检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Na, Byunggook Jang, Jaehee Park, Seongsik Kim, Seijoon Kim, Joonoo Jeong, Moon Sik Kim, Kwang Choon Heo, Seon Kim, Yoonsang Yoon, Sungroh Dept. of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Korea Institute of Science and Technology Seoul Korea Republic of Samsung Advanced Institute of Technology Samsung Electronics Suwon Korea Republic of Mobile Communications Business Samsung Electronics Suwon Korea Republic of ASRI INMC ISRC Interdisciplinary Program in AI Seoul National University Seoul Korea Republic of

Various deep learning applications on smartphones have been rapidly rising, but training deep neural networks (DNNs) has too large computational burden to be executed on a single smartphone. A portable cluster, which connects smartphones with a wireless network and supports parallel computation using them, can be a potential approach to resolve the issue. However, by our findings, the limitations of wireless communication restrict the cluster size to up to 30 smartphones. Such small-scale clusters have insufficient computational power to train DNNs from scratch. In this paper, we propose a scalable smartphone cluster enabling deep learning training by removing the portability to increase its computational efficiency. The cluster connects 138 Galaxy S10+ devices with a wired network using Ethernet. We implemented large-batch synchronous training of DNNs based on Caffe, a deep learning library. The smartphone cluster yielded 90% of the speed of a P100 when training ResNet-50, and approximately 43x speed-up of a V100 when training MobileNet-v1. © 2021, CC BY-NC-ND.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Unmasking Illusions: Understanding Human Perception of Audiovisual Deepfakes

arXiv

引用

arXiv 2024年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei11529 Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu300044 Taiwan Department of Computer Science National Chengchi University Taipei11529 Taiwan Department of Electrical Engineering Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan Institute of Information Science Academia Sinica Taipei11529 Taiwan

The emergence of contemporary deepfakes has attracted significant attention in machine learning research, as artificial intelligence (AI) generated synthetic media increases the incidence of misinterpretation and is difficult to distinguish from genuine content. Currently, machine learning techniques have been extensively studied for automatically detecting deepfakes. However, human perception has been less explored. Malicious deepfakes could ultimately cause public and social problems. Can we humans correctly perceive the authenticity of the content of the videos we watch? The answer is obviously uncertain;therefore, this paper aims to evaluate the human ability to discern deepfake videos through a subjective study. We present our findings by comparing human observers to five state-of-the-art deepfake detection models. To this end, we used gamification concepts to provide 110 participants (55 native English speakers and 55 non-native English speakers) with a web-based platform where they could access a series of 40 videos (20 real and 20 fake) to determine their authenticity. Each participant performed the experiment twice with the same 40 videos in different random orders. The videos are manually selected from the FakeAVCeleb dataset. We found that all AI models performed significantly better than humans when evaluated on the same 40 videos. The study also reveals that while deception is not impossible, humans tend to overestimate their detection capabilities. Our experimental results may help benchmark human versus machine performance, advance forensics analysis, and enable adaptive countermeasures. © 2024, CC BY.

关键词： Audiovisual

来源：评论

学校读者我要写书评

暂无评论

Error analysis for RADAR neighbor matching localization in linear logarithmic strength varying Wi-Fi environment

The Scientific World Journal

引用

The Scientific World Journal 2014年第1期2014卷 647370页

作者： Zhou, Mu Tian, Zengshan Xu, Kunjie Yu, Xiang Wu, Haibo Chongqing Key Lab of Mobile Communications Technology Chongqing University of Posts and Telecommunications Chongqing 400065 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Kowloon Hong Kong Graduate Telecommunications and Networking Program University of Pittsburgh Pittsburgh PA 15260 United States China Internet Research Lab Computer Network Information Center Chinese Academy of Sciences Beijing 100190 China

This paper studies the statistical errors for the fingerprint-based RADAR neighbor matching localization with the linearly calibrated reference points (RPs) in logarithmic received signal strength (RSS) varying Wi-Fi environment. To the best of our knowledge, little comprehensive analysis work has appeared on the error performance of neighbor matching localization with respect to the deployment of RPs. However, in order to achieve the efficient and reliable location-based services (LBSs) as well as the ubiquitous context-awareness in Wi-Fi environment, much attention has to be paid to the highly accurate and cost-efficient localization systems. To this end, the statistical errors by the widely used neighbor matching localization are significantly discussed in this paper to examine the inherent mathematical relations between the localization errors and the locations of RPs by using a basic linear logarithmic strength varying model. Furthermore, based on the mathematical demonstrations and some testing results, the closed-form solutions to the statistical errors by RADAR neighbor matching localization can be an effective tool to explore alternative deployment of fingerprint-based neighbor matching localization systems in the future. © 2014 Mu Zhou et al.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding Audiovisual Deepfake Detection: Techniques, Challenges, Human Factors and Perceptual Insights

arXiv

引用

arXiv 2024年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei11529 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu300044 Taiwan The Department of Computer Science National Chengchi University Taipei11529 Taiwan The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Deep Learning has been successfully applied in diverse fields, and its impact on deepfake detection is no exception. Deepfakes are fake yet realistic synthetic content that can be used deceitfully for political impersonation, phishing, slandering, or spreading misinformation. Despite extensive research on unimodal deepfake detection, identifying complex deepfakes through joint analysis of audio and visual streams remains relatively unexplored. To fill this gap, this survey first provides an overview of audiovisual deepfake generation techniques, applications, and their consequences, and then provides a comprehensive review of state-of-the-art methods that combine audio and visual modalities to enhance detection accuracy, summarizing and critically analyzing their strengths and limitations. Furthermore, we discuss existing open source datasets for a deeper understanding, which can contribute to the research community and provide necessary information to beginners who want to analyze deep learning-based audiovisual methods for video forensics. By bridging the gap between unimodal and multimodal approaches, this paper aims to improve the effectiveness of deepfake detection strategies and guide future research in cybersecurity and media integrity. © 2024, CC BY.

关键词： Audiovisual

来源：评论

学校读者我要写书评

暂无评论

ENERGY-EFFICIENT BROADCASTING IN WIRELESS AD HOC NETWORKS LOWER BOUNDS AND ALGORITHMS

引用

Journal of Interconnection Networks 2002年第3N04期3卷 149-166页

作者： FANG BIAN ASHISH GOEL C. S. RAGHAVENDRA XIN LI Department of Computer Science University of Southern California Los Angeles CA 90089-0781 USA Bian and Raghavendra are supported in part by the DARPA contract F33615-00-C-1633 in the Power Aware Computing and Communications Program and by the DARPA/AFRL under agreement no. F30602-01-2-0549. Goel is supported in part by the NSF GAREER award 0133968. Department of Electrical Engineering University of Southern California Los Angeles CA 90089-2652 USA

Energy-efficient communication is critical for increasing life of power limited wireless ad hoc networks. There has been considerable interest in minimum energy broadcast operations. In this paper, we develop bounds and an algorithm for minimizing energy cost for broadcasting from any source to all other nodes in the network. Most prior work have used simpler model for energy cost for wireless communications by accounting only the analog radiation cost for transmission and ignored the fixed cost for electronics in transmission and reception circuitry in nodes. Furthermore, in a network it is possible for some node pairs not be able to communicate directly even though they are in their radio ranges due to obstacles present in the terrain of the network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting Metabolic Syndrome With Machine Learning Models of Hybrid Analysis

Predicting Metabolic Syndrome With Machine Learning Models o...

引用

2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023

作者： Wu, Yi-Syuan Wang, Wei-Yun Wu, Hao-Yi Chen, Chao-Wen Chu, Chi-Ming Wu, Cheng-Wei Division of Trauma and Surgical Critical Care Department of Surgery Kaohsiung Medical University Hospital Kaohsiung Medical University Kaohsiung Taiwan Master Program of E-Learning for Multimedia and Network Communications National I-Lan University Yilan Taiwan National Defense Medical Center Tri-Service General Hospital Songshan Branch School of Nursing Department of Nursing Taipei Taiwan National Defense Medical Center Department of Nursing Tri-Service General Hospital Taipei Taiwan Kaohsiung Medical University Hospital Kaohsiung Medical University Trauma and Critical Care Service Department of Surgery Kaohsiung Taiwan National Defense Medical Center School of Public Health Taipei Taiwan National I-Lan University Department of Computer Science and Information Engineering Yilan Taiwan

ISBN: (纸本)9798350324174

The study uses machine learning to determine the accuracy of different algorithms for predicting MetS. Early prediction of MetS through routine health screening is an important goal for preventive medicine. The subjects in this study were employees aged 20 to 65 years old who signed a consent form for in-hospital health screening data were collected from 2015 to 2020. Total of 3538 individuals who underwent health screening were included in this study. Baseline characteristics of the 315 participants diagnosed with metabolic syndrome and 3222 participants without metabolic syndrome. This is a machine learning approach to identify metabolic syndrome using biochemical values and lifestyle habits. We found that the F1 score for detection of metabolic syndrome by neural network is the most accurate and higher compared to other models. Our study also identified some new indicators, including heart rhythm, RBC, WBC, Hb, and uric acid, as candidates for better detection of metabolic syndrome. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Artificial Neural Network to Model Characteristic Fluctuation of Multi-Channel Gate-All-Around Silicon Nanosheet and Nanofin MOSFETs Induced by Random Nanosized Metal Grains

Application of Deep Artificial Neural Network to Model Chara...

引用

IEEE Electron Devices Technology and Manufacturing Conference (EDTM)

作者： Sagarika Dash Yiming Li Wen-Li Sung Parallel and Scientific Computing Laboratory National Yang-Ming Chiao Tung University Hsinchu Taiwan Electrical Engineering and Computer Science International Graduate Program National Yang-Ming Chiao Tung University Hsinchu Taiwan Institute of Communications Engineering National Yang-Ming Chiao Tung University Hsinchu Taiwan Department of Electronics and Electrical Engineering National Yang-Ming Chiao Tung University Hsinchu Taiwan Institute of Biomedical Engineering National Yang-Ming Chiao Tung University Hsinchu Taiwan Center for mm Wave Smart Radar System and Technologies National Yang-Ming Chiao Tung University Hsinchu Taiwan

In this work, we propose a deep artificial neural network (D-ANN) to estimate the work function fluctuation (WKF) on 4-channel stacked gate-all-around (GAA) silicon (Si) nanosheet (NS) and nanofin (NF) MOSFET devices for the first time. The 2-layered simple deep model can well predict the transfer characteristics for both NS/NF FET with a large number of (128) input features, utilizing considerably lesser (1100 samples) data uniformly. The resultant model is evaluated by the $\mathrm{R}^{2}$ score and RMSE to witness its competency and the average error is $< 4\%$ . We do also discuss the circuit simulation possibility by applying the ANN approach.

关键词： Semiconductor device modeling MOSFET Gallium arsenide Artificial neural networks Predictive models Logic gates Silicon

来源：评论

学校读者我要写书评

暂无评论

PARALLEL AND DISTRIBUTED TLM COMPUTATION WITH SIGNAL-PROCESSING FOR ELECTROMAGNETIC-FIELD MODELING

引用

INTERNATIONAL JOURNAL OF NUMERICAL MODELLING-ELECTRONIC NETWORKS DEVICES AND FIELDS 1995年第3-4期8卷 169-185页

作者： SO, PPM ESWARAPPA, C HOEFER, WJR NSERC/MPR Teltech Research Chair in RF Engineering Department of Electrical and Computer Engineering University of Victoria Victoria British Columbia V8W 3P6 Canada Poman So received his B.Sc. degree in computer science and physics from the University of Toronto Toronto Onatario Canada in 1985. He obtained his B.A. Sc. and M.A.Sc. degrees in electrical engineering (summa cum laude) from the University of Ottawa Ottawa Ontario Canada in 1987 and 1989 respectively. Mr So was a research engineer in the University of Ottawa from January 1989 to October 1991 his research interests included CAD techniques of microwave circuits and numerical methods for electromagnetic wave modelling. He specialized in the development of electromagnetic engineering CAD software and successfully implemented a number of electromagnetic wave simulators based on the two-dimensional and three-dimensional transmission-line matrix methods. From August 1990 to February 1991 he accompanied Professor W. J. R. Hoefer to Rome Italy and Sophia Antiopolas France. During that time he implemented a parallel version of the 3D-TLM simulator for the CM-2 Connection Machine using C-Star and X Windows Library. He is a research engineer and a Ph.D. student at the University of Victoria Victoria British Columbia Canada. He ported the 2D- and 3D-TLM simulators to DECmpp 1200 massively parallel computer using MPL C and C++. He also combined OSA90/hope a commercially available microwave CAD program with a 2D-TLM simulation module for geometry optimization using the Datapipe technique of OSA90/hope. Recently he has developed a distributed client-server computing technique for the TLM method this technique could accelerate the TLM simulation by more than an order of magnitude. Channabasappa Eswarappa received the M.Tech. degree in electrical engineering from the Indian Institute of Technology Kanpur India in 1983 and Ph. D. degree from the University of Ottawa Canada in 1990. He worked as an Assistant Executive Engineer and later as

This paper describes the implementation of transmission-line matrix (TLM) method algorithms on a massively parallel computer (DECmpp 12000), the technique of distributed computing in the UNIX environment, and the combination of TLM analysis with Prony's method as well as with autoregressive moving average (ARMA) digital signal processing for electromagnetic field modelling. By combining these advanced computation techniques, typical electromagnetic field modelling of microwave structures by TLM analysis can be accelerated by a few orders of magnitude.

关键词： Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Empirical testing: The prototyper's evaluation mechanism

引用

NAVAL ENGINEERS JOURNAL 1997年第1期109卷 41-46页

作者： Hafner, AN Arnold N. Hafner Ph.D.:is founder and president of Information Systems Research (ISR). He has twenty-five years of experience in systems development and is published in the field of systems development management. He served as corporate research scientist at Systems Exploration Inc. from 1988 to 1991 program director at Computer Science Corporation from 1983 to 1988 director of operations at Republic Management Systems Corporation from 1981 to 1983 and program manager at Computer Science Corporation from 1972 to 1981. A 1962 graduate of the US. Naval Academy he holds a doctoral degree in human behavior and engineering degrees in electronics and communications. He has taught courses on information systems and systems management at most of the colleges in the San Diego area. Dr. Hafner has presented fourteen refereed research papers while publishing sixteen articles and a book A Manager's Guide to Software System Development.

Evaluating complex systems is the subject of this paper, the third in a series investigating prototyping. It provides an interesting and helpful overview of how to evaluate systems prototypes and outlines the iterative stream of developer-user interactions that is replacing older approaches to testing and evaluating new military systems, which promise to reduce the time required to develop and field future military capabilities. Changes to the acquisition process, such as those the paper sketches, will facilitate the nation's rapid transit through its current revolution in military affairs.

关键词： Systems analysis

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Service Transmission in the ATM Environment using a Distributed Simulator

引用

International Journal of Modelling & Simulation 1996年第1期16卷 30-30页

作者： Koutroubinas, S. Antonakopoulos, T. Stavroulopoulos, C. Makios, V. Laboratory of Electromagnetics Electrical Engineering Department University of Patras 26500 Patras Greece School of Electrical Engineering University of Patras Patras Greece European Economic Community Laboratory of Electromagnetics University of Patras Video Mail Services Technical Chamber of Greece Communications Group Electrical Engineering Department University of Patras Program Committee IEEE Intl. Workshop Rapid Syst. P. Commun. and Computer Societies IEEE Technical University Munich Germany Max Planck Inst. for Plasmaphisics Technical University Munich Germany Max Planck Inst. for Plasmaphisics Munich Germany Department of Electronics Carleton University Ottawa Ont. Canada Carleton University Electromagnetics Laboratory Electrical Engineering Department University of Patras Greece IEEE Canadian Association of Physicist German Physical Society VDE Greek Technical Chamber

This paper presents a distributed simulator for performance analysis of various applications in the asynchronous transfer mode (ATM) environment. The simulator is used to determine how the quality of a service, either synchronous or asynchronous, is affected when it is transmitted through an ATM network under various traffic conditions. The simulator has been implemented in a distributed Unix environment using network and operating system functions and simulates the three lower layers of B-ISDN. It has been based on the time-driven approach, and is modular and expandable because it uses standard operating system calls for adapting new applications and services to the simulator environment. The paper presents performance analysis results of constant and variable bit rate services, as well as experimental results on compressed and uncompressed image transmissions.

关键词： ATM B-ISDN Performance analysis Simulation

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：