustness of multi-modality re-id models unexplored. Due to the lack of knowledge about the specific type of model deployed in the target black-box surveillance system, we aim to generate modality unified AEs for omni-modality (single-, cross- and multi-modality) re-id models. Specifically, we propose a novel Modality Unified Attack method to train modality-specific adversarial generators to generate AEs that effectively attack different omni-modality models. A multi-modality model is adopted as the surrogate model, wherein the features of each modality are perturbed by metric disruption loss before fusion. To collapse the common features of omnimodality models, Cross Modality Simulated Disruption approach is introduced to mimic the cross-modality feature embeddings by intentionally feeding images to non-corresponding modality-specific subnetworks of the surrogate model. Moreover, Multi Modality Collaborative Disruption strategy is devised to facilitate the attacker to comprehensively corrupt the informative content of person images by leveraging a multi modality feature collaborative metric disruption loss. Extensive experiments show that our MUA method can effectively attack the omni-modality re-id models, achieving 55.9%, 24.4%, 49.0% and 62.7% mean mAP Drop Rate, respectively. © 2005-2012 IEEE.

关键词： Modality unified attack Multi Modality Collaborative Disruption Omni-Modality re-id

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：