检索结果-内蒙古大学图书馆

HeadSonic: Usable Bone Conduction Earphone Authentication via Head-conducted Sounds

IEEE Transactions on Mobile Computing 2025年

作者： He, Zhixiang Chen, Jing He, Kun Gu, Yangyang Deng, Qiyi Zhang, Zijian Du, Ruiying Zhao, Qingchuan Wu, Cong Wuhan University School of Cyber Science and Engineering Wuhan430072 China State Key Lab of Intelligent Transportation System Beijing China Beijing Institute of Technology School of Cyberspace Science and Technology China City University of Hong Kong Department of Computer Science Hong Kong The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong

Earables (ear wearables) are rapidly emerging as a new platform encompassing a diverse of personal applications, prompting the development of authentication schemes to protect user privacy. Existing earable authentication methods are all specifically designed for air-conduction earphones, which are not suited for bone conduction earphones (BCEs) that rely on bone conduction mechanisms. In this paper, we propose HeadSonic, a usable BCE authentication system based on the unique head-conducted sounds, which can be acquired when the user wears the BCE device. Specifically, the system emits a millisecond-level sound to initiate the authentication session. The signal captured by the BCE microphone is propagated through the user’s head, which is unique in density, geometry, and bone-tissue ratio. It operates implicitly, while maintaining robustness across different behaviors. Extensive experiments involving 60 subjects demonstrate that HeadSonic achieves a commendable balanced accuracy of 96.59%, proving its efficacy and resilience against replay and synthesis attacks. Our dataset and source codes are available at https://***/r/HeadSonic1CE4. © 2025 IEEE. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Matching Based Intelligent Edge Resource Allocation 3rd

Matching Based Intelligent Edge Resource Allocation

引用

3rd International Conference on Artificial Intelligence, 2022

作者： Qin, Peng Wang, Miao Zhao, Xiongwen Liu, Jiayan Wang, Shuo He, Haoting Xie, Yuanbo State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources School of Electrical and Electronic Engineering North China Electric Power University Beijing102206 China Hebei Key Laboratory of Power Internet of Things Technology North China Electric Power University Baoding071003 China School of Control and Computer Engineering North China Electric Power University Beijing102206 China

ISBN: (纸本)9789811694226

With the rapid development of the Internet of Things, multi-access edge computing (MEC) has emerged as a key technique and intelligent edge resource allocation has become one of the important research issues in MEC. In this paper, we utilize advantages of matching game to integrate users’ needs and the position of edge computing nodes in IoT networks. The proposed GS-based two-sided matching approach simulates the competition and negotiation relationship between different user sets in IoT edge nodes, and provides feasible options based on the preference between different entities. Simulations show that it not only solves the problem of edge resource allocation in a semi-distributed manner, but also effectively improves SP’s revenue. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

DSDFormer: An Innovative Transformer-Mamba Framework for Robust High-Precision Driver Distraction Identification

arXiv

引用

arXiv 2024年

作者： Chen, Junzhou Zhang, Zirui Yu, Jing Huang, Heqiang Zhang, Ronghui Xu, Xuemiao Sheng, Bin Yan, Hong Guangdong Provincial Key Laboratory of Intelligent Transportation System School of Intelligent Systems Engineering Sun Yat-Sen University Guangzhou510275 China The School of Computer Science and Engineering South China University of Technology China The Department of Computer Science and Engineering Shanghai Jiao Tong University China The Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong

Driver distraction remains a leading cause of traffic accidents, posing a critical threat to road safety globally. As intelligent transportation systems evolve, accurate and real-time identification of driver distraction has become essential. However, existing methods struggle to capture both global contextual and fine-grained local features while contending with noisy labels in training datasets. To address these challenges, we propose DSDFormer, a novel framework that integrates the strengths of Transformer and Mamba architectures through a Dual State Domain Attention (DSDA) mechanism, enabling a balance between long-range dependencies and detailed feature extraction for robust driver behavior recognition. Additionally, we introduce Temporal Reasoning Confident Learning (TRCL), an unsupervised approach that refines noisy labels by leveraging spatiotemporal correlations in video sequences. Our model achieves state-of-the-art performance on the AUC-V1, AUC-V2, and 100-Driver datasets and demonstrates real-time processing efficiency on the NVIDIA Jetson AGX Orin platform. Extensive experimental results confirm that DSDFormer and TRCL significantly improve both the accuracy and robustness of driver distraction detection, offering a scalable solution to enhance road safety. Copyright © 2024, The Authors. All rights reserved.

关键词： Highway accidents

来源：评论

学校读者我要写书评

暂无评论

Optimal Resource Allocation for U-Shaped Parallel Split Learning

Optimal Resource Allocation for U-Shaped Parallel Split Lear...

引用

IEEE Globecom Workshops

作者： Song Lyu Zheng Lin Guanqiao Qu Xianhao Chen Xiaoxia Huang Pan Li The Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong China School of Electronics and Communication Engineering Sun Yat-sen University Shenzhen China The Department of Electrical Computer and System Engineering Case Western Reserve University Cleveland OH USA

Split learning (SL) has emerged as a promising approach for model training without revealing the raw data samples from the data owners. However, traditional SL inevitably leaks label privacy as the tail model (with the last layers) should be placed on the server. To overcome this limitation, one promising solution is to utilize U-shaped architecture to leave both early layers and last layers on the user side. In this paper, we develop a novel parallel U-shaped split learning and devise the optimal resource optimization scheme to improve the performance of edge networks. In the proposed framework, multiple users communicate with an edge server for SL. We analyze the end-to-end delay of each client during the training process and design an efficient resource allocation algorithm, called LSCRA, which finds the optimal computing resource allocation and split layers. Our experimental results show the effectiveness of LSCRA and that U-shaped parallel split learning can achieve a similar performance with other SL baselines while preserving label privacy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI-aided power electronic converters automatic online real-time efficiency optimization method

引用

Fundamental Research 2025年第3期5卷 1111-1116页

作者： Tang, Yuanhong Cao, Di Xiao, Jian Jiang, Chenying Huang, Qi Li, Yunwei Chen, Zhe Blaabjerg, Frede Hu, Weihao Power System Wide-area Measurement and Control Sichuan Provincial Key Laboratory School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu 611731 China MORNSUN Guangzhou Science & Technology Co. Ltd. Guangzhou 510663 China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu 611731 China Yangtze Delta Region Institute (Quzhou) University of Electronic Science and Technology of China Quzhou 324000 China Department of Chengdu State Grid Corporation of China Chengdu 610599 China Southwest University of Science and Technology Mianyang 621010 China Department of Electrical and Computer Engineering University of Alberta Edmonton AB T6G 2V4 Canada Department of Energy Technology Aalborg University Aalborg 9220 Denmark

Energy losses during the conversion and supply of electric power are considered a significant issue and cannot be estimated. Improvement in the efficiency of energy conversion systems is highly restricted because of their internal nonlinearity and complexity. Thus, inspired by the successful utilization of robotic chemists, we demonstrate a pioneering concept of artificial intelligence (AI)-aided automatic online real-time optimization of a power electronics converter using a dual active bridge (DAB) converter as an example. An optimal modulation strategy was obtained through repeated automatic exploration experiments on a practical DAB converter platform. Specifically, the DAB experimental platform operated autonomously around the clock for approximately 71 h. It performed 120,000 consecutive experiments (12,000 episodes) within a six-variable experimental space driven by a deep deterministic policy gradient (DDPG) algorithm. The proposed AI-aided automatic online real-time optimization method achieved significantly improved efficiency of power conversion and supply. Consequently, zero carbon emissions may be obtained in the future. © 2023

关键词： Artificial intelligence Automatic online real-time exploration DC-DC converter Dual active bridge converter Energy conversion system Power electronics

来源：评论

学校读者我要写书评

暂无评论

A Website Fingerprinting Attack Based on Parameter Prediction Model for Conceptual Drift

A Website Fingerprinting Attack Based on Parameter Predictio...

引用

Software system and Information Processing (ICSSIP), IEEE International Conference on

作者： Jian Cui Taizhong Xu Li Zhao Shuai Han College of Computer Science and Technology Harbin Engineering University Harbin China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing China School of Electrical and Information Engineering Yunnan Minzu University Yunnan Key Laboratory of Unmanned Autonomous System Kunming China

ISBN: (数字)9798331506131

ISBN: (纸本)9798331506148

Website content updates and changes in the network environment can lead to concept drift, significantly impacting the performance of existing website fingerprinting methods. Recent research has focused on transfer learning-based approaches for concept drift adaptation to address this issue with limited samples. These methods involve pre-training a robust feature extractor and fine-tuning the classifier with a few samples. However, the effectiveness of these classifiers is highly dependent on the distributional gap between pre-training and fine-tuning datasets. As the divergence increases, more fine-tuning data is required to maintain classification performance. Consequently, existing methods struggle to achieve effective website identification tasks under severe concept drift with limited tuning data. To overcome these limitations, we propose a model parameter prediction approach, which adapts to new domains from data and model perspectives to enhance website identification performance. The proposed method predicts future model parameters to mitigate the effects of distributional changes, effectively adapting to evolving network environments. Experimental results demonstrate that our approach achieves significant improvements in accuracy, particularly under scenarios with limited tuning data and substantial concept drift.

关键词： Adaptation models Accuracy Concept drift Predictive models Fingerprint recognition Feature extraction Data models Robustness Long short term memory Tuning

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Competitive Multiobjective Multitasking: One-Pass Optimization of Heterogeneous Pareto Solutions

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Li, Yanchi Wu, Xinyi Gong, Wenyin Xu, Meng Wang, Yubo Gu, Qiong China University of Geosciences School of Computer Wuhan430074 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Hubei University of Arts and Science School of Computer Engineering Xiangyang441053 China Hubei University of Arts and Science Hubei Key Laboratory of Power System Design and Test for Electrical Vehicle Xiangyang441053 China

Competitive multiobjective multitask optimization (CMO-MTO) problems involve multiple tasks with comparable objectives but heterogeneous decision variables. The final Pareto front in CMO-MTO consists of multiple subsets corresponding to different tasks. Since the Pareto front subset of one task may be dominated by that of another, competition arises among tasks. Additionally, there may be exploitable similarities among tasks that evolutionary multitasking methods can leverage. For a comprehensive study of CMO-MTO, we construct 12 benchmark CMO-MTO problems with varied competitive relationships and inter-task similarities. To effectively solve CMO-MTO problems, we propose a reference vector contribution-based multitask evolutionary algorithm (RVC-MTEA). RVC-MTEA facilitates both global and local knowledge transfer based on vector contributions and integrates global archives to gather non-dominated solutions across multiple competitive tasks. Comparative results with four popular single-task and six state-of-the-art multitask evolutionary algorithms demonstrate the efficacy of RVC-MTEA. Finally, we apply RVC-MTEA to several real-world applications, showcasing the potential of CMO-MTO in practical decision-making scenarios. © 1997-2012 IEEE.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

DeepCell: Multiview Representation Learning for Post-Mapping Netlists

arXiv

引用

arXiv 2025年

作者： Shi, Zhengyuan Ma, Chengyu Zheng, Ziyang Zhou, Lingfeng Pan, Hongyang Jiang, Wentao Yang, Fan Yang, Xiaoyan Chu, Zhufei Xu, Qiang Department of Computer Science and Engineering The Chinese University of Hong Kong Sha Tin Hong Kong Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China School of Computer Science Hangzhou Dianzi University Hangzhou China School of Microelectronics State Key Laboratory of Integrated Chips and System Fudan University Shanghai China National Center of Technology Innovation for EDA Nanjing China

Representation learning for post-mapping (PM) netlists is a critical challenge in Electronic Design Automation (EDA), driven by the diverse and complex nature of modern circuit designs. Existing approaches focus on intermediate representations like And-Inverter Graphs (AIGs), limiting their applicability to post-synthesis stages. We introduce DeepCell, a multiview representation learning framework that integrates structural and functional insights from both PM netlists and AIGs to learn rich, generalizable embeddings. At its core, DeepCell employs the novel Mask Circuit Modeling (MCM) mechanism, which refines PM netlist representations in a self-supervised manner using pretrained AIG encoders. DeepCell sets a new benchmark in PM netlist representation, outperforming existing methods in predictive accuracy and reconstruction fidelity. To validate its efficacy, we apply DeepCell to functional engineering Change Orders (ECO), achieving significant reductions in patch generation costs and runtime while improving patch quality. Copyright © 2025, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

PMU-Timescale Topology Identification of Sub-station Node-Breaker Models using Deep Learning

PMU-Timescale Topology Identification of Sub-station Node-Br...

引用

IEEE General Meeting Power& Energy Society

作者： Behrouz Azimian Anamitra Pal Backer Abu-Jaradeh Lang Chen Penn Markham School of Electrical Computer and Energy Engineering Arizona State University Tempe AZ USA Engineering Department Electric Power Group Pasadena CA USA System Operations Engineering Dominion Energy Richmond VA USA

In an actual power system, the bus-branch model used in a state estimator is usually derived from the substation nodebreaker model. Therefore, incorrect topology information in the substation node-breaker model will cause the state estimation results to deteriorate. This paper presents a bus-branch topology identification framework for substation node-breaker models. The proposed method employs phasor measurement unit (PMU) data to identify the intra-substation connectivity at very high speeds. PMU data from Dominion Energy, a power utility in the U.S., is used to validate and test the proposed topology identification framework on the IEEE 30-bus system. The results demonstrate the applicability of the proposed framework for different cases in which varying levels of measurement noise are present under partial system observability provided by PMUs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Operation of an Integrated Electricity-heat Energy system Considering Flexible Resources Dispatch for Renewable Integration

引用

Journal of Modern Power systems and Clean Energy 2021年第4期9卷 699-710页

作者： Wei Wang Shuhao Huang Guangming Zhang Jizhen Liu Zhe Chen State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power UniversityBeijing 102206China School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China Department of Energy Technology Aalborg University9220 AalborgDenmark

Large fluctuations may occur on the energy supply and the load sides when large-scale renewable energies are integrated,leading to great challenges in power *** renewable power curtailment is especially numerous in the integrated electricity-heat energy system(IEHES)on account of electricity-heat *** flexible resources(FRs)on both the energy supply and load sides are introduced into the optimal dispatch of the IEHES and further modeled to alleviate the renewable fluctuations in this *** the energy supply side,three kinds of FRs based on electricity-heat coordination are modeled and *** the load side,the shiftable electricity demand resource is *** this basis,the solution for FRs participating in IEHES dispatch is given,with goals of maximizing the renewable penetration ratio and lowering operation *** scenarios are performed,and the results indicate that the proposed optimal dispatch strategy can effectively reduce the renewable energy curtailment and improve the flexibility of the *** contribution degrees of different FRs for renewable integration are also explored.

关键词： Integrated electricity-heat energy system(IEHES) renewable penetration flexible resource(FR) electricity-heat coordination shiftable demand load

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：