检索结果-内蒙古大学图书馆

computing Innovation, Intelligence, Technologies and Education (CIITE), International Conference on

作者： Mu Heng He Chean Khim Toa School of Computing and Data Science Xiamen University Malaysia Selangor Malaysia

ISBN: (数字)9798350377286

ISBN: (纸本)9798350377293

This review article aims to provide a comprehensive overview of sensor-based gait recognition systems, exploring different sensor types, data processing methods, and modeling algorithms. Gait analysis enables the recognition and analysis of individual gait characteristics by collecting biometric data (e.g., acceleration, angular velocity, and posture information) generated during human movement. In this way, it is applied in areas such as safety verification, health monitoring, and fall detection for the elderly. This paper also explores the diversity of gait patterns, the impact of environmental factors on gait analysis, and technical challenges in data capture and analysis, and proposes future technological innovations and research directions.

关键词： Deep learning Technological innovation Reviews data processing Environmental factors data models Older adults Fall detection Gait recognition Monitoring

来源：评论

学校读者我要写书评

暂无评论

EdgeMove: Pipelining Device-Edge Model Training for Mobile Intelligence 23

EdgeMove: Pipelining Device-Edge Model Training for Mobile I...

引用

32nd ACM World Wide Web Conference, WWW 2023

作者： Dong, Zeqian He, Qiang Chen, Feifei Jin, Hai Gu, Tao Yang, Yun School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computing Technologies Swinburne University of Technology Australia School of Information Technology Deakin University Australia School of Computing Macquarie University Australia National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450394161

Training machine learning (ML) models on mobile and Web-of-Things (WoT) has been widely acknowledged and employed as a promising solution to privacy-preserving ML. However, these end-devices often suffer from constrained resources and fail to accommodate increasingly large ML models that crave great computation power. Offloading ML models partially to the cloud for training strikes a trade-off between privacy preservation and resource requirements. However, device-cloud training creates communication overheads that delay model training tremendously. This paper presents EdgeMove, the first device-edge training scheme that enables fast pipelined model training across edge devices and edge servers. It employs probing-based mechanisms to tackle the new challenges raised by device-edge training. Before training begins, it probes nearby edge servers' training performance and bootstraps model training by constructing a training pipeline with an approximate model partitioning. During the training process, EdgeMove accommodates user mobility and system dynamics by probing nearby edge servers' training performance adaptively and adapting the training pipeline proactively. Extensive experiments are conducted with two popular DNN models trained on four datasets for three ML tasks. The results demonstrate that EdgeMove achieves a 1.3 × -2.1 × speedup over the state-of-the-art scheme. © 2023 ACM.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Exploring the Risk Posed by Adversarial Attacks on Face Recognition with CNN

Exploring the Risk Posed by Adversarial Attacks on Face Reco...

引用

computing Innovation, Intelligence, Technologies and Education (CIITE), International Conference on

作者： Zixuan Zhu Saif Kifah School of Computing and Data Science Xiamen University Malaysia Sepang Malaysia

ISBN: (数字)9798350377286

ISBN: (纸本)9798350377293

Face recognition models are gaining rising attention, especially CNN-based models. They are employed in multiple applications, such as security and surveillance. However, those models are vulnerable to adversarial attacks. This study investigates some adversarial attack strategies to evaluate the capability of the CNN-based face recognition models against adversarial attacks. In addition, some attack methods are employed in the same model to assess the abilities of those adversarial attack methods. Two CNN-based face recognition models are trained to test model accuracy and loss. Then, two adversarial attack methods are applied to attack the models. The first attack method is the Fast Gradient Sign Method (FGSM). As for the second attack method, it is the Random Gradient Method (RGM). This study demonstrates that ArcFace and CosFace models are vulnerable to Adversarial Attacks. Furthermore, the FGSM method has a better attack success rate in comparison with RGM to CNN-based face recognition models.

关键词： Technological innovation Gradient methods Accuracy Face recognition Computational modeling Surveillance Education Security

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multi-Objective Optimization Approach for Low-Interference UAV Communication Based on Collaborative Beamforming 10

Enhanced Multi-Objective Optimization Approach for Low-Inter...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Zhang, Chao Kang, Hui Sun, Geng Li, Jiahui Wang, Boxiong Xu, Bo Jilin University College of Computer Science and Technology Changchun130012 China Nanyang Technological University Singapore College of Computing and Data Science 639798 Singapore Hainan University College of Information and Communication Engineering Haikou570228 China

ISBN: (纸本)9798331520861

Unmanned aerial vehicles (UAVs) are widely used in the field of wireless communications due to their inherent advantages such as easy deployment and low cost. Employing collaborative beamforming techniques to form a UAV-based virtual antenna array (UVAA) is a promising solution to achieve remote and low-cost communications. Owing to the nature of electromagnetic waves, UVAA may cause interference to unaffiliated users when deployed in densely populated areas. To address this issue, UAVs must identify the most suitable positions to achieve optimal beam patterns. However, considering their limited energy capacity and the increased power consumption associated with excessive flight, a multi-objective optimization analysis is necessary to balance these factors. Thus, we formulate a low-interference communication multi-objective problem (LIMOP), aiming to maximize transmission rate, minimize interference, and reduce energy consumption through the optimization of UAV positions, excitation currents, and the selection of target BS. Given the complexity of LIMOP, we introduce multiple improvement strategies to propose an improved swarm intelligence method. According to simulation results, the proposed IMOAHA is effective in addressing the formulated LIMOP and is superior to other algorithms. © 2024 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure 10

Who Responded to Whom: The Joint Effects of Latent Topics an...

引用

10th SIGHAN Workshop on Chinese Language Processing, SIGHAN 2024

作者： Ji, Lu Chen, Lei Li, Jing Wei, Zhongyu Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University China School of Data Science Fudan University China Department of Computing The Hong Kong Polytechnic University Hong Kong Research Institute of Intelligent and Complex Systems Fudan University China

ISBN: (纸本)9798891761551

Vast amount of online conversations are produced on a daily basis, resulting in a pressing need to automatic conversation understanding. As a basis to structure a discussion, we identify the responding relations in the conversation discourse, which link response utterances to their initiations. To figure out who responded to whom, here we explore how the consistency of topic contents and dependency of discourse roles indicate such interactions, whereas most prior work ignore the effects of latent factors underlying word occurrences. We propose a neural model to learn latent topics and discourse in word distributions, and predict pairwise initiation-response links via exploiting topic consistency and discourse dependency. Experimental results on both English and Chinese conversations show that our model significantly outperforms the previous state of the arts. © 2024 Association for Computational Linguistics

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Diversified Batch Selection for Training Acceleration 41

Diversified Batch Selection for Training Acceleration

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hong, Feng Lyu, Yueming Yao, Jiangchao Zhang, Ya Tsang, Ivor W. Wang, Yanfeng Cooperative Medianet Innovation Center Shanghai Jiao Tong University Shanghai China Singapore Singapore Shanghai AI Laboratory Shanghai China College of Computing and Data Science NTU Singapore

The remarkable success of modern machine learning models on large datasets often demands extensive training time and resource consumption. To save cost, a prevalent research line, known as online batch selection, explores selecting informative subsets during the training process. Although recent efforts achieve advancements by measuring the impact of each sample on generalization, their reliance on additional reference models inherently limits their practical applications, when there are no such ideal models available. On the other hand, the vanilla reference-model-free methods involve independently scoring and selecting data in a sample-wise manner, which sacrifices the diversity and induces the redundancy. To tackle this dilemma, we propose Diversified Batch Selection (DivBS), which is reference-model-free and can efficiently select diverse and representative samples. Specifically, we define a novel selection objective that measures the group-wise orthogonalized representativeness to combat the redundancy issue of previous sample-wise criteria, and provide a principled selection-efficient realization. Extensive experiments across various tasks demonstrate the significant superiority of DivBS in the performance-speedup trade-off. The code is publicly available. Copyright 2024 by the author(s)

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Exploring the Role of Internet of Things in Wireless Sensor Networks for Industry 4.0 Applications 1

Exploring the Role of Internet of Things in Wireless Sensor ...

引用

1st International Conference on Pioneering Developments in Computer science and Digital Technologies, IC2SDT 2024

作者： Palarimath, Suresh Maran, Pyingkodi N.r, Wilfred Blessing Sujatha, T. Renuga, S. R.s, Chithra College of Computing and Information Sciences University of Technology and Applied Sciences Salalah Oman Kongu Engineering College Department of Computer Application Erode India College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Sri Krishna College of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India Panimalar Engineering College Department of Artificial Intelligence and Data Science Chennai India Ponjesly College of Engineering Department of Computer Science and Engineering Kanyakumari India

ISBN: (纸本)9798350365016

Recent developments in computer networking have made it possible to access information from a faraway location via either wireless or wired networks. The recent advancements in wireless infrastructure are directly responsible for the advent of wireless sensor networks, often known as WSNs. These networks make it easier to keep track of environmental happenings and activities, as well as document them and manage them. In WSNs, data relaying is accomplished through the use of a variety of routing strategies. Industry 4.0, also known as the fourth industrial revolution, is characterized by the incorporation of highly developed physical automation systems. These systems are made up of several pieces of machinery and gadgets that are linked together by sensors and are operated by software. The goal of the fourth industrial revolution is to improve the effectiveness and dependability of business processes. The Internet of Things (IoT) can be leveraged in manufacturing, which gives a means of linking engines, power grids, and sensors to the cloud in an industrial context. This is accomplished through the use of Industrial IoT. The purpose of this paper is to gain an understanding of how the Internet of Things functions in wireless sensor networks and its possible applications in a variety of settings. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Low-Rank Dynamic MRI Imaging Model Based on MC Penalty Function

引用

IAENG International Journal of Applied Mathematics 2024年第9期54卷 1840-1846页

作者： Luo, Zhijun Wang, Lirong Zhu, Zhibin Li, Yingying School of Mathematics and Finance Hunan University of Humanities Science and Technology Loudi417000 China School of Mathematics and Finance Hunan University of Humanities Science and Technology Loudi417000 China School of Mathematics and Computing Science The Guangxi Colleges and Universities Key Laboratory of Data Analysis and Computation Guilin University of Electronic Technology Guilin541004 China School of Mathematics and Finance Hunan University of Humanities Science and Technology Loudi417000 China

In the research of dynamic MRI imaging, we have utilized the minimax-concave (MC) function to replace the traditional nuclear norm, thereby significantly enhancing the model's fitting accuracy. The Total Variation (TV) duality technique is introduced to refine the model resolution further, better capturing underlying structures in MRI data. The splitting method is also employed to establish a comprehensive solution framework for the model. A high-efficiency algorithm, designed using the proximity operator, is developed to solve sub-problems within this framework, ensuring swift and accurate convergence. Numerical experiments on various dynamic MRI datasets and undersampling templates demonstrate that the new method outperforms traditional approaches in several key metrics, including CPU runtime, iteration count, and reconstruction performance. The new method reduces computational overhead, expedites the image reconstruction process, and significantly improves the quality of reconstructed images. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Local and Global Feature-Aware Dual-Branch Networks for Plant Disease Recognition

引用

植物表型组学（英文） 2024年第4期6卷 828-840页

作者： Jianwu Lin Xin Zhang Yongbin Qin Shengxian Yang Xingtian Wen Tomislav Cernava Quirico Migheli Xiaoyulong Chen Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University Guizhou Provincial Science and Technology DepartmentGuiyang 550025China Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University Guizhou Provincial Science and Technology DepartmentGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China School of Biological Sciences Faculty of Environmental and Life SciencesUniversity of SouthamptonSouthampton S017 1BJUK Dipartimento di Agraria and NRD-Nucleo di Ricerca sulla Desertificazione Università degli Studi di SassariSassariItaly Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University Guizhou Provincial Science and Technology DepartmentGuiyang 550025China College of Life Sciences Guizhou UniversityGuiyang 550025China

Accurate identification of plant diseases is important for ensuring the safety of agricultural *** neural networks(CNNs)and visual transformers(VTs)can extract effective representations of images and have been widely used for the intelligent recognition of plant disease ***,CNNs have excellent local perception with poor global perception,and VTs have excellent global perception with poor local *** makes it difficult to further improve the performance of both CNNs and VTs on plant disease recognition *** this paper,we propose a local and global feature-aware dual-branch network,named LGNet,for the identification of plant *** specifically,we first design a dual-branch structure based on CNNs and VTs to extract the local and global ***,an adaptive feature fusion(AFF)module is designed to fuse the local and global features,thus driving the model to dynamically perceive the weights of different ***,we design a hierarchical mixed-scale unit-guided feature fusion(HMUFF)module to mine the key information in the features at different levels and fuse the differentiated information among them,thereby enhancing the model's multiscale perception ***,extensive experiments were conducted on the Al Challenger 2018 dataset and the self-collected corn disease(SCD)*** experimental results demonstrate that our proposed LGNet achieves state-of-the-art recognition performance on both the Al Challenger 2018 dataset and the SCD dataset,with accuracies of 88.74％and 99.08％,respectively.

关键词： global plant disease dual-branch feature-aware local networks recognition

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinopathy Imaging: Network Exudate Detection to Classify Abnormalities

Diabetic Retinopathy Imaging: Network Exudate Detection to C...

引用

2023 Intelligent computing and Control for Engineering and Business Systems, ICCEBS 2023

作者： Chinnasamy, A. Selvakumari, P. School of Computing Srmist Department of Data Science and Business Systems kattankulathur campus Chennai India Chennai Institute of Technology Chennai Anna University Department of Computer Science and Engineering India

ISBN: (纸本)9798350394580

The DR becomes increasingly common, there is a need to automatically extract and classify disease severity. Due to diabetes problems, about 2% of people with this disease become completely blind, and DR complications make him 10% visually impaired if he has diabetes for 15 years. Furthermore, it plays an important role in the progression of blindness in middle-aged and older adults. If the disease is not recognized as soon as possible, patients can experience a severe stage of irreversible blindness. The shortage of ophthalmologists is a serious problem for the growing number of diabetic patients. Hard exudates must be found to screen and assist in disease monitoring and diagnosis. Therefore, Lloyd's clustering technique was used in this work. © 2023 IEEE.

关键词： Cat Swarm Optimization Diabetes Mellitus Diabetic Retinopathy Mean Squared Error

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：