检索结果-内蒙古大学图书馆

Wireless Federated Learning With Hybrid Local and Centralized Training: A Latency Minimization Design

IEEE Journal on Selected Topics in Signal Processing 2023年第1期17卷 248-263页

作者： Huang, Ning Dai, Minghui Wu, Yuan Quek, Tony Q. S. Shen, Xuemin State Key Lab of Internet of Things for Smart City China University of Macau Department of Computer and Information Science China University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer and Information Science China Zhuhai Um Science and Technology Research Institute Zhuhai519031 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore National Cheng Kung University Taiwan University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Wireless federated learning (FL) is a collaborative machine learning (ML) framework in which wireless client-devices independently train their ML models and send the locally trained models to the FL server for aggregation. In this paper, we consider the coexistence of privacy-sensitive client-devices and privacy-insensitive yet computing-resource constrained client-devices, and propose an FL framework with a hybrid centralized training and local training. Specifically, the privacy-sensitive client-devices perform local ML model training and send their local models to the FL server. Each privacy-insensitive client-device can have two options, i.e., (i) conducting a local training and then sending its local model to the FL server, and (ii) directly sending its local data to the FL server for the centralized training. The FL server, after collecting the data from the privacy-insensitive client-devices (which choose to upload the local data), conducts a centralized training with the received datasets. The global model is then generated by aggregating (i) the local models uploaded by the client-devices and (ii) the model trained by the FL server centrally. Focusing on this hybrid FL framework, we firstly analyze its convergence feature with respect to the client-devices' selections of local training or centralized training. We then formulate a joint optimization of client-devices' selections of the local training or centralized training, the FL training configuration (i.e., the number of the local iterations and the number of the global iterations), and the bandwidth allocations to the client-devices, with the objective of minimizing the overall latency for reaching the FL convergence. Despite the non-convexity of the joint optimization problem, we identify its layered structure and propose an efficient algorithm to solve it. Numerical results demonstrate the advantage of our proposed FL framework with the hybrid local and centralized training as well as our proposed alg

关键词： information management

来源：评论

学校读者我要写书评

暂无评论

Attention information Fusion Emotion Analysis Model Based on BiLSTM-BERT

Attention Information Fusion Emotion Analysis Model Based on...

引用

Consumer Electronics and computer engineering (ICCECE), 2021 IEEE International Conference on

作者： Zhi-Wei Cheng Shun-Xin Li Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial Wuhan University of Science and Technology Wuhan China

Aiming at the problem that most sentiment analysis methods do not focus on the weight fusion of local context and global context information and the important information in fusion features is not prominent, AIFM-BB (Attention information fusion emotion analysis model based on BiLSTM-BERT) is proposed. The model uses a pre-trained BERT model to process text vectors and a collaborative speech analysis algorithm to process audio vectors, and introduces BiLSTM and Attention mechanisms. The weight of the feature vector is dynamically adjusted by combining the global information and local information of text and audio and the attention information of text and audio modes. The emotion analysis results are obtained through the Softmax layer after the fusion features are self-focused. The experimental results show that the accuracy of the proposed AIFM-BB model on the CMU-MOSI dataset is 85.3%, which is 2.8 percentage points higher than the baseline. In the multi-category emotion classification task, the accuracy of the model is 44.7%, an improvement of 1.1 percentage points compared with baseline. The accuracy is 83.6% on the CMU-MOSEI dataset, an improvement of 1.4 percentage points compared to baseline.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PpNNT: Multiparty Privacy-Preserving Neural Network Training System

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 370-383页

作者： Feng, Qi He, Debiao Shen, Jian Luo, Min Choo, Kim-Kwang Raymond Wuhan University School of Cyber Science and Engineering Wuhan430072 China Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China School of Information Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China Shanghai Technology Innovation Centre of Distributed Privacy-Preserving Artificial Intelligence Matrix Elements Technologies Shanghai201204 China University of Texas at San Antonio Department of Information Systems and Cyber Security San AntonioTX78249 United States

By leveraging smart devices [e.g., industrial Internet of Things (IIoT)] and real-time data analytics, organizations, such as production plants can benefit from increased productivity, reduced costs, enhanced self-monitoring, and autonomous decision-making. In such a setting, machine learning plays an important role in data analytics, but the use of conventional centralized machine learning solutions may raise uncomfortable concerns about data privacy. Hence, one can explore the use of federated learning. In this article, we propose privacy-preserving deep neural network training (PpNNT), which is designed to support federated learning in the multiparty setting. To minimize the overall costs, we further design a hybrid architecture to fully maximize resource utilization. Our proposed design allows the PpNNT system to provide high security, efficiency, and scalability for IIoT data analytics, as evidenced by our theoretical security proof and experimental results on the CIFAR10 dataset. © 2020 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Bridging the Artificial Intelligence Knowledge and Skill Gaps in Africa: a Case of the 3rdGoogle Tensorflow Bootcamp and FEDGEN Mini-Workshop

Bridging the Artificial Intelligence Knowledge and Skill Gap...

引用

2024 International Conference on science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Adetiba, Emmanuel Wejin, John S. Oshin, Oluwadamilola Ifijeh, Ayodele H. Lawal, Comfort Thakur, Surendra Colin Awelewa, Ayokunle A. Kala, Raymond Jules Ajayi, Priscilla O. Akanle, Matthew B. Sweetwiliams, Faith O. Nnaji, Uche Owolabi, Emmanuel Idowu-Bismark, Olabode Sobola, Gabriel Ota Nigeria Durban University of Technology HRA Institute for Systems Science Durban South Africa Covenant University Department of Electrical and Information Engineering CApIC-ACE Jalingo Nigeria Taraba State University Department of Computer Science Jalingo Nigeria Covenant University Department of Electrical and Information Engineering CApIC-ACE Ota Nigeria Durban University of Technology Department of Information Technology Kzn E-Skills Co-Laboratory Durban4001 South Africa Covenant University Department of Electrical and Information Engineering Ota Nigeria International University of Grand Bassam Grand Bassam Ivory Coast Covenant University Center for Systems and Information Services CApIC-ACE Ota Nigeria Covenant University Department of Computer and Information Science CApIC-ACE Ota Nigeria Ltd 405 Justice Mahomed St. Gauteng Pretoria0002 South Africa

ISBN: (纸本)9798350358155

In transiting from one civilization to another, technology has played a vital and positive role. In the 21st century, one of the digital developments that is paving ways for human life improvement is machine-assisted technology using Artificial Intelligence (AI). Artificial Intelligence has successfully enhanced man's capacity in solving complex problems and processes. However, as developed nations continue to reap from the adoption of AI in various fields of human endeavors, the continent of Africa has remained behind, especially in AI-based skills and research. Various governments in developing nations have encouraged the adoption of AI, especially in institutions of learning. However, theoretical adoption without practical experience has remained an ineffective way of bridging the digital divide. In this paper we present the outcome of a practical approach to bridging the AI divide among students and researchers in Africa through funding support from the Google TensorFlow College Outreach Award. A 3-day hybrid bootcamp was organized (11th to 13th December, 2023) using the Google funding in order to equip postgraduate students and researchers with AI and collaborative research skills. A pre-survey method was employed to ascertain the knowledge level of the bootcamp participants. From the pre-surveyed feedback, training sessions on various AI domains were presented, and participant equipped with practical AI skills using a deployed AI-based cloud programming platform running on the private Federated Genomic Cloud (FEDGEN) infrastructure at Covenant University. A post-survey feedback was used to ascertain the effectiveness of this approach. A comparative analysis of the pre-survey and post-survey reveals a 70% improvement of AI skills among participants. This shows that having continuous training session for students and researchers is an effective method in closing the AI skills gap between developed and developing nations. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces 38

Taming "data-hungry" reinforcement learning? Stability in co...

引用

38th Conference on Neural information Processing systems, NeurIPS 2024

作者： Duan, Yaqi Wainwright, Martin J. Department of Technology Operations and Statistics Stern School of Business New York University New YorkNY10012 United States Laboratory for Information and Decision Systems Statistics and Data Science Center Department of Electrical Engineering and Computer Science Department of Mathematics Massachusetts Institute of Technology CambridgeMA02139 United States

We introduce a novel framework for analyzing reinforcement learning (RL) in continuous state-action spaces, and use it to prove fast rates of convergence in both off-line and on-line settings. Our analysis highlights two key stability properties, relating to how changes in value functions and/or policies affect the Bellman operator and occupation measures. We argue that these properties are satisfied in many continuous state-action Markov decision processes. Our analysis also offers fresh perspectives on the roles of pessimism and optimism in off-line and on-line RL. © 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

IoT Enabled Driver Compatible Cost-Effective System for Drowsiness Detection with Optimized Response time 3rd

IoT Enabled Driver Compatible Cost-Effective System for Drow...

引用

3rd EAI International Conference on Cognitive Computing and Cyber Physical systems, IC4S 2022

作者： Sarkar, Argha Kundu, Mayuri Pareek, Prakash Gupta, Nishu Reis, Manuel J. Cabral S. School of Computer Science and Engineering REVA University Karnataka Bangalore560064 India Department of Electronics and Communication Engineering Vishnu Institute of Technology Andhra Pradesh Bhimavaram534202 India Department of Electronic Systems Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Gjøvik2815 Norway Engineering Department UTAD/IEETA Vila Real5001-801 Portugal

ISBN: (纸本)9783031289743

The present work researches driver drowsiness, which constitutes a huge problem, and can turn into fatal incidents potentially involving the losing of lives, being it while driving in a highway (car, bus, truck, etc.), in the railway, or any other transportation mean (ship, airplane, etc.). Recent technology has been involved in the study of the fatigue behaviour. The purpose of this work is to identify the in-driver’s drowsiness, contributing to get rid of the accidents, mainly during the night, and to ensure better safety in train and on the highways. A camera is used to capture images from the driver, and face detection is executed in real-time to find out the exact position of driver’s face. Here, the blinking of the driver’s eye is under consideration. The fundamental concept lies in the closing of the driver’s eye for a specific duration of time. If the closing time exceeds that certain duration, drowsiness is detected and an alarm is sounded for awareness. Python and OpenCV (using Haarcascade library) are the fundamental programming platforms for sensing the facial attributes. In this work, a cost-effective system for the driver’s drowsiness detection is aimed. Further, the result also indicates the reduction of response and processing time, which is ideal for real time detection. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Two-Sided Online Task Assignment Based on Worker Portraits in Mobile CrowdSensing

Two-Sided Online Task Assignment Based on Worker Portraits i...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Zhenyang Mao Peng Li Guangzhong Liao Lei Nie Haizhou Bao Qin Liu School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China School of Cyber Science and Engineering Wuhan University China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Task assignment is a challenging problem in mobile crowdsensing (MCS), especially since workers and tasks are online. Existing work does not consider the portrait of the workers when assigning tasks, which may result in workers being assigned to fields they are not familiar with, thus affecting the quality of task completion. In this paper, we focus on online scenarios and identify a more practical task assignment problem, a two-sided (workers and tasks) online task assignment problem based on worker portrait in MCS. We decompose this problem into two subproblems: the worker portrait analysis problem (WPA) and the two-sided online personalized assignment problem (TOPA). To solve the WPA problem, we propose a worker portrait analysis algorithm that uses the semi-supervised model to describe the worker portrait at a fine-grained level. Then, based on the worker portrait, we propose a two-sided online personalized assignment algorithm to solve the TOPA problem. The proposed algorithm guarantees a lower bound on the assignment results by analyzing the worker portrait data. Moreover, we prove the TOPA problem is NP-hard and demonstrate the competitive ratio can achieve ln(max(u i,j )+1). Finally, we conduct extensive experiments on two datasets, and the experimental results show that our method outperforms baseline algorithms.

关键词： Analytical models Crowdsensing Federated learning Task analysis Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Human Faces Detection and Tracking for Crowd Management in Hajj and Umrah

引用

computers, Materials & Continua 2022年第6期71卷 6275-6291页

作者： Riad Alharbey Ameen Banjar Yahia Said Mohamed Atri Abdulrahman Alshdadi Mohamed Abid Department of Information Systems and Technology College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia Electrical Engineering Department College of EngineeringNorthern Border UniversityArarSaudi Arabia Laboratory of Electronics and Microelectronics(LR99ES30) Faculty of Sciences of MonastirUniversity of MonastirTunisia College of Computer Sciences King Khalid UniversityAbhaSaudi Arabia CES Laboratory ENISUniversity of SfaxTunisia

Hajj and Umrah are two main religious duties for *** help faithfuls to perform their religious duties comfortably in overcrowded areas,a crowd management system is a must to control the entering and exiting for each *** the number of people is very high,an intelligent crowd management system can be developed to reduce human effort and accelerate the management *** this work,we propose a crowd management process based on detecting,tracking,and counting human faces using Artificial Intelligence *** detection and counting will be performed to calculate the number of existing visitors and face detection and tracking will be used to identify all the humans for security *** proposed crowd management system is composed form three main parts which are:(1)detecting human faces,(2)assigning each detected face with a numerical identifier,(3)storing the identity of each face in a database for further identification and *** main contribution of this work focuses on the detection and tracking model which is based on an improved object detection *** improved Yolo v4 was used for face detection and *** has been very effective in detecting small objects in highresolution *** novelty contained in thismethod was the integration of the adaptive attention mechanism to improve the performance of the model for the desired *** wise attention mechanism was applied to the output layers while both channel wise and spatial attention was integrated in the building *** main idea from the adaptive attention mechanisms is to make themodel focus more on the target and ignore false positive *** demonstrated the efficiency of the proposed method through expensive experimentation on a publicly available *** wider faces dataset was used for the train and the evaluation of the proposed detection and tracking *** proposed model has achieved good results with 91.2%of mAP and a processing speed

关键词： Crowdmanagement Hajj and Umrah face detection object tracking convolutional neural networks(CNN) adaptive attention mechanisms

来源：评论

学校读者我要写书评

暂无评论

Disentangling Spatio-Temporal Knowledge for Weakly Supervised Object Detection and Segmentation in Surgical Video

Disentangling Spatio-Temporal Knowledge for Weakly Supervise...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Guiqiu Liao Matjaz Jogan Sai Koushik Eric Eaton Daniel A. Hashimoto Department of Surgery PCASO Laboratory University of Pennsylvania Department of Electrical and Systems Engineering University of Pennsylvania Department of Computer and Information Science University of Pennsylvania

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Weakly supervised video object segmentation (WSVOS) enables the identification of segmentation maps without requiring extensive annotations of object masks, relying instead on coarse video labels indicating object presence. WSVOS in surgical videos is, however, more challenging due to the complex interaction of multiple transient objects, such as surgical tools moving in and out of the surgical field. In this scenario, state-of-the-art WSVOS methods struggle to learn accurate segmentation maps. We address this problem by introducing ViDeo Spatio-Temporal disentanglement Networks (VDST-Net), a framework to disentangle complex spatio-temporal object interactions using semi-decoupled knowledge distillation to predict high-quality class activation maps (CAMs). A teacher network is designed to help a temporal-reasoning student network resolve activation conflicts, as the student leverages temporal dependencies when specifics about object location and timing in the video are not provided. We demonstrate the efficacy of our framework on a challenging surgical video dataset where objects are, on average, present in less than 60% of annotated frames, and compare our method to state-of-the-art methods on surgical data and on a public dataset commonly used to benchmark WSVOS. Our method outperforms state-of-the-art techniques and generates accurate segmentation masks under video-level weak supervision. Our code is available at: https://***/PCASOlab/VDST-net.

关键词： Accuracy Weak supervision Surgery Object segmentation Object detection Streaming media real-time systems Timing Object recognition Transient analysis

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition of sEMG Based on Res-LSTM 17th

Gesture Recognition of sEMG Based on Res-LSTM

引用

17th International Conference on Intelligent Robotics and Applications, ICIRA 2024

作者： Zhao, Yujia Zou, Chunlong Yun, Juntong Jiang, Du Huang, Li Liu, Ying Jiang, Guozhang Xie, Yuanmin Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China College of Mechanical Engineering Hubei University of Automotive Technology Shiyan442000 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan430081 China College of Computer Science and Technology Wuhan University of Science and Technology Wuhan430081 China School of Mechanical Engineering Hubei Engineering University Xiaogan432000 China

ISBN: (纸本)9789819607761

sEMG (surface electromyography) signal control of bionic prostheses has been widely studied over the past few years. In particular, sparse sEMG signals are rapidly developing in the field of gesture recognition for their convenience, noninvasiveness, and ease of access. However, compared with high-density EMG signals, sparse EMG signals lack rich feature information, which in turn affects gesture recognition accuracy. In order to reduce the loss of feature information of sparse EMG signals in the spatio-temporal dimension, this paper proposes a hybrid neural network Res-LSTM combining residual network and long short-term memory network. The ordinary convolutional blocks in the CNN network are replaced with residual blocks, and the final fully connected layer is removed and a constant mapping layer is added to adequate extraction of spatial feature information of the data. The Res layer’s output is utilized as the input for the long and short-term memory (LSTM) network, which further extracts the features of the data in the temporal dimension, and finally completes the categorization output through a fully connected layer. The average accuracy of 91.11% for gesture-motion classification was verified by training on a homebrew dataset;and tested on a public dataset, NinaPro DB1, with an average accuracy of 91.03%. The experimental findings indicate that the proposed Res-LSTM network framework contributes to solving the problem of lack of feature information of sparse sEMG signals and improves the pattern recognition accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Gesture recognition

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：