检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tahernezhad-Javazm, Farajollah Rankin, Debbie Bois, Naomi Du Smith, Alice E. Coyle, Damien Intelligent Systems Research Center School of Computing Engineering and Intelligent Systems Ulster University LondonderryBT48 7JL United Kingdom The Bath Institute for Augmented Human University of Bath BathBA2 7AY United Kingdom The Department of Industrial and Systems Engineering Department of Computer Science and Software Engineering Auburn University AuburnAL36849 United States

Choosing an appropriate optimization algorithm is essential to achieving success in optimization challenges. Here we present a new evolutionary algorithm structure that utilizes a reinforcement learning-based agent aimed at addressing these issues. The agent employs a double deep q-network to choose a specific evolutionary operator based on feedback it receives from the environment during optimization. The algorithm’s structure contains five single-objective evolutionary algorithm operators. This single-objective structure is transformed into a multi-objective one using the R2 indicator. This indicator serves two purposes within our structure: first, it renders the algorithm multi-objective, and second, provides a means to evaluate each algorithm’s performance in each generation to facilitate constructing the reinforcement learning-based reward function. The proposed R2-reinforcement learning multi-objective evolutionary algorithm (R2-RLMOEA) is compared with six other multiobjective algorithms that are based on R2 indicators. These six algorithms include the operators used in R2-RLMOEA as well as an R2 indicator-based algorithm that randomly selects operators during optimization. We benchmark performance using the CEC09 functions, with performance measured by inverted generational distance and spacing. The R2-RLMOEA algorithm outperforms all other algorithms with strong statistical significance (p © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Video Deepfake Detection

arXiv

引用

arXiv 2023年

作者： Shahzad, Sahibzada Adil Hashmi, Ammarah Peng, Yan-Tsung Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan The Department of Computer Science National Chengchi University Taipei11605 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Multimodal manipulations (also known as audiovisual deepfakes) make it difficult for unimodal deepfake detectors to detect forgeries in multimedia content. To avoid the spread of false propaganda and fake news, timely detection is crucial. The damage to either modality (i.e., visual or audio) can only be discovered through multi-modal models that can exploit both pieces of information simultaneously. Previous methods mainly adopt uni-modal video forensics and use supervised pre-training for forgery detection. This study proposes a new method based on a multi-modal self-supervised-learning (SSL) feature extractor to exploit inconsistency between audio and visual modalities for multi-modal video forgery detection. We use the transformer-based SSL pre-trained Audio-Visual HuBERT (AV-HuBERT) model as a visual and acoustic feature extractor and a multi-scale temporal convolutional neural network to capture the temporal correlation between the audio and visual modalities. Since AV-HuBERT only extracts visual features from the lip region, we also adopt another transformer-based video model to exploit facial features and capture spatial and temporal artifacts caused during the deepfake generation process. Experimental results show that our model outperforms all existing models and achieves new state-of-the-art performance on the FakeAVCeleb and DeepfakeTIMIT datasets. © 2023, CC BY.

关键词： Audio acoustics

来源：评论

学校读者我要写书评

暂无评论

Time-varying cortical connectivity by adaptive multivariate estimators applied to a combined foot-lips movement

Time-varying cortical connectivity by adaptive multivariate ...

引用

29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS 2007), vol.11

作者： L. Astolfi F. Cincotti D. Mattia F. De Vico Fallani A. Colosimo S. Salinari M. G. Marciani M. Ursino M. Zavaglia W. Hesse H. Witte F. Babiloni Department of Computer Science University of Rome La Sapienza and IRCCS Fondazione Santa Lucia Rome Italy Fondazione Santa Lucia IRCCS Rome Italy Centro di Ricerca de La Sapienza per l'Analisi dei Modelli e dell'Informazione nei Sistemi Biomedici Rome Italy Department of Neuroscience Fondazione Santa Lucia University of Roma Tor Vergata Rome Italy DEIS University of Bologna Bologna Italy Institute of Medical Statistics Computer Sciences and Documentation Friedrich-Schiller-Universitat Jena Germany Department of Human Physiology and Pharmacology of the University of Rome La Sapienza and IRCCS Fondazione Santa Lucia Rome Italy

In this paper we propose the use of an adaptive multivariate approach to define time-varying multivariate estimators based on the Directed Transfer Function (DTF) and the Partial Directed Coherence (PDC). DTF and PDC are frequency-domain estimators that are able to describe interactions between cortical areas in terms of the concept of Granger causality. Time-varying DTF and PDC were obtained by the adaptive recursive fit of an MVAR model with time-dependent parameters, by means of a generalized recursive least-square (RLS) algorithm, taking into consideration a set of EEG epochs. Such estimators are able to follow rapid changes in the connectivity between cortical areas during an experimental task. We provide an application to the cortical estimations obtained from high resolution EEG data, recorded from a group of healthy subject during a combined foot-lips movement, and present the time-varying connectivity patterns resulting from the application of both DTF and PDC. Two different cortical networks were detected, one constant across the task and the other evolving during the preparation of the joint movement.

关键词： Electroencephalography Signal processing algorithms Transfer functions Coherence Brain modeling Resonance light scattering Neuroscience humans Physiology computer science

来源：评论

学校读者我要写书评

暂无评论

Erratum to: Effective session key distribution for secure fast handover in mobile networks

引用

Telecommunication Systems 2009年第1期52卷 359-359页

作者： Park, Jong Hyuk Jin, Qun Department of Computer Science and Engineering Seoul National University of Technology Seoul Korea Department of Human Informatics and Cognitive Sciences Waseda University Saitama Japan

来源：评论

学校读者我要写书评

暂无评论

Revisiting Lesion Tracking in 3D Total Body Photography

arXiv

引用

arXiv 2024年

作者： Huang, Wei-Lun Xue, Minghao Liu, Zhiyou Tashayyod, Davood Kang, Jun Gandjbakhche, Amir Kazhdan, Misha Armand, Mehran Johns Hopkins University Whiting School of Engineering Department of Computer Science BaltimoreMD United States Johns Hopkins School of Medicine Department of Dermatology BaltimoreMD United States University of Arkansas Institute for Integrative and Innovative Research Department of Mechanical Engineering AR United States Eunice Kennedy Shriver National Institute of Child Health and Human Development BethesdaMD United States Lumo Imaging RockvilleMD United States

Melanoma is the most deadly form of skin cancer. Tracking the evolution of nevi and detecting new lesions across the body is essential for the early detection of melanoma. Despite prior work on longitudinal tracking of skin lesions in 3D total body photography, there are still several challenges, including 1) low accuracy for finding correct lesion pairs across scans, 2) sensitivity to noisy lesion detection, and 3) lack of large-scale datasets with numerous annotated lesion pairs. We propose a framework that takes in a pair of 3D textured meshes, matches lesions in the context of total body photography, and identifies unmatchable lesions. We start by computing correspondence maps bringing the source and target meshes to a template mesh. Using these maps to define source/target signals over the template domain, we construct a flow field aligning the mapped signals. The initial correspondence maps are then refined by advecting forward/backward along the vector field. Finally, lesion assignment is performed using the refined correspondence maps. We propose the first large-scale dataset for skin lesion tracking with 25K lesion pairs across 198 subjects. The proposed method achieves a success rate of 89.9 % (at 10 mm criterion) for all pairs of annotated lesions and a matching accuracy of 98.2% for subjects with more than 200 lesions. Copyright © 2024, The Authors. All rights reserved.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Clinical "MUTATOME" Of Myelodysplastic Syndrome;Comparison To Primary Acute Myelogenous Leukemia

引用

BLOOD 2013年第21期122卷 518-518页

作者： Makishima, Hideki LaFramboise, Thomas Przychodzen, Bartlomiej P. Yoshida, Kenichi Ruffalo, Matthew Gomez-Segui, Ines Husseinzadeh, Holleh D. Shiraishi, Yuichi Sanada, Masashi Nagata, Yasunobu Sato, Yusuke Sato-Otsubo, Aiko Chiba, Kenichi Tanaka, Hiroko Nakamaki, Tsuyoshi Hofmann, Wolf-Karsten Miyawaki, Shuichi Shih, Lee-Yung Chiba, Shigeru Miyano, Satoru Hosono, Naoko Polprasert, Chantana Thota, Swapna Dienes, Brittney Guinta, Kathryn M. Sauntharatajah, Yogen Sekeres, Mikkael A. Ogawa, Seishi Maciejewski, Jaroslaw P. Translational Hematology and Oncology Research Cleveland Clinic Taussig Cancer Institute Cleveland OH USA Department of Electrical Engineering and Computer Science Case Western Reserve University Cleveland OH USA Department of Pathology and Tumor biology Kyoto University Kyoto Japan Electrical Engineering and Computer Science Case Western Reserve University Cleveland OH USA Hematology Department University Hospital La Fe Valencia Spain Laboratory of DNA Information Analysis Human Genome Center Institute of Medical Science The University of Tokyo Tokyo Japan Department of Pathology and Tumor Biology Graduate School of Medicine Kyoto University Kyoto Japan Cancer Genomics Project Graduate School of Medicine The University of Tokyo Tokyo Japan Laboratory of Sequence Data Analysis Human Genome Center Institute of Medical Science The University of Tokyo Tokyo Japan Division of Hematology Department of Medicine Showa University School of Medicine Tokyo Japan Department of Hematology and Oncology University Hospital Mannheim Mannheim Germany Division of Hematology Department of Internal Medicine Tokyo Metropolitan Ohtsuka Hospital Tokyo Japan Chang Gung Memorial Hospital Taoyuan Taiwan Department of Hematology Faculty of Medicine University of Tsukuba Tsukuba Japan

518

关键词：

来源：评论

学校读者我要写书评

暂无评论

A serious game developed for physical rehabilitation of frail elderly

引用

European Research in Telemedicine 2016年第2期5卷 45-53页

作者： Soares, A.V. Borges Júnior, N.G. Hounsell, M.S. Marcelino, E. Rossito, G.M. Sagawa Júnior, Y. Laboratory for Research in Neurorehabilitation Guilherme Guimbala College R. São José 490 - Anita Garibaldi Joinville CEP 89202-010 SC Brazil Program in Human Movement Science College of Health and Sport Science University of Santa Catarina State Campus Universitário Reitor João David Ferreira Lima bairro Trindade Trindade–Florianópolis–SC CEP 88040-900 Brazil Laboratory for Research on Visual Applications (LARVA) State University of Santa Catarina (UDESC) Computer Science Department (DCC) Campus Universitário S/N CEP 890233-100 Joinville SC Brazil Laboratory of Clinical Functional Exploration of Movement University Hospital of Besançon Bâtiment Magenta 3 boulevard Alexander-Fleming Besançon cedex 25030 France Integrative and Clinical Neurosciences EA481 Bourgogne Franche-Comte University 2 place du Maréchal-Leclerc Besançon cedex 25030 France

Introduction Serious games (SGs) have been used to increase the level of physical activity, balance training and muscle strength in older people with frailty syndrome (FS). The aim of this study was to evaluate the effects of an exercise program with a SG developed for the rehabilitation of older people. Materials and methods In this quasi-experimental study, 24 institutionalized older people with average (SD) age of 80.9 (5.6) years old (16 women) were distributed into two groups (experimental and control). The SG exercise program was conducted twice a week for three months (20 sessions of 15 to 25 minutes). The participants were evaluated in terms of mobility with the Timed Up and Go Test (TUG), balance with the Functional Reach Test (FRT), and strength with dynamometer measurements of hand-grip, upper and lower limbs. Results Only the experimental group showed significant changes in post-test measurements regarding functional mobility (TUG: d = −1.3, p = 10⁻⁴), balance (FRT: d = 1.2, p = 0.003), and upper and lower limb strengths (d = [0.2–0.6], p = [0.04–0.01]). Discussion The results are in line with previous studies suggesting that the SG could integrate the therapeutic repertoire to increase the level of physical activity. Moreover, physical stimulation of older people with SGs is a viable and interesting strategy to involve them in the rehabilitation process. Conclusions The exercise program with the SG resulted in significant improvements in terms of balance, mobility and strength of large muscle groups of older people with FS. This SG has a potential for home or institutional use, since it is relatively safe, allows the training of important functions in older people and could help the stimulation and the monitoring of patients in treatment by the health team. © 2016 Elsevier Masson SAS

关键词： Exercise Frail elderly Older adults Rehabilitation Serious games

来源：评论

学校读者我要写书评

暂无评论

Confidentiality Guaranteed E-Health Treatment for Cloud Cover Enhanced Systems Based on IoT

引用

Journal of Physics: Conference Series 2021年第4期1964卷

作者： P Kiran Kumar Reddy A Narasima Venkatesh S S Arumugam J Jegan Amarnath Department of Computer Science and Engineering Malla Reddy Institute of Engineering and Technology Secunderabad Telangana India Department of MBA-Human Resource Management R.V. Institute of Management Bangalore Karnataka India Department of Computer Science and Engineering Chennai Institute of Technology Malayambakkam Tamil Nadu India Department of Computer Science and Engineering Sri Sairam Engineering College Chennai Tamil Nadu India

The advances made with Internet-of- Things (IoTs) on networking technologies and hardware has made for an at the moment more relaxed human life. In addition to the so -called 'intelligent' settings, e-healthcare services, as well as real-time diagnoses and diagnostic consulting, have increasingly been integrated into IoT. Cloud cover layers have also been hired, and have demonstrated their utility by offering quick response time and low latency to increase the capability of IoT based health systems. Such a development, however, retains the privacy of users as a serious obstacle, to some degree solving security/privacy problems. Such technology still had less privacy controls when it was at a childhood stage. Therefore, our latest work is on an eHealth System for the security of privacy problems in electronic medical reports (EMR). In addition, we have interacted with and compared work on the proposed work in terms of reaction time and delay. The findings demonstrate the complete work in conjunction with normal network parameters is effective to provide privacy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meet the Engineering Education Pioneers — Panel & Roundtable

Meet the Engineering Education Pioneers — Panel & Roundtabl...

引用

Frontiers in Education (FIE) Conference

作者： Samantha Brunhaver Ken Yasuhara Jennifer Case Wendy Newstetter Jennifer Turns Adam Carberry Cheryl Allendoerfer Cynthia Finelli Sheri Sheppard Jeremi London Cynthia Atman Ann McKenna Karl Smith Karan Watson The Polytechnic School Arizona State University Mesa Arizona USA College of Engineering University of Washington Seattle Washington USA Department of Engineering Education Virginia Tech Blacksburg Virginia USA College of Engineering Georgia Institute of Technology Atlanta Georgia USA Department of Human Centered Design and Engineering University of Washington Seattle Washington USA Shoreline Community College Shoreline Washington USA Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor Michigan USA Department of Mechanical Engineering Stanford University Stanford California USA School of Engineering Education Purdue University West Lafayette Indiana USA Department of Electrical and Computer Engineering Texas A&M University College Station Texas USA

ISBN: (纸本)9781538611753;9781538611746

This panel session combines principles from graduate student socialization and intergenerational mentorship to provide a unique opportunity for early career scholars and pioneers in engineering education to interact face-to-face. Pioneers will serve as panelists and give their personal tips and reflections on networking and mentorship. Session attendees will then meet with the pioneers in a roundtable format, to ask questions, seek advice, and get feedback. This work builds on the National science Foundation-funded Engineering Education Pioneers Project, which documented the stories of more than 40 engineering education pioneers through online profiles. The intended audience for this panel includes graduate students, junior faculty, and other individuals interested in the engineering education community. Expected benefits include better understanding, increased belonging, and new or enhanced interest in engineering education. Future efforts associated with this session include understanding the impact of such exposure to the pioneers on attendees and exploring the possibility of offering this event at future engineering education conferences.

关键词： Engineering education Mentoring Engineering profession History Reflection Trajectory

来源：评论

学校读者我要写书评

暂无评论

Search for neutrino-less double beta decay by CANDLES

引用

AIP Conference Proceedings 2013年第1期1533卷 115-120页

作者： S. Umehara T. Kishimoto M. Nomachi S. Yoshida S. Ajimura K. Suzuki K. Ichimura K. Matsuoka N. Nakatani G. Ito H. Kakubata M. Saka W. Wang J. Takemoto W. Chan M. Doihara Y. Tamagawa I. Ogawa S. Ueno S. Maeda A. Yamamoto S. Tomita G. Fujita A. Kawamura T. Harada K. Fushimi R. Hazama H. Ohsumi K. Okada Research Center for Nuclear Physics Osaka University Ibaraki Osaka 560-0047 Japan Graduate School of Science Osaka University Toyonaka Osaka 560-0043 Japan Graduate School of Engineering University of Fukui Fukui 910-8507 Japan Faculty of Integrated Arts and Science The University of Tokushima Tokushima 770-8502 Japan Faculty of Human Environment Osaka Sangyo University Daito Osaka 574-8530 Japan Faculty of Culture and Education Saga University Saga 840-8502 Japan Department of Computer Science and Engineering Kyoto San-gyo University Kyoto 603-8555 Japan

CANDLES is the project to search for neutrino-less double beta decay (0νββ) of 48Ca . The observation of 0νββ will prove existence of a massive Majorana neutrino. Now we installed the CANDLES III system at Kamioka underground laboratory. Here performances of the system for background rejection are presented. It is also described current status of development for the detector system.

关键词：

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：