检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Mao, Junzhu Shen, Yang Guo, Jinyang Yao, Yazhou Hua, Xiansheng School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China State Key Laboratory of Software Development Environment Institute of Artificial Intelligence Beihang University Beijing100191 China Terminus Group Beijing100027 China

Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token compression method called Prune and Merge. Our approach integrates token pruning and merging operations within transformer models to achieve layer-wise token compression. By introducing trainable merge and reconstruct matrices and utilizing shortcut connections, we efficiently merge tokens while preserving important information and enabling the restoration of pruned tokens. Additionally, we introduce a novel gradient-weighted attention scoring mechanism that computes token importance scores during the training phase, eliminating the need for separate computations during inference and enhancing compression efficiency. We also leverage gradient information to capture the global impact of tokens and automatically identify optimal compression structures. Extensive experiments on the ImageNet-1k and ADE20K datasets validate the effectiveness of our approach, achieving significant speed-ups with minimal accuracy degradation compared to state-of-the-art methods. For instance, on DeiT-Small, we achieve a 1.64× speed-up with only a 0.2% drop in accuracy on ImageNet-1k. Moreover, by compressing segmenter models and comparing with existing methods, we demonstrate the superior performance of our approach in terms of efficiency and effectiveness. Code and models have been made available at https://***/ NUST-Machine-Intelligence-Laboratory/prune_and_merge. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Potential Indicator for Continuous Emotion Arousal by Dynamic Neural Synchrony

Potential Indicator for Continuous Emotion Arousal by Dyna...

引用

4th International Workshop on Human Brain and Artificial Intelligence, HBAI 2024

作者： Pan, Guandong Wu, Zhaobang Yang, Yaqian Wang, Xin Liu, Longzhao Zheng, Zhiming Tang, Shaoting School of Computer Science and Engineering Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Key Laboratory of Mathematics Informatics and Behavioral Semantics Beihang University Beijing100191 China Institute of Medical Artificial Intelligence Binzhou Medical University Yantai264003 China Zhongguancun Laboratory Beijing100094 China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang University Beijing100191 China PengCheng Laboratory Shenzhen518055 China State Key Lab of Software Development Environment Beihang University Beijing100191 China

ISBN: (纸本)9789819640003

The need for automatic and high-quality emotion annotation is paramount in applications such as continuous emotion recognition and video highlight detection, yet achieving this through manual human annotations is challenging. Inspired by inter-subject correlation (ISC) utilized in neuroscience, this study introduces a novel Electroencephalography (EEG) based ISC methodology that leverages a single-electrode and feature-based dynamic approach. Our contributions are three folds: Firstly, we reidentify two potent emotion features suitable for classifying emotions-first-order difference (FD) an differential entropy (DE). Secondly, through the use of overall correlation analysis, we demonstrate the heterogeneous synchronized performance of electrodes. This performance aligns with neural emotion patterns established in prior studies, thus validating the effectiveness of our approach. Thirdly, by employing a sliding window correlation technique, we showcase the significant consistency of dynamic ISCs across various features or key electrodes in each analyzed film clip. Our findings indicate the method’s reliability in capturing consistent, dynamic shared neural synchrony among individuals, triggered by evocative film stimuli. This underscores the potential of our approach to serve as an indicator of continuous human emotion arousal. The implications of this research are significant for advancements in affective computing and the broader neuroscience field, suggesting a streamlined and effective tool for emotion analysis in real-world applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electroencephalography (EEG) Emotion Annotation Inter-subject Correlation

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Backoff Hierarchical Clustering Algorithms for Multi-Hop Wireless Sensor Networks

引用

Journal of Computer Science & Technology 2011年第2期26卷 283-291页

作者：王珺曹涌涛谢俊元陈世福 State Key Lab for Novel Software Technology at Nanjing University Department of Computer Science and Technology Nanjing University Institute of Communication and Information Engineering Nanjing University of Posts and Telecommunications China Development Center Trend Micro Corp.

Compared with flat routing protocols, clustering is a fundamental performance improvement technique in wireless sensor networks, which can increase network scalability and lifetime. In this paper, we integrate the multi-hop technique with a backoff-based clustering algorithm to organize sensors. By using an adaptive backoff strategy, the algorithm not only realizes load balance among sensor node, but also achieves fairly uniform cluster head distribution across the network. Simulation results also demonstrate our algorithm is more energy-efficient than classical ones. Our algorithm is also easily extended to generate a hierarchy of cluster heads to obtain better network management and energy-efficiency.

关键词： multi-hop wireless sensor network clustering algorithm backoff strategy

来源：评论

学校读者我要写书评

暂无评论

Peer priority based data scheduling algorithm in P2P streaming system

引用

High Technology Letters 2013年第2期19卷 208-213页

作者：任浩 Wang Jinlin You Jiali National Network New Media Engineering Research Center Institute of AcousticsChinese Academy of Sciences Graduate University of Chinese Academy of Sciences State Nuclear Power Software Development Center

In order to solve the problem that the existing data scheduling algorithm cannot make full use of neighbors' bandwidth resources when allocating data request among several senders in the multisender based P2P streaming system,a peer priority based scheduling algorithm is *** algorithm calculates neighbors' priority based on peers' historical service evaluation as well as how many wanted data that the neighbor *** data request allocated to each neighbor is adjusted dynamically according to the priority when *** with high priority are preferred to allocate more data *** shows the algorithm can make full use of neighbors' bandwidth resources to transmit data to reduce server pressure effectively and improve system scalability.

关键词： peer-to-peer (P2P) streaming data scheduling priority request allocation

来源：评论

学校读者我要写书评

暂无评论

Ethical Principles and Governance Technology development of AI in China

引用

engineering 2020年第3期6卷 302-309页

作者： Wenjun Wu Tiejun Huang Ke Gong State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China School of Electronics Engineering and Computer Science Peking UniversityBeijing 100871China Chinese Institute of New Generation Artificial Intelligence Development Strategie Nankai UniversityTianjin 300071China

Ethics and governance are vital to the healthy and sustainable development of artificial intelligence(AI).With the long-term goal of keeping AI beneficial to human society,governments,research organizations,and companies in China have published ethical guidelines and principles for AI,and have launched projects to develop AI governance *** paper presents a survey of these efforts and highlights the preliminary outcomes in *** also describes the major research challenges in AI governance research and discusses future research directions.

关键词： AI ethical principles AI governance technology Machine learning Privacy Safety Fairness

来源：评论

学校读者我要写书评

暂无评论

An intelligent cyber-physical system based-consensus algorithm for sustainable edge service provisioning in 6G-based IIoT applications

引用

Cyber-Physical Systems 2025年

作者： Byeon, Haewon Jena, Soumya Ranjan Bhargavi, Kovvuri N. Ramesh, Janjhyam Venkata Naga Bozarboyevich, Abdullayev Abror Soni, Mukesh Shabaz, Mohammad Department of AI and Software Inje University Gimhae Korea Republic of NextGen University International United States School of Computing and Artificial Intelligence NIMS University Jaipur India Department of CSE Aditya University Surampalem India Department of CSE Graphic Era Hill University Dehradun India Department of CSE Graphic Era Deemed To Be University Uttarakhand Dehradun India The Department of Financial Analysis Tashkent State University of Economics Tashkent Uzbekistan Division of Research and Development Lovely Professional University Phagwara India Dr. D. Y. Patil School of Science & Technology Tathawade Pune India Model Institute of Engineering and Technology Jammu India

This paper proposes a credit-driven practical byzantine fault tolerance based on a consensus algorithm for sustainable 6G communication to address the potential threat of malicious activity in green and sustainable 6G-based Industrial Internet of Things (IIoT) applications. The dual-layer architecture allows for simultaneous verification of transactions and the execution of read-write operations. According to simulation studies, CD-PBFT enhances algorithm performance and stability while efficiently reducing validation time. Empirical findings demonstrate that CD-PBFT achieves both efficiency and security fault tolerance by reducing network transaction latency by an average of 34.8% and increasing throughput by 25.2% compared to PBFT. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

User-level failure detection and auto-recovery of parallel programs in HPC systems

引用

Frontiers of Computer Science 2021年第6期15卷 31-42页

作者： Guozhen ZHANG Yi LIU Hailong YANG Jun XU Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China Sino-German Joint Software Institute Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing 100854China

As the mean-time-between-failures(MTBF)continues to decline with the increasing number of components on large-scale high performance computing(HPC)systems,program failures might occur during the execution period with high *** successful execution of the HPC programs has become an issue that the unprivileged users should be *** the user perspective,if the program failure cannot be detected and handled in time,it would waste resources and delay the progress of program ***,the unprivileged users are unable to perform program state checking due to execution control by the job management system as well as the limited ***,automated tools for supporting user-level failure detection and autorecovery of parallel programs in HPC systems are *** paper proposes an innovative method for the unprivileged user to achieve failure detection of job execution and automatic resubmission of failed *** state checker in our method is encapsulated as an independent job to reduce interference with the user *** addition,we propose a dual-checker mechanism to improve the robustness of our *** implement the proposed method as a tool named automatic re-launcher(ARL)and evaluate it on the Tianhe-2 *** results show that ARL can detect the execution failures effectively on Tianhe-2 *** addition,the communication and performance overhead caused by ARL is *** good scalability of ARL makes it applicable for large-scale HPC systems.

关键词： high performance computing parallel program failure detection failure auto-recovery

来源：评论

学校读者我要写书评

暂无评论

Robust and Scalable P2P Live Streaming

引用

Journal of Donghua University(English Edition) 2009年第5期26卷 482-488页

作者：陈锬熊馨 State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeijing University of Aeronautics and Astronautics College of Computer Sciences Beijing University of Technology College of Computer and Communication Engineering Zhengzhou Institute of Light Industry

Distributing real-time video stream in large scale group communication over Interuet poses several challenging problems due to the complex network dynamics, stringent requirement of delay and loss. This paper proposes a novel peer-to-peer scheme, named TeamCast, to combat with these issues. Constructing multiple diverse application layer multicast （ALM） trees to transmit multiple independent complementary descriptions produced by multiple description coding （MDC） simultaneously, TeamCast improves error resilient ability in the presence of various levels of packet loss caused by unpredictable congestion of Internet and node failure, as well as enlarges system capacity. The results of extensive simulations indicate that TeamCast achieves low latency, scalability, and fault tolerance for the delivery of live media stream.

关键词： path diversity multiple description coding application layer multicast media streaming topologyuware

来源：评论

学校读者我要写书评

暂无评论

A Novel Machine Learning Approach to Delay Efficient Offloading Strategy for Mobile Edge Computing 1st

A Novel Machine Learning Approach to Delay Efficient Offload...

引用

1st International Conference on Microelectronics, Communication Systems, Machine Learning, and Internet of Things, MCMI 2020

作者： Bharti, Piyush Chaudhary, Srishti Snigdh, Itu Department of Computer Science and Engineering Birla Institute of Technology Mesra India Software Development Microland Limited Bengaluru India

ISBN: (纸本)9789811919053

There have been studies on the problems experienced in offloading. But, how to leverage machine learning for resource-efficient computation offloading is not completely explored yet. We present this paper with the motivation to leverage machine learning and backward induction to suggest a method for the resource-efficient computation offloading in IoT devices. In particular, we use machine learning to predict the most efficient device to which a task should be offloaded through the use of a two-model machine learning system deployed in the edge cloud itself, since most high power IoT devices are fixed in their positions and display a certain pattern in their CPU utilization data. This is followed by using backward induction to determine the optimal execution location for each task component. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： computation offloading

来源：评论

学校读者我要写书评

暂无评论

A novel framework for improving recommender diversity

A novel framework for improving recommender diversity

引用

2013 International Workshop on Behavior and Social Informatics and Computing, BSIC 2013

作者： Chen, Jinpeng Liu, Yu Hu, Jun He, Wei Li, Deyi State Key Laboratory of Software Development Environment Bei Hang University China Institute of Electronic System Engineering China

ISBN: (纸本)9783319040479

Recommender systems are being used to assist users in finding relevant items from a large set of alternatives in many online applications. However, while most research up to this point has focused on improving the accuracy of recommender systems, other important aspects of recommendation quality, such as the diversity of recommendations, have often been overlooked. In this paper, we present a novel recommendation framework, designed to balance and diversify personalized top-N recommendation lists in order to capture the user's complete spectrum of interests. Systematic experiments on the real-world rating data set have demonstrated the effectiveness of our proposed framework in learning both accuracy and diversity of recommendations. © Springer International Publishing Switzerland 2013.

关键词： Collaborative filtering

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：