检索结果-内蒙古大学图书馆

FedMood: Federated learning on mobile health data for mood detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xu, Xiaohang Peng, Hao Sun, Lichao Bhuiyan, Md Zakirul Alam Liu, Lianzhong He, Lifang School of Cyber Science and Technology Beihang University Beijing100083 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing100083 China Department of Computer Science University of Illinois at Chicago Chicago United States Department of Computer and Information Sciences Fordham University JMH 334 E Fordham Road BronxNY10458 United States Department of Computer Science and Engineering Lehigh University BethlehemPA18015 United States

Depression is one of the most common mental illness problems, and the symptoms shown by patients are not consistent, making it difficult to diagnose in the process of clinical practice and pathological research. Although researchers hope that artificial intelligence can contribute to the diagnosis and treatment of depression, the traditional centralized machine learning needs to aggregate patient data, and the data privacy of patients with mental illness needs to be strictly confidential, which hinders machine learning algorithms clinical application. To solve the problem of privacy of the medical history of patients with depression, we implement federated learning to analyze and diagnose depression. First, we propose a general multi-view federated learning framework using multi-source data,which can extend any traditional machine learning model to support federated learning across different institutions or parties. Secondly, we adopt late fusion methods to solve the problem of inconsistent time series of multi-view data. Finally, we compare the federated framework with other cooperative learning frameworks in performance and discuss the related results. Copyright © 2021, The Authors. All rights reserved.

关键词： data privacy

Learning deterministic hydrodynamic equations from stochastic active particle dynamics

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Maddu, Suryanarayana Vagne, Quentin Sbalzarini, Ivo F. Technische Universität Dresden Faculty of Computer Science Dresden01069 Germany Max Planck Institute of Molecular Cell Biology and Genetics Dresden01307 Germany Center for Systems Biology Dresden Dresden01307 Germany Center for Scalable Data Analytics and Artificial Intelligence ScaDS.AI Dresden Leipzig Germany Cluster of Excellence Physics of Life TU Dresden Germany Max Planck Institute for the Physics of Complex Systems Dresden01187 Germany Department of Genetics and Evolution University of Geneva Switzerland

We present a principled data-driven strategy for learning deterministic hydrodynamic models directly from stochastic non-equilibrium active particle trajectories. We apply our method to learning a hydrodynamic model for the propagating density lanes observed in self-propelled particle systems and to learning a continuum description of cell dynamics in epithelial tissues. We also infer from stochastic particle trajectories the latent phoretic fields driving chemotaxis. This demonstrates that statistical learning theory combined with physical priors can enable discovery of multi-scale models of non-equilibrium stochastic processes characteristic of collective movement in living systems. © 2022, CC BY.

关键词： Stochastic systems

An Acoustic Analysis of Formants between Frequently Smoking Subjects and Non-smoking Subjects 3

学校读者我要写书评

暂无评论

An Acoustic Analysis of Formants between Frequently Smoking ...

3rd Annual Scientific Meeting on Medical Physics and Biophysics, PIT-FMB in conjunction with the 17th South-East Asia Congress of Medical Physics, SEACOMP 2019

作者： Suwandi, G.R.F. Mustajab, M.A. Haekal, M. Khotimah, S.N. Haryanto, F. Nuclear Physics and Biophysics Research Division Department of Physics Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Bandung Indonesia Material Electronics Physics Research Division Department of Physics Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Bandung Indonesia Biophysics Laboratory Department of Physics Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Bandung Indonesia Department of Physics Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Surabaya Indonesia

Smoking is one of the factors that affect the respiratory health of human. A system of respiratory health indicators is needed to prevent the negative effects of smoking at an early stage. The relation between respiratory and vocal coordination can be analysed by measuring the formant frequencies, which indicate the spectral shaping of the human vocal tract. In this study, two groups of subjects with and without smoking habits were studied in terms of their formant frequencies. The results showed that there were statistical significance differences in the four formant frequencies between the two groups. The differences might be due to the changes in the elasticity of the oral cavity, which were affected by the smoke produced from cigarettes. Therefore, we conclude that a smoking person can be identified by the characteristics of their formant frequencies. © Published under licence by IOP Publishing Ltd.

关键词： Smoke

Modeling the Aberrant Behavior of Nigerian Drivers Using the Manchester Driver Behavior Questionnaire

学校读者我要写书评

暂无评论

SSRN

SSRN 2021年

作者： Labbo, Muwaffaq Safiyanu Xinguo, Jiang School of Transportation and Logistics Southwest Jiaotong University West Park High-Tech District Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology West Park High-Tech District Chengdu611756 China Department of Civil Engineering Kano University of Science and Technology Wudil Kano Nigeria

The Driver Behavior Questionnaire (DBQ) is one of the most widely used tool for measuring self-reported driving style and behavior. Nigeria, which is among the top countries with high rate of accident is lacking in behavioral and safety studies. Therefore, the aim of this research was to develop a measurement model for the Nigerian Drivers, and to investigate the factor structure of the DBQ in Nigerian context. 741 Nigerian Drivers of age 18 years and above, with and without driving license participated in the questionnaire. The Confirmatory Factor Analysis (CFA) was used for the development of the Model, in which 20 questions out of 30 were used. Three (H1, H2, and H3) models with different factors were hypothesized, in which the second model H2 was found to be the best performing among the three models, with Violation, Lapses and Aggression as factors. The results were in consistent with the usefulness of the DBQ in characterizing risky behaviors in Nigeria, which can be used in improving road safety. © 2021, The Authors. All rights reserved.

关键词： Factor analysis

Unsupervised hashing with contrastive information bottleneck

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Qiu, Zexuan Su, Qinliang Ou, Zijing Yu, Jianxing Chen, Changyou School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Artificial Intelligence Sun Yat-sen University Guangdong China CSE Department SUNY at Buffalo Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Many unsupervised hashing methods are implicitly established on the idea of reconstructing the input data, which basically encourages the hashing codes to retain as much information of original data as possible. However, this requirement may force the models spending lots of their effort on reconstructing the unuseful background information, while ignoring to preserve the discriminative semantic information that is more important for the hashing task. To tackle this problem, inspired by the recent success of contrastive learning in learning continuous representations, we propose to adapt this framework to learn binary hashing codes. Specifically, we first propose to modify the objective function to meet the specific requirement of hashing and then introduce a probabilistic binary representation layer into the model to facilitate end-to-end training of the entire model. We further prove the strong connection between the proposed contrastive-learning-based hashing method and the mutual information, and show that the proposed model can be considered under the broader framework of the information bottleneck (IB). Under this perspective, a more general hashing model is naturally obtained. Extensive experimental results on three benchmark image datasets demonstrate that the proposed hashing method significantly outperforms existing baselines. © 2021, CC BY.

关键词： Semantics

Likelihood for a Network of Gravitational-Wave Detectors with Correlated Noise

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cireddu, Francesco Wils, Milan Wong, Isaac C.F. Pang, Peter T.H. Li, Tjonnie G.F. Del Pozzo, Walter Leuven Gravity Institute KU Leuven Celestijnenlaan 200D box 2415 Leuven3001 Belgium Department of Physics and Astronomy Laboratory for Semiconductor Physics KU Leuven LeuvenB-3001 Belgium Dipartimento di Fisica "E. Fermi" Università di Pisa PisaI-56127 Italy Department of Physics The Chinese University of Hong Kong N.T. Shatin Hong Kong STADIUS Center for Dynamical Systems Signal Processing and Data Analytics LeuvenB-3001 Belgium Nikhef Science Park 105 Amsterdam1098 XG Netherlands Utrecht University Princetonplein 1 Utrecht3584 CC Netherlands INFN Sezione di Pisa PisaI-56127 Italy

The Einstein Telescope faces a critical data analysis challenge with correlated noise, often overlooked in current parameter estimation analyses. We address this issue by presenting the statistical formulation of the likelihood that includes correlated noise for the Einstein Telescope or any detector network. By considering varying degrees of correlation, we probe the impact of noise correlations on the parameter estimation analysis of a GW150914-like event. We show that neglecting these correlations may significantly reduce the accuracy of the chirp mass reconstruction. This emphasizes how critical a proper treatment of correlated noise is, as presented in this work, to unlocking the wealth of results promised by the Einstein Telescope. © 2023, CC BY.

关键词： Telescopes

The difference in all-cause mortality between COVID-19 patients treated with standard of care plus placebo and those treated with standard of care alone: a network meta-analysis of randomised controlled trials of immunomodulatory kinase inhibitors

学校读者我要写书评

暂无评论

Journal of the Royal Society of Medicine 2024年第2期117卷 57-68页

作者： Tseng, Ping-Tao Zeng, Bing-Syuan Hsu, Chih-Wei Thompson, Trevor Stubbs, Brendon Hsueh, Po-Ren Su, Kuan-Pin Chen, Yen-Wen Chen, Tien-Yu Wu, Yi-Cheng Lin, Pao-Yen Carvalho, Andre F Li, Dian-Jeng Yeh, Ta-Chuan Sun, Cheuk-Kwan Cheng, Yu-Shian Shiue, Yow-Ling Liang, Chih-Sung Tu, Yu-Kang Institute of Biomedical Sciences National Sun Yat-sen University Kaohsiung 80424 Taiwan Department of Psychology College of Medical and Health Science Asia University Taichung 41354 Taiwan Prospect Clinic for Otorhinolaryngology & Neurology Kaohsiung 811 Taiwan Institute of Precision Medicine National Sun Yat-sen University Kaohsiung City 80424 Taiwan Department of Internal Medicine E-Da Cancer Hospital I-Shou University Kaohsiung 824 Taiwan Department of Psychiatry Kaohsiung Chang Gung Memorial Hospital Chang Gung University College of Medicine Kaohsiung 833 Taiwan Centre for Chronic Illness and Ageing University of Greenwich London SE10 9LS United Kingdom Department of Psychological Medicine Institute of Psychiatry Psychology and Neuroscience King’s College London London WC2R 2LS United Kingdom Physiotherapy Department South London and Maudsley NHS Foundation Trust London BR3 3BX United Kingdom Faculty of Health Social Care Medicine and Education Anglia Ruskin University Chelmsford CB1 1PT United Kingdom Departments of Laboratory Medicine and Internal Medicine China Medical University Hospital Taichung 404327 Taiwan School of Medicine China Medical University Taichung 404327 Taiwan College of Medicine China Medical University Taichung 404327 Taiwan Mind-Body Interface Research Center (MBI-Lab) China Medical University and Hospital Taichung 404 Taiwan An-Nan Hospital China Medical University Tainan 709 Taiwan Department of Psychiatry Tri-Service General Hospital School of Medicine National Defense Medical Center Taipei 11490 Taiwan Institute of Brain Science National Yang Ming Chiao Tung University Taipei 112 Taiwan Department of Sports Medicine Landseed International Hospital Taoyuan 32449 Taiwan Institute for Translational Research in Biomedical Sciences Kaohsiung Chang Gung Memorial Hospital Kaohsiung 833 Taiwan Innovation in Mental and Physical Health and Clinical Treatment (IMPACT) Strategic Research Centre School of Medicin

Objectives: The aim of this network meta-analysis (NMA) was to assess whether participants assigned to a placebo and standard of care (SoC) group had different major coronavirus disease 2019 (COVID-19)-related outcomes than those assigned to SoC alone. Design: Frequentist model-based NMA. Setting: We searched for randomised controlled trials (RCTs) of Janus kinase/Bruton tyrosine kinase inhibitors for the management of COVID-19. Participants: Patients with COVID-19 infection. Main outcome measures: The primary outcome was the 28-day all-cause mortality, and secondary outcomes were: (1) use of mechanical ventilation;(2) secondary bacterial infection;(3) acceptability (i.e. drop-out rate);and (4) safety (i.e. serious adverse events). We conducted an NMA using the frequentist model. Effect sizes were estimated using odds ratios (ORs) with 95% confidence intervals (95% CIs). Results: We identified 14 eligible RCTs enrolling a total of 13,568 participants with COVID-19. Participants assigned to placebo plus SoC had a significantly higher risk of 28-day all-cause mortality than those receiving SoC alone (OR = 1.39, 95% CI = 1.07–1.79). This finding did not change substantially by subgroup analysis stratified by epidemiology factor, pandemic history progression and statistical methodologic consideration. In addition, none of the treatments investigated were associated with a significantly different risk of secondary bacterial infection, acceptability or safety compared with the SoC group. Conclusions: This NMA suggested a higher all-cause mortality in patients treated with placebo plus SoC compared with those treated with SoC alone. However, caution is advised in interpreting these results due to the absence of a direct head-to-head comparison. Future research should critically evaluate the necessity of placebo administration in COVID-19 RCTs and consider alternative study designs to minimise potential biases. Trial registration: The current study was approved by the Insti

关键词： COVID-19 immunomodulatory kinase inhibitor mortality Network meta-analysis placebo

Communication-efficient distributed deep learning: Survey, evaluation, and challenges

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shi, Shaohuai Tang, Zhenheng Chu, Xiaowen Liu, Chengjian Wang, Wei Li, Bo Department of Computer Science Hong Kong Baptist University Kowloon Hong Kong College of Big Data and Internet Shenzhen Technology University Shenzhen China Department of Computer Science and Engineering Hong Kong University of Science and Technology Kowloon Hong Kong

In recent years, distributed deep learning techniques are widely deployed to accelerate the training of deep learning models by exploiting multiple computing nodes. However, the extensive communications among workers dramatically limit the system scalability. In this article, we provide a systematic survey of communication-efficient distributed deep learning. Specifically, we first identify the communication challenges in distributed deep learning. Then we summarize the state-of-the-art techniques in this direction, and provide a taxonomy with three levels: optimization algorithm, system architecture, and communication infrastructure. Afterwards, we present a comparative study on seven different distributed deep learning techniques on a 32-GPU cluster with both 10Gbps Ethernet and 100Gbps InfiniBand. We finally discuss some challenges and open issues for possible future investigations. Copyright © 2020, The Authors. All rights reserved.

关键词： Surveys

DynaComm: Accelerating distributed CNN training between edges and clouds through dynamic communication scheduling

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cai, Shangming Wang, Dongsheng Wang, Haixia Lyu, Yongqiang Xu, Guangquan Zheng, Xi Vasilakos, Athanasios V. Department of Computer Science and Technology Tsinghua University Beijing100084 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen518066 China Big Data School Qingdao Huanghai University Qingdao266427 China College of Intelligence and Computing Tianjin University Tianjin300350 China Department of Computing Macquarie University SydneyNSW2109 Australia College of Mathematics and Computer Science Fuzhou University Fuzhou350116 China School of Electrical and Data Engineering University of Technology Sydney Australia Department of Computer Science Electrical and Space Engineering Lulea University of Technology Lulea97187 Sweden

To reduce uploading bandwidth and address privacy concerns, deep learning at the network edge has been an emerging topic. Typically, edge devices collaboratively train a shared model using real-time generated data through the Parameter Server framework. Although all the edge devices can share the computing workloads, the distributed training processes over edge networks are still time-consuming due to the parameters and gradients transmission procedures between parameter servers and edge devices. Focusing on accelerating distributed Convolutional Neural Networks (CNNs) training at the network edge, we present DynaComm, a novel scheduler that dynamically decomposes each transmission procedure into several segments to achieve optimal layer-wise communications and computations overlapping during run-time. Through experiments, we verify that DynaComm manages to achieve optimal layer-wise scheduling for all cases compared to competing strategies while the model accuracy remains untouched. Copyright © 2021, The Authors. All rights reserved.

关键词： Edge computing