检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Bar, Yarin Shaer, Shalev Romano, Yaniv Department of Computer Science Technion-Israel Institute of Technology Israel Department of Electrical and Computer Engineering Technion-Israel Institute of Technology Israel

We present a novel approach for test-time adaptation via online self-training, consisting of two components. First, we introduce a statistical framework that detects distribution shifts in the classifier's entropy values obtained on a stream of unlabeled samples. Second, we devise an online adaptation mechanism that utilizes the evidence of distribution shifts captured by the detection tool to dynamically update the classifier's parameters. The resulting adaptation process drives the distribution of test entropy values obtained from the self-trained classifier to match those of the source domain, building invariance to distribution shifts. This approach departs from the conventional self-training method, which focuses on minimizing the classifier's entropy. Our approach combines concepts in betting martingales and online learning to form a detection tool capable of quickly reacting to distribution shifts. We then reveal a tight relation between our adaptation scheme and optimal transport, which forms the basis of our novel self-supervised loss. Experimental results demonstrate that our approach improves test-time accuracy under distribution shifts while maintaining accuracy and calibration in their absence, outperforming leading entropy minimization methods across various scenarios. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Integrated Method for Healthcare Data Classification with Incompleteness

引用

computers, Materials & Continua 2024年第11期81卷 3125-3145页

作者： Sonia Goel Meena Tushir Jyoti Arora Tripti Sharma Deepali Gupta Ali Nauman Ghulam Muhammad Electrical and Electronics Engineering(EEE)Department Maharaja Surajmal Institute of TechnologyNew-Delhi110058India Information Technology(IT)Department Maharaja Surajmal Institute of TechnologyNew-Delhi110058India Chitkara University Institute of Engineering and Technology Chitkara UniversityRajpuraPunjab140401India Department of Computer Science and Engineering Yeungnam UniversityGyeongsan-si38541Republic of Korea Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11421Saudi Arabia

In numerous real-world healthcare applications,handling incomplete medical data poses significant challenges for missing value imputation and subsequent clustering or classification *** approaches often rely on statistical methods for imputation,which may yield suboptimal results and be computationally *** paper aims to integrate imputation and clustering techniques to enhance the classification of incomplete medical data with improved *** classification methods are ill-suited for incomplete medical *** enhance efficiency without compromising accuracy,this paper introduces a novel approach that combines imputation and clustering for the classification of incomplete ***,the linear interpolation imputation method alongside an iterative Fuzzy c-means clustering method is applied and followed by a classification *** effectiveness of the proposed approach is evaluated using multiple performance metrics,including accuracy,precision,specificity,and *** encouraging results demonstrate that our proposed method surpasses classical approaches across various performance criteria.

关键词： Incomplete data nearest neighbor linear interpolation imputation clustering classification

来源：评论

学校读者我要写书评

暂无评论

Beamforming Design for Dynamic Metasurface Antennas-Based Massive Multiuser MISO Downlink Systems

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the Communications Society 2024年 5卷 1387-1398页

作者： Chen, Jung-Chieh Hsu, Chiu-Hsiang National Cheng Kung University Department of Electrical Engineering Tainan701401 Taiwan Institute of Computer and Communication Engineering National Cheng Kung University Tainan701401 Taiwan

This study addresses a massive multiuser multiple-input single-output downlink system with a base station equipped with dynamic metasurface antennas (DMAs) serving single-antenna users. Our goal is to jointly optimize the transmit precoder and configurable DMA coefficients to maximize system performance. This task is challenging due to the complex interdependencies between these parameters. The established solution, AO-RMO, employs alternating optimization (AO) to iteratively optimize the transmit precoder using the weighted minimum mean squared error algorithm and Riemannian manifold optimization (RMO) for the DMA coefficients. While AO-RMO performs reasonably well, it exhibits high time and computational complexity due to RMO. To address this issue, we propose a computationally efficient alternative: a projected gradient descent (PGD)-based algorithm for determining the DMA coefficients. Additionally, for practical reconfiguration of DMA coefficients with discrete values, we introduce the cross-entropy optimization (CEO)-based algorithm. Simulation results demonstrate that when continuous DMA coefficients are used, our proposed AO-PGD algorithm achieves nearly comparable weighted sum rate performance to the AO-RMO algorithm but with significantly reduced computational complexity and running time. When discrete DMA coefficients are applied, the proposed AO-CEO algorithm surpasses other benchmark algorithms in various system configurations. © 2020 IEEE.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation via Face Morphing for Recognizing Intensities of Facial Emotions

引用

IEEE Transactions on Affective Computing 2023年第2期14卷 1228-1235页

作者： Huang, Tsung-Ren Hsu, Shin-Min Fu, Li-Chen National Taiwan University Department of Psychology Center for Artificial Intelligence & Advanced Robotics Taipei106319 Taiwan National Taiwan University Center for Artificial Intelligence & Advanced Robotics Department of Electrical Engineering Department of Computer Science and Information Engineering Taipei106319 Taiwan

Being able to recognize emotional intensity is a desirable feature for a facial emotional recognition (FER) system. However, the development of such a feature is hindered by the paucity of intensity-labeled data for model training. To ameliorate the situation, the present study proposes using face morphing as a novel way of data augmentation to synthesize faces that express different degrees of a designated emotion. Such an approach has been successfully validated on humans and machines. Specifically, humans indeed perceived different levels of intensified emotions in these parametrically synthesized faces, and FER systems based on neural networks indeed showed improved sensitivities to intensities of different emotions when additionally trained on the synthesized faces. Overall, the proposed data augmentation method is not only simple and effective but also useful for building FER systems that recognize facial expressions of mixed emotions. © 2010-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Balancing Memorization and Generalization in RNNs for High Performance Brain-Machine Interfaces 37

Balancing Memorization and Generalization in RNNs for High P...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Costello, Joseph T. Temmar, Hisham Cubillos, Luis H. Mender, Matthew J. Wallace, Dylan M. Willsey, Matthew S. Patil, Parag G. Chestek, Cynthia A. Department of Electrical and Computer Engineering Biomedical Engineering Robotics and Neurosurgery University of Michigan Ann ArborMI United States

ISBN: (纸本)9781713899921

Brain-machine interfaces (BMIs) can restore motor function to people with paralysis but are currently limited by the accuracy of real-time decoding algorithms. Recurrent neural networks (RNNs) using modern training techniques have shown promise in accurately predicting movements from neural signals but have yet to be rigorously evaluated against other decoding algorithms in a closed-loop setting. Here we compared RNNs to other neural network architectures in real-time, continuous decoding of finger movements using intracortical signals from nonhuman primates. Across one and two finger online tasks, LSTMs (a type of RNN) outperformed convolutional and transformer-based neural networks, averaging 18% higher throughput than the convolution network. On simplified tasks with a reduced movement set, RNN decoders were allowed to memorize movement patterns and matched able-bodied control. Performance gradually dropped as the number of distinct movements increased but did not go below fully continuous decoder performance. Finally, in a two-finger task where one degree-of-freedom had poor input signals, we recovered functional control using RNNs trained to act both like a movement classifier and continuous decoder. Our results suggest that RNNs can enable functional real-time BMI control by learning and generating accurate movement patterns. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Mammals

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Lightweight Certificateless Authenticated Key Agreement Protocol for V2V Communications in IoV

引用

IEEE Internet of Things Journal 2024年第16期11卷 27744-27759页

作者： Lin, Hui-Tang Jhuang, Wei-Li National Cheng Kung University Institute of Computer and Communication Engineering The Department of Electrical Engineering Tainan City701 Taiwan Silicon Motion Technology Corporation Zhubei Taiwan

With the emergence of the Internet of Things, traditional vehicular ad hoc networks have evolved into the more sophisticated Internet of Vehicles (IoV). IoV is expected to play a key role in the development of future smart cities and intelligent transportation systems. However, like most information technology systems, IoV is vulnerable to the cyberattack. A hacker may gain control over a vehicle, thereby posing serious danger to the vehicle occupants, surrounding vehicles and pedestrians. Consequently, improving the security of IoV is essential in ensuring its future success. Among the various security concerns surrounding IoV, secure communications and authentication are two of the most critical. Currently, most proposed works suffers the single-point-of-failure (SPOF) problem and the trusted third party (TTP) compromise issue. To address these issues, the present study proposes a secure key generation mechanism which leverages the advantages of blockchain technology and certificateless public-key cryptography. In the proposed method, the distributed architecture of blockchain is exploited to realize a decentralized TTP service to prevent the SPOF problem and the TTP compromise issue. In addition, an authenticated key agreement (AKA) protocol based on the legal key pairs is proposed to facilitate efficient mutual authentication and session key agreement between the vehicles. The security analysis results show that the proposed schemes have excellent resistance to the typical TTP issues. Moreover, the feasibility of the proposed AKA protocol is demonstrated through the extended Canetti-Krawczyk model. Finally, the performance analysis results show that the proposed scheme yields a significant reduction in the computational cost compared to the existing AKA protocols. © 2014 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Investigation on compressed air energy storage system for efficient utilisation of renewable power sources

引用

International Journal of Power and Energy Conversion 2024年第3期15卷 281-293页

作者： Karthika, J. Annamalai, T. Kumar, P. Veera Sanjeeva Olana, Firew Dereje Rasu, N. Govindha Department of Electrical and Electronics Engineering Sri Krishna College of Engineering and Technology Kuniamuthur Coimbatore641008 India Department of Electrical and Electronics Engineering Sri Venkateswara College of Engineering Tamil Nadu Sriperumbudur602117 India Department of Mechanical Engineering Annamacharya Institute of Technology and Sciences Andhra Pradesh Rajampet516126 India Department of Electrical and Computer Engineering Mattu University Post-318 Mattu Ethiopia School of Mechanical Engineering Vellore Institute of Technology Vellore India

In recent years, emerging nations have shifted their focus to renewable energy sources for electricity production. This shift has happened in both industrialised and underdeveloped countries. The percentage of electricity produced overall in most developed countries that originates from renewable sources of energy is rising significantly. Currently, the grid is going through a number of modifications to improve its intelligence and stability. These adjustments are becoming more pronounced. Although there are many various types of storage systems available, the CAES system is the most appropriate for large-capacity storage that is ideal for grid integration. However, the overall roundtrip efficiency is less than that of a pumped hydro storage system when it comes to large-scale renewable energy storage. © 2024 Inderscience Enterprises Ltd.

关键词： Compressors

来源：评论

学校读者我要写书评

暂无评论

Ethical hacking for IoT: Security issues, challenges, solutions and recommendations

引用

Internet of Things and Cyber-Physical Systems 2023年第1期3卷 280-308页

作者： Yaacoub, Jean-Paul A. Noura, Hassan N. Salman, Ola Chehab, Ali FEMTO-ST Institute CNRS Belfort France American University of Beirut Department of Electrical and Computer Engineering Lebanon

In recent years, attacks against various Internet-of-Things systems, networks, servers, devices, and applications witnessed a sharp increase, especially with the presence of 35.82 billion IoT devices since 2021;a number that could reach up to 75.44 billion by 2025. As a result, security-related attacks against the IoT domain are expected to increase further and their impact risks to seriously affect the underlying IoT systems, networks, devices, and applications. The adoption of standard security (counter) measures is not always effective, especially with the presence of resource-constrained IoT devices. Hence, there is a need to conduct penetration testing at the level of IoT systems. However, the main issue is the fact that IoT consists of a large variety of IoT devices, firmware, hardware, software, application/web-servers, networks, and communication protocols. Therefore, to reduce the effect of these attacks on IoT systems, periodic penetration testing and ethical hacking simulations are highly recommended at different levels (end-devices, infrastructure, and users) for IoT, and can be considered as a suitable solution. Therefore, the focus of this paper is to explain, analyze and assess both technical and non-technical aspects of security vulnerabilities within IoT systems via ethical hacking methods and tools. This would offer practical security solutions that can be adopted based on the assessed risks. This process can be considered as a simulated attack(s) with the goal of identifying any exploitable vulnerability or/and a security gap in any IoT entity (end devices, gateway, or servers) or firmware. © 2023 The Authors

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Demographic and Operational Variables on 1-to-Many Face ID Search

IEEE Transactions on Technology and Society

引用

IEEE Transactions on Technology and Society 2024年第2期5卷 217-230页

作者： Pangelinan, Gabriella Bhatta, Aman Wu, Haiyu King, Michael C. Bowyer, Kevin W. Florida Institute of Technology Department of Electrical Engineering and Computer Science MelbourneFL32901 United States University of Notre Dame Department of Computer Science and Engineering Notre DameIN46556 United States

Concerns related to the proliferation of automated face recognition technology with the intent of solving or preventing crimes continue to mount. The technology being implicated in wrongful arrest following 1-to-many face identification has heightened scrutiny in the media and spawned lawsuits. We analyze the accuracy of 1-to-many face identification across African-American and Caucasian demographic groups and in the presence of blur and reduced resolution in the probe image, as might occur in "surveillance camera quality"images. Because of the high accuracy of modern face recognition algorithms with "government ID quality"images and the size of available datasets, we use the following indirect metrics to assess the relative propensity for false positive identifications: (1) the traditional d-prime statistic between mated and non-mated score distributions, (2) absolute score difference between thresholds in the high-similarity tail of the non-mated distribution and the low-similarity tail of the mated distribution, and (3) distribution of (mated - non-mated rank-one scores) across the set of probe images. We find that demographic variation patterns in 1-to-many accuracy largely, but not perfectly, follow that observed in 1-to-1 accuracy. We show that, different from the case with 1-to-1 matching accuracy, demographic comparison of 1-to-many accuracy can be affected by different numbers of identities and images across demographics. We also show that increased blur or reduced resolution of the face in the probe image can significantly increase the false positive identification rate. This point is important because the reputation of modern face recognition algorithms for high accuracy in 1-to-many face identification comes from statistics based on analyzing "government ID quality"rather than "surveillance camera quality"images. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Defense for Advanced Persistent Threat with Inadvertent and Malicious Insider Threats

引用

无人系统（英文） 2024年第2期12卷 341-358页

作者： Ziqin Chen Guanpu Chen Yiguang Hong Department of Control Science and Engineering and Shanghai Research Institute for Intelligent Autonomous Systems Tongji UniversityShanghaiP.R.China School of Electrical Engineering and Computer Science KTH Royal Institute of TechnologyStockholmSweden

In this paper,we propose a game theory framework to solve advanced persistent threat problems,especially considering two types of insider threats:malicious and *** this framework,we establish a unified three-player game model and derive Nash equilibria in response to different types of insider *** analyzing these Nash equilibria,we provide quantitative solutions to advanced persistent threat problems pertaining to insider ***,we have conducted a comparative assessment of the optimal defense strategy and corresponding defender's costs between two types of insider ***,our findings advocate a more proactive defense strategy against inadvertent insider threats in contrast to malicious ones,despite the latter imposing a higher burden on the *** theoretical results are substantiated by numerical results,which additionally include a detailed exploration of the conditions under which different insiders adopt risky *** conditions can serve as guiding indicators for the defender when calibrating their monitoring intensities and devising defensive strategies.

关键词： Security game advanced persistent threat insider threats Nash equilibrium

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：