检索结果-内蒙古大学图书馆

Evaluation of Deep Learning Models for Person Authentication Based on Touch Gesture

computer Systems science & engineering 2022年第8期42卷 465-481页

作者： Asrar Bajaber Mai Fadel Lamiaa Elrefaei Computer Science Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Electrical Engineering Department Faculty of Engineering at ShoubraBenha UniversityCairo11629Egypt

Touch gesture biometrics authentication system is the study of user's touching behavior on his touch device to identify *** features traditionally used in touch gesture authentication systems are extracted using hand-crafted feature extraction *** this work,we investigate the ability of Deep Learning(DL)to automatically discover useful features of touch gesture and use them to authenticate the *** different models are investigated Long-Short Term Memory(LSTM),Gated Recurrent Unit(GRU),Convolutional Neural Network(CNN)combined with LSTM(CNN-LSTM),and CNN combined with GRU(CNN-GRU).In addition,different regularization techniques are investigated such as Activity Regularizer,Batch Normalization(BN),Dropout,and *** deep networks were trained from scratch and tested using TouchAlytics and BioIdent datasets for dynamic touch *** result reported in terms of authentication accuracy,False Acceptance Rate(FAR),False Rejection Rate(FRR).The best result we have been obtained was 96.73%,96.07%and 96.08%for training,validation and testing accuracy respectively with dynamic touch authentication system on TouchAlytics dataset with CNN-GRU DL model,while the best result of FAR and FRR obtained on TouchAlytics dataset was with CNN-LSTM were FAR was 0.0009 and FRR was *** BioIdent dataset the best results have been obtained was 84.87%,78.28%and 78.35%for Training,validation and testing accuracy respectively with CNN-LSTM *** use of a learning based approach in touch authentication system has shown good results comparing with other state-of-the-art using TouchAlytics dataset.

关键词： Touch authentication system touch gestures behavioral biometric deep learning classification CNN RNN LSTM

来源：评论

学校读者我要写书评

暂无评论

Ternary Multiply-Accumulate Circuit Based on Domino Structure 15

Ternary Multiply-Accumulate Circuit Based on Domino Structur...

引用

15th IEEE International Conference on ASIC, ASICON 2023

作者： Shi, Hanyu Zhang, Yuejun Zhang, Huihong Li, Qikang Wang, Pengjun Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China Wenzhou University College of Electrical and Electronic Engineering Wenzhou325035 China

ISBN: (纸本)9798350312980

In order to solve the problem of memory and computation bottleneck in neural networks and improve the efficiency of computation, this paper proposes a design scheme of ternary multiply-accumulate circuits based on domino structure. This paper first analyzes the principles of ternary logic and multiply-accumulate circuits, then introduces the design scheme of domino ternary literal arithmetic circuits, multiply circuits, and accumulate circuits, and finally realizes the ternary multiply-accumulate arithmetic by combining the above circuits. The scheme is tested under Taiwan Semiconductor Manufacturing Company(TSMC) 65nm process, and the results verify the accuracy of the arithmetic results. The two-bit multiply four-bit accumulate circuit operates at the supply voltage of 1.2V, the temperature of 27°C, and the clock frequency of 50MHz, and the average power dissipation of the circuit is measured to be 75.5uW, and the maximum delay of the circuit is 385ps. © 2023 IEEE.

关键词： domino circuit multiply-accumulate circuit ternary logic

来源：评论

学校读者我要写书评

暂无评论

Does Daily Use of Digital Technologies Influence the Reading and Information Literacy of 15-year-old Students? 46

Does Daily Use of Digital Technologies Influence the Reading...

引用

46th ICT and Electronics Convention, MIPRO 2023

作者： Lang, V. Spernjak, A. Sorgo, A. University of Maribor Faculty of Natural Sciences and Mathematics Maribor Slovenia University of Maribor Faculty of Electrical Engineering and Computer Science Slovenia

ISBN: (纸本)9789532331042

This paper focuses on the impact of out-of-school and in-school use of digital technologies on the reading and information literacy skills of 15-year-old Slovenian students who participated in the PISA 2018 study. For our study, we selected PISA 2018 variables related to the use of digital technologies in school or outside school. The sample (N=2612) consists of 50.8% girls and 49.2% boys. Part of the questionnaire refers to the use of digital technologies outside school: for entertainment and practical information purposes, for school purposes, and time spent with digital technologies. Part of the questionnaire refers to the use of digital technologies in school: for various purposes, for learning or teaching, and the time spent using digital technologies in class. The results show that the constructs of using digital technologies in school or out of school are strongly related but have a very low/insignificant impact on reading literacy and information literacy. © 2023 MIPRO Croatian Society.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Agent Selection Framework for Federated Learning in Resource-Constrained Wireless Networks

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2024年 2卷 1265-1282页

作者： Raftopoulou, Maria Da Silva, Jose Mairton B. Litjens, Remco Vincent Poor, H. Van Mieghem, Piet Uppsala University Department of Information Technology Uppsala751 05 Sweden Delft University of Technology Faculty of Electrical Engineering Mathematics and Computer Science Delft2628 CD Netherlands Department of Networks The Hague2595 DA Netherlands Princeton University Department of Electrical and Computer Engineering PrincetonNJ08544 United States

Federated learning is an effective method to train a machine learning model without requiring to aggregate the potentially sensitive data of agents in a central server. However, the limited communication bandwidth, the hardware of the agents and a potential application-specific latency requirement impact how many and which agents can participate in the learning process at each communication round. In this paper, we propose a selection metric characterizing each agent's importance with respect to both the learning process and the resource efficiency of its wireless communication channel. Leveraging this importance metric, we formulate a general agent selection optimization problem, which can be adapted to different environments with latency or resource-oriented constraints. Considering an example wireless environment with latency constraints, the agent selection problem reduces to the 0/1 Knapsack problem, which we solve with a fully polynomial approximation. We then evaluate the agent selection policy in different scenarios, using extensive simulations for an example task of object classification of European traffic signs. The results indicate that agent selection policies which consider both learning and channel aspects provide benefits in terms of the attainable global model accuracy and/or the time needed to achieve a targeted accuracy level. However, in scenarios where agents have a limited number of data samples or where the latency requirement is very stringent, a pure learning-based agent selection policy is shown to be more beneficial during the early or late stages of the learning process. © 2023 CCBY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Study on 1D-Point Cloud Using Through-Wall mm Wave Radar for Human Pose Estimation 12

A Study on 1D-Point Cloud Using Through-Wall mm Wave Radar f...

引用

12th International electrical engineering Congress, iEECON 2024

作者： Phaisiri, Kritthee Kittiyanpunya, Chainarong Shutimarrungson, Nattakarn Boonpoonga, Akkarat Akkaraekthalin, Prayoot Kaemarungsi, Kamol King Mongkut's University Of Technology North Bangkok Faculty Of Engineering Department Of Electrical And Computer Engineering Bangkok Thailand Rajamangala University Of Technology Rattanakosin Faculty Of Engineering Department Of Mechatronics Engineering Nakhon Pathom Thailand Mahasarakham Business School Mahasarakham University Department Of Business Computer Maha Sarakham Thailand Faculty Of Engineering Department Of Electrical And Computer Engineering Bangkok Thailand National Electronics And Computer Technology Center National Science And Technology Development Agency Pathum Thani Thailand

ISBN: (纸本)9798350383591

This paper presents human pose estimation using millimeter-wave (mmWave) radar technology capable of penetrating obstacles. Operating within the frequency modulated continuous wave (FMCW) at 60 - 64 GHz, our radar system generates signals conducive to accurate human pose representation. Our data processing framework focuses on producing point cloud data, effectively capturing each human movement. Results are visualized through a 2D graph, with the z-axis representing time. Experimental data, collected from various activities conducted behind different walls, underwent thorough analysis, comparing point cloud positions with actual human postures. The outcomes affirm the effectiveness of mmWave radar systems, positioned behind obstacles, in accurately extracting human postures. © 2024 IEEE.

关键词： Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

Vehicle-Named Data Network Case Study in Traffic Management System 6

Vehicle-Named Data Network Case Study in Traffic Management ...

引用

6th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2023

作者： Gusrian, Ghivari Faiz Negara, Ridha Muldina Ahdan, Syaiful Telecommunication Engineering School of Electrical Engineering Telkom University Indonesia Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Lampung Indonesia

ISBN: (纸本)9798350358346

Rapid technological advancements, especially in telecommunications, have increased network demands. According to Cisco's annual report, the global internet user population is expected to grow by 66% by 2023, reflecting the surge of technology in-vehicle networks. In this context, Named Data Networking (NDN) is emerging as a potential solution to enhance the efficiency of data movement in vehicle environments through the Vehicular-NDN (V-NDN) concept. NDN is a content-focused network architecture and is considered the architecture of the future owing to its routing scalability, forwarding speed, network security, and content protection and privacy. Within this paradigm, data requests are content based, supporting data acquisition efficiency in vehicle environments. The V-NDN network is anticipated to realize the future transportation system, enabling vehicles to communicate with each other (V2V) and with infrastructure (V2I). NDNs can potentially reduce delays in data retrieval by allowing consumers to access or share data through communication processes. In this paper, a simulation of data movement was conducted using moving nodes and three forwarding strategies. The simulation involved two schemes: changes in test time and variations in the amount of interest. Overall, multicast VANET exhibited the best performance compared to the other two forwarding strategies. 'Best Route' demonstrated superior performance, outperforming 'Localhop'. © 2023 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Analysis of web accessibility evaluation tools and guidelines for monitoring according to the Directive (EU) 2016/2102 10

Analysis of web accessibility evaluation tools and guideline...

引用

10th International Conference on Software Development and Technologies for Enhancing Accessibility and Fighting Info-Exclusion, DSAI 2022

作者： Rajh, Nataša Debevc, Matjaž University of Maribor Faculty of Electrical Engineering and Computer Science Slovenia

ISBN: (纸本)9781450398077

This paper presents a comparative analysis of automated web accessibility assessment tools and guidelines for monitoring of public websites and reporting according to the Directive (EU) 2016/2102. A review of previous research and our own comparative analysis revealed that the tools differ not only in functionality and result presentation, but also in violation discovery. Overviews of the Web Accessibility Directive Expert Group meetings' minutes and first reports by the European member states showed that unified monitoring and reporting do not exist between member states. We provided guidelines that would meet the minimum requirements of the Commission Implementing Decision (EU) 2018/1524, as well as guidelines for more detailed evaluation, which would improve results in terms of providing a clearer picture of the actual level of accessibility and enable efficient comparison between European member states. © 2022 ACM.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

ATM: Adaptive transformer model for reconstruction of remote sensing multi-temporal non-equispaced sequence imagery

引用

Journal of King Saud University - computer and Information sciences 2025年第4期37卷 1-13页

作者： Qi, Zhi-Peng Zhao, Zi-Yi Jin, Xing Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo 315211 China

Due to the influence of the imaging characteristics of the solar orbiting satellite and atmospheric conditions, the multi-spectral observation data often have the missing of phase image, which brings difficulties to the efficient and automatic processing of regional remote sensing data. However, the observation sequence contain complex and diverse information, it is difficult for the conventional method to characterize this information. To address this issue, we perform an adaptive transformer model (ATM) for reconstruction of remote sensing multi-temporal non-equispaced sequence imagery. To realize efficient information processing by dynamically adjusting the weight distribution of the internal relations of data, the core workflow of ATM is divided into three steps: feature coding, relationship evaluation and adaptive focusing. Firstly, the input data is encoded as a sequence of vectors, each representing a local feature of the data. Then, the model generates an attention score by calculating the similarity between the query and the key, quantifying the strength of the association between the different features. Finally, a context-aware feature representation is formed by using the normalized attention score weighted aggregation vector. Our experiments, conducted utilizing unmanned aerial vehicle (UAV) datasets and the Landsat-8 datasets, demonstrate that the proposed methodology achieves promising performance in terms of both precision (RMSE decreases by about 2.5 points, and SSIM increases by about 0.05 points) and effectiveness (time cost savings of about 50 %), and the proposed model has wide application prospects in intelligent agriculture, water color inversion and vegetation phenology detection. © The Author(s) 2025.

关键词： Adaptive transformer model Missing of phase image Multi-spectral observation data Non-equispaced sequence imagery

来源：评论

学校读者我要写书评

暂无评论

Industrial Teleassistance with the Help of Augmented Reality 23

Industrial Teleassistance with the Help of Augmented Reality

引用

23rd RoEduNet Conference: Networking in Education and Research, RoEduNet 2024

作者： Bobeica, Valentin Popescu, Dan Angelescu, Nicoleta Ichim, Loretta National University of Science and Technology Politehnica Bucharest Faculty of Automatic Control and Computer Science Bucharest Romania Valahia University of Targoviste Faculty of Electrical Engineering Electronics and Information Technology Targoviste Romania

ISBN: (纸本)9798331540388

This paper details the integration of augmented reality (AR) in a new factory, focusing on enhancing maintenance efficiency and optimization. The innovative approach involves combining AR technology, an Android application, and Siemens PLCs (Programmable Logic Controller), for efficient automation. The robustness of the PLC enables seamless integration within manufacturing environments, accommodating diverse programming paradigms. The software aspect features Human Machine Interface (HMI) configuration using Siemens' WinCC software, offering dynamic visualizations, alarm handling, and data logging. WinCC's scalability suits applications of varying sizes. The HMI architecture is designed for easy parameter display. The Android application, developed with Java and Python, leverages their respective strengths in Android app development and image processing. Data exchange is facilitated by OPC-UA, supporting multiple programming languages for seamless communication. The AR Teleassistance is highlighted as a revolutionary solution, fostering real-Time communication among global experts, technicians, and operators. Beyond gaming origins, AR teleassistance enhances efficiency in various sectors, minimizing downtime and facilitating global knowledge transfer. The integration of Teleassistance promotes effective collaboration between human expertise and automated systems, crucial for optimal performance in modern industrial settings. Continuous development is suggested through the addition of more 3D mechanical drawings and real-Time stock information for parts in the application, aiming for future optimization and performance enhancement. © 2024 IEEE.

关键词： augmented reality data exchange global knowledge image processing manufacturing environment production processes smart industrial

来源：评论

学校读者我要写书评

暂无评论

Tube-based Model Reference Adaptive Control for Vibration Suppression of Active Suspension Systems

引用

IEEE/CAA Journal of Automatica Sinica 2022年第4期9卷 728-731页

作者： Yashar Mousavi Alireza Alfi Ibrahim Beklan Kucukdemiral Afef Fekih IEEE the Department of Applied Science School of ComputingEngineering and Built EnvironmentGlasgow Caledonian University the Faculty of Electrical Engineering Shahrood University of Technology the Electrical and Computer Engineering Department University of Louisiana at Lafayette

Dear editor,With the developments of industrial automation in recent years,vehicle suspension systems have received a great deal of attention in industry and academia due to their critical role in the chassis performance of vehicles[1].The suspension system is expected to guarantee the vehicle’s maneuverability and provide satisfactory ride comfort by absorbing the vibrations arising from the road surface excitations and ensuring road-holding capability and suspension *** by the desirable performance of the model reference adaptive control(MRAC)approach,various literature studies have investigated its performance in diverse linear and nonlinear practical systems[2].

关键词： editor Active guarantee

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：