检索结果-内蒙古大学图书馆

International Conference on intelligent System and Knowledge engineering, ISKE

作者： Hao Chen Ruiping Yin Zhen Yang Faculty of Information Technology Beijing University of Technology Beijing China The Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing China

Under traditional recommendation frameworks based on a central server, recommender systems provide rec-ommendations for different users by training a global model for all users on the cloud. However, this method cannot provide high-quality recommendations for the majority of low-active users as well as those who are not willing to provide their personal data to the central server. Additionally, training solely on a user's device with local data may lead to overfitting due to the insufficiency of local data. In this work, we propose a two-stage process of coarse and fine-grained data augmentation using clustering and filtering to alleviate data insufficiency at the edge. Furthermore, we use meta-learning to formulate a two-stage training process from cloud to edge. The meta-training process of the global model is conducted on the cloud, and fast training on the edge is suitable for resource-constrained edge devices, enabling high-quality recommendations for each user. The extensive experimental results demonstrate the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Time Series Prediction Integrated RNN-DRL for Energy-Emission Management in HEVs 7

Time Series Prediction Integrated RNN-DRL for Energy-Emissio...

引用

7th CAA International Conference on Vehicular control and Intelligence, CVCI 2023

作者： Luan, Junzhi Guo, Lulu Ma, Baolin Chen, Hong Clean Energy Automotive Engineering Center Tongji University Shanghai China Department of Control Science and Engineering Tongji University Shanghai China Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China

ISBN: (纸本)9798350340488

Learning-based strategies have gained widespread adoption in the field of energy management strategy (EMS) for hybrid electric vehicles (HEVs). However, existing algorithms often struggle to maintain the effectiveness in different driving scenarios. Additionally, achieving a fully observable Markov decision process in real-world situations is impractical due to the limitation in sensor sensitivity and noise. Therefore, it is crucial to design a stable EMS for HEVs that can adapt to various driving scenarios. This paper proposes a novel approach called the twin-delayed deep deterministic policy gradient with a long-short-term combined algorithm. It aims to enhance the generalization performance and EMS capability of HEVs' learning-based EMS by integrating temporal predicted information using a recurrent neural network. Comparing this algorithm with other established deep reinforcement learning algorithms, the results demonstrate significant improvements in EMS performance for HEVs, including state of charge maintenance, energy conservation, and emission reduction. Notably, the algorithm achieves these improvements while ensuring robust generalization across diverse driving cycles and scenarios. © 2023 IEEE.

关键词： DRL EMS generalization HEVs predicted information

来源：评论

学校读者我要写书评

暂无评论

Anomaly-Resistant Decentralized State Estimation Under Minimum Error Entropy With Fiducial Points for Wide-Area Power Systems

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 74-87页

作者： Bogang Qu Zidong Wang Bo Shen Hongli Dong Hongjian Liu the College of Automation Engineering Shanghai University of Electric PowerShanghai 200090China IEEE the Department of Computer Science Brunel University LondonUxbridgeMiddiesex UB83PHUK the College of Information Science and Technology Donghua UniversityShanghai 200051 the Engineering Research Center of Digitalized Textile and Fashion Technology Ministry of EducationShanghai 201620China the Artificial Intelligence Energy Research Institute Northeast Petroleum UniversityDaqing 163318 the Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Northeast PetroleumDaqing 163318 the Sanya Offshore Oil&Gas Research Institute Northeast Petroleum UniversitySanya 572024China the Key Laboratory of Advanced Perception and Intelligent Control of High-End Equipment Ministry of EducationAnhui Polytechnic UniversityWuhu 2410000 the School of Mathematics and Physics Anhui Polytechnic UniversityWuhu 241000China

This paper investigates the anomaly-resistant decentralized state estimation(SE) problem for a class of wide-area power systems which are divided into several non-overlapping areas connected through transmission lines. Two classes of measurements(i.e., local measurements and edge measurements) are obtained, respectively, from the individual area and the transmission lines. A decentralized state estimator, whose performance is resistant against measurement with anomalies, is designed based on the minimum error entropy with fiducial points(MEEF) criterion. Specifically, 1) An augmented model, which incorporates the local prediction and local measurement, is developed by resorting to the unscented transformation approach and the statistical linearization approach;2) Using the augmented model, an MEEF-based cost function is designed that reflects the local prediction errors of the state and the measurement;and 3) The local estimate is first obtained by minimizing the MEEF-based cost function through a fixed-point iteration and then updated by using the edge measuring information. Finally, simulation experiments with three scenarios are carried out on the IEEE 14-bus system to illustrate the validity of the proposed anomaly-resistant decentralized SE scheme.

关键词： Decentralized state estimation(SE) measurements with anomalies minimum error entropy unscented Kalman filter wide-area power systems

来源：评论

学校读者我要写书评

暂无评论

Fast tracing method for Sybil attack in VANETs

Fast tracing method for Sybil attack in VANETs

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Zhaoyi Zhang Yingxu Lai Ye Chen Jingwen Wei Yuan Feng Faculty of Information Technology Beijing University of Technology Beijing China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing China

In VANETs, malicious nodes launch Sybil attacks using false traffic information by forging basic safety messages, leading to erroneous decisions and ultimately causing traffic accidents that threaten the lives of passengers. Existing Sybil attack detection methods can only mitigate the impact of Sybil attacks and cannot trace the attack back to find malicious nodes. Meanwhile, malicious nodes can suppress the performance of tracing methods with the help of pseudonym exchange policy. This study proposes a fast Sybil attack tracing method in VANETs to address the above challenges. The method quickly identifies suspicious BSMs through cascading operations. Finally, the results of cascading operations are used to perform source estimation and complete the attack tracing. Experimental results show the method’s precision ≥97% and recall ≥96%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Linear Deception Attacks on Remote State Estimation with Constrained Alarm Rates: A Low-Dimensional Case 63

Optimal Linear Deception Attacks on Remote State Estimation ...

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Shang, Jun Zhang, Hanwen Zhou, Jing Chen, Tongwen Tongji University Shanghai Research Institute for Intelligent Autonomous Systems National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Department of Control Science and Engineering Shanghai200092 China University of Science and Technology Beijing Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering Beijing100083 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada

ISBN: (纸本)9798350316339

This study addresses linear attacks on remote state estimation within the context of a constrained alarm rate. Smart sensors, which are equipped with local Kalman filters, transmit innovations instead of raw measurements through a wireless communication network. This transmission is vulnerable to malicious data interception and manipulation by attackers. The aim of this research is to identify the optimal attack strategy that degrades the system performance while adhering to stealthiness constraints. A notable innovation of this paper is the direct association of the attack's stealthiness with the alarm rate, diverging from traditional approaches that rely on the covariance of the innovation or the Kullback-Leibler divergence, which are conventional metrics that have been extensively explored in previous studies. Our findings reveal that the optimal attack strategy exhibits some structural characteristics in systems of low dimensions. The performance of the proposed attack strategy is demonstrated through numerical examples. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation for Blockchain-Enabled Fog Computing with Deep Reinforcement Learning 12

Resource Allocation for Blockchain-Enabled Fog Computing wit...

引用

12th International Conference on Communication and Network Security, ICCNS 2022

作者： Zhang, Yihe Tu, Shanshan Waqas, Muhammad Yang, Yongjie Wu, Aiming Bai, Xuetao Engineering Research Center of Intelligent Perception and Autonomous Control Faculty of Information Technology Beijing University of Technology Beijing China Computer Engineering Department College of Information Technology University of Bahrain 32038 Bahrain School of Engineering Edith Cowan University Perth6027 Australia

ISBN: (纸本)9781450397520

With the developments of the Internet of Things, the demands of low latency, high bandwidth and high-performance computing has increased higher. Therefore, the distributed computing named Fog Computing has proposed to solve the problem above. Fog computing can provide lower transmission latency, faster response time and less network congestion. However, the fog devices are unable to guarantee the security and privacy of data transmission, due to they are vulnerable to attack. Blockchain technology works as a decentralized public ledger to store and share transactions. Blockchain can improve security and protect data privacy of Fog Computing. Moreover, there are still issues in the blockchain-enabled Fog Computing, the two main issues are the energy consumption and computing efficiency. Thus, in this paper, we propose an optimization framework for blockchain-enabled Fog Computing systems to optimize resource allocation. Besides, we adopt the dueling deep reinforcement learning to obtain the optimal resource allocation strategy, with dynamically selecting the fog server, offloading decision, block size. Simulation results show that the proposed framework can reduce the energy consumption and computation overhead of the system, as well as can improve the computing efficiency. © 2022 ACM.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Multi-Vehicle Cooperative Localization Using a TOA-Based Simulated Annealing Extended Kalman Filter in Urban Canyons

引用

IEEE Internet of Things Journal 2025年

作者： Li, Duhao Deng, Heng Yu, Tianhong Zhang, Liguo Beijing University of Technology School of information Science and Technology Beijing100124 China Ministry of Education Engineering Research Center of Intelligence Perception and Autonomous Control Beijing100124 China

This paper proposes a new multi-vehicle cooperative localization approach that combines Time of Arrival (TOA) with a heuristic Simulated Annealing Extended Kalman Filter (SA-EKF) to enhance positioning accuracy and robustness in urban canyons. The method incorporates a path loss model to account for the complex communication environment between vehicles, using TOA measurements for distributed EKF estimation. The integration of a simulated annealing strategy within the method is instrumental in circumventing local minima, thereby facilitating global optimisation. Furthermore, an adaptive weighted filtering correction mechanism is employed to enhance estimation accuracy and system stability. Experimental results conducted on the SUMO simulation platform and in real-world scenarios demonstrate that the proposed method offers certain advantages over existing approaches in complex, noisy environments. © 2014 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection Based on Bidirectional Long Short-Term Memory with Attention Mechanism

引用

Computers, Materials & Continua 2023年第1期74卷 801-815页

作者： Yongjie Yang Shanshan Tu Raja Hashim Ali Hisham Alasmary Muhammad Waqas Muhammad Nouman Amjad Engineering Research Center of Intelligent Perception and Autonomous Control Faculty of Information TechnologyBeijing University of TechnologyBeijing100124China Faculty of Computer Science and Engineering GIK Institute of Engineering Sciences and TechnologyTopi23460Pakistan Department of Computer Science College of Computer ScienceKing Khalid UniversityAbhaSaudi Arabia Information Security and Cybersecurity Unit King Khalid UniversityAbhaSaudi Arabia Computer Engineering Department College of Information TechnologyUniversity of Bahrain32038Bahrain School of Engineering Edith Cowan UniversityJoondalup PerthWA6027Australia School of Engineering University of Management and TechnologyLahorePakistan

With the recent developments in the Internet of Things(IoT),the amount of data collected has expanded tremendously,resulting in a higher demand for data storage,computational capacity,and real-time processing *** computing has traditionally played an important role in establishing ***,fog computing has recently emerged as a new field complementing cloud computing due to its enhanced mobility,location awareness,heterogeneity,scalability,low latency,and geographic ***,IoT networks are vulnerable to unwanted assaults because of their open and shared *** a result,various fog computing-based security models that protect IoT networks have been developed.A distributed architecture based on an intrusion detection system(IDS)ensures that a dynamic,scalable IoT environment with the ability to disperse centralized tasks to local fog nodes and which successfully detects advanced malicious threats is *** this study,we examined the time-related aspects of network traffic *** presented an intrusion detection model based on a twolayered bidirectional long short-term memory(Bi-LSTM)with an attention mechanism for traffic data classification verified on the UNSW-NB15 benchmark *** showed that the suggested model outperformed numerous leading-edge Network IDS that used machine learning models in terms of accuracy,precision,recall and F1 score.

关键词： Fog computing intrusion detection bi-LSTM attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A Multi-loop Reveals Different Neural Mechanisms of Inductive Reasoning in DLPFC and SPL 17th

A Multi-loop Reveals Different Neural Mechanisms of Inducti...

引用

17th International Conference on Brain Informatics, BI 2024

作者： Ma, Lianfang Chen, Shiyun Huang, Jiajin Wang, Zhijiang Chen, Jianhui The School of Information Science and Technology Beijing University of Technology Beijing100124 China Beijing International Collaboration Base on Brain Informatics and Wisdom Services Beijing100124 China College of Environmental Science and Engineering Beijing University of Technology Beijing100124 China Beijing100191 China National Clinical Research Center for Mental Disorders and Key Laboratory of Mental Health Ministry of Health Peking University Beijing100191 China Engineering Research Center of Intelligent Perception and Autonomous Control Beijing100124 China Ministry of Education and Engineering Research Center of Digital Community Ministry of Education Beijing100124 China

ISBN: (纸本)9789819632961

Recent findings in the field of neuroimaging have greatly enriched our understanding of the process of human inductive reasoning. However, as an extremely complex cognitive activity, inductive reasoning involves multiple cognitive functions such as attention, memory, executive function, symbol processing, and fluid intelligence, and requires the collaborative participation of multiple brain regions. Therefore, achieving a unified and transparent understanding of human inductive reasoning from different datasets presents formidable challenges. This paper proposes a multi-loop based integration analysis framework of multiple source brain data. By employing representational similarity analysis and multi-task functional neuroimaging analyses, this framework combines internal evidence, i.e., multi-source functional neuroimaging data, and external evidence, i.e., knowledge from published neuroimaging articles, to reveal different neural mechanisms of inductive reasoning in DLPFC and SPL. Experimental results reveal the intricate uncertainty surrounding brain localization in human reasoning. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Functional neuroimaging

来源：评论

学校读者我要写书评

暂无评论

HiFi-Sim: A High-Fidelity Simulation Platform for Intelligence Assessment of USV 9

HiFi-Sim: A High-Fidelity Simulation Platform for Intelligen...

引用

9th International Conference on Computer and Communications, ICCC 2023

作者： Liu, Ziyu Xue, Zhenfeng Huang, Tao Chen, Zhuo Liu, Yong Huzhou University School of Information Engineering Huzhou313000 China Huzhou Institute of Zhejiang University Intelligent Perception and Control Center Huzhou313098 China Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China Cssc Systems Engineering Research Institute Beijing100094 China

ISBN: (纸本)9798350317251

The Unmanned Surface Vessel (USV) is one of important equipments for river and marine activities. During the development stage, full process simulation plays a key role due to the coupling relationship between the USV sub-systems. Nonetheless, there are few open source platforms available in the community, and existing ones are outdated and not suitable for intelligent evaluation. Thus, we propose this paper to promote our platform, a simulation platform for USV. The biggest feature lies in its high fidelity, mainly manifested in the following aspects. First, a great deal of effort was put into building the river scenes in Unity, where the lighting and rendering characteristics can be well guaranteed. Second, the input and output controls are achieved through Robot Operating System (ROS), which is test-friendly for personnel engaged in unmanned system development. Third, we have developed and imported a large number of sensor plugins in Unity to ensure various types of sensor data, including multiple cameras and LiDARs, and that is vital for evaluating intelligent algorithms of USV. Integration between ROS and Unity is achieved through TCP/IP communication, facilitating data transfer via topic-based mechanisms. Environmental impacts are also taken into account by including water wave, wind and rain scripts in Unity3D. We have conduced some representative experiments of USV to verify its effectiveness, including direct LiDAR odometry and water segmentation. © 2023 IEEE.

关键词： Robot Operating System

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：