检索结果-内蒙古大学图书馆

A 3D Transmurally Heterogeneous computational Model of the Brugada Syndrome Phenotype

IEEE ACCESS 2023年 11卷 81711-81724页

作者： Seghetti, Paolo Biasi, Niccolo Tognetti, Alessandro Scuola Super Sant Anna Hlth Sci Interdisciplinary Ctr I-56127 Pisa Italy CNR Inst Clin Physiol I-56124 Pisa Italy Univ Pisa Informat Engn Dept I-56126 Pisa Italy Univ Pisa Res Ctr E Piaggio I-56122 Pisa Italy

In this work, we present a computational study of the Brugada Syndrome (BrS) phenotype aimed at investigating the main factors contributing to the development of arrhythmias. We developed a model that incorporated a BrS substrate within a region resembling the right ventricular outflow tract (RVOT) in a three-dimensional anisotropic ventricular cardiac tissue with transmural heterogeneity. Consistent with our previous two-dimensional study, our results confirmed the requirement of both electrophysiological alterations and structural abnormalities to trigger arrhythmic events. In particular, we found that the combination of electrophysiological alterations and structural abnormalities caused percolation in the tissue, eventually leading to sustained reentry. Moreover, our model is able to replicate the majority of epicardial electrogram features observed in the arrhythmic substrate of Brugada patients, furthermore, the behavior of our model agrees with clinical findings on BrS patients. We identified the density and size of structural abnormalities, the degree of myocyte electrophysiological alteration, and the size of the arrhythmic substrate as risk factors for the genesis of arrhythmias. These findings could be used in a model-based approach to develop processing techniques that highlight arrhythmogenic features in BrS patients' recorded electrograms, improving risk stratification in patients.

关键词： Brugada syndrome computational modeling unipolar electrograms cardiac electrophysiology risk stratification

来源：评论

学校读者我要写书评

暂无评论

FreqSense: Adaptive Sampling Rates for Sensor-Based Human Activity Recognition Under Tunable computational Budgets

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2023年第12期27卷 5791-5802页

作者： Yang, Guangyu Zhang, Lei Bu, Can Wang, Shuaishuai Wu, Hao Song, Aiguo Nanjing Normal Univ Sch Elect & Automat Engn Nanjing 210023 Peoples R China Yunnan Univ Sch Informat Sci & Engn Kunming 650500 Peoples R China Southeast Univ Dept Instrument Sci & Engn Nanjing 210096 Peoples R China

Recent years have witnessed great success of deep convolutional networks in sensor-based human activity recognition (HAR), yet their practical deployment remains a challenge due to the varying computational budgets required to obtain a reliable prediction. This article focuses on adaptive inference from a novel perspective of signal frequency, which is motivated by an intuition that low-frequency features are enough for recognizing "easy" activity samples, while only "hard" activity samples need temporally detailed information. We propose an adaptive resolution network by combining a simple subsampling strategy with conditional early-exit. Specifically, it is comprised of multiple subnetworks with different resolutions, where "easy" activity samples are first classified by lightweight subnetwork using the lowest sampling rate, while the subsequent subnetworks in higher resolution would be sequentially applied once the former one fails to reach a confidence threshold. Such dynamical decision process could adaptively select a proper sampling rate for each activity sample conditioned on an input if the budget varies, which will be terminated until enough confidence is obtained, hence avoiding excessive computations. Comprehensive experiments on four diverse HAR benchmark datasets demonstrate the effectiveness of our method in terms of accuracy-cost tradeoff. We benchmark the average latency on a real hardware.

关键词： Feature extraction Human activity recognition Redundancy computational efficiency computational modeling Adaptive systems Signal resolution Activity recognition sensor convolution adaptive inference sampling rate computational budget

来源：评论

学校读者我要写书评

暂无评论

Crowd Evacuation With Multi-Modal Cooperative Guidance in Subway Stations: computational Experiments and Optimization

引用

IEEE TRANSACTIONS ON computational SOCIAL SYSTEMS 2023年第5期10卷 2536-2545页

作者： Zhou, Min Dong, Hairong Ioannou, Petros A. Wang, Fei-Yue Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China Univ Southern Calif Dept Elect Engn Los Angeles CA 90089 USA Univ Southern Calif Ctr Adv Transportat Technol Los Angeles CA 90089 USA Chinese Acad Sci CASIA State Key Lab Management & Control Complex Syst S Inst Automat Beijing 100190 Peoples R China

Setting up guidance equipment and leaders is widely used as an effective measure to improve the operation and evacuation efficiency of subway stations for the safety of passengers. Cooperation among different kinds of guidance modals can benefit the passenger evacuation process and reduce the operating and management costs as well as the risk of injury to people in subway stations. This article proposes a framework of multimodal cooperative guidance (MMCG) systems for commanding the crowd evacuation in case of emergency, where three types of guidance modes are considered. The bi-level MMCG optimization models are constructed to determine the optimal quantities and initial locations of multimodal guidance. The MMCG schemes are designed by minimizing cost functions taking into account the constraints of the number of guidance, valid coverage, and guiding expectation. An extended social force (SF) model is proposed to study crowd evacuation dynamics with multimodal guidance. The computational experiments are conducted to evaluate the performance of the proposed cooperative guidance schemes at the subway platform scenario. Three unimodal guidance schemes and a contrasted scheme without guidance are also proposed as comparison schemes. The results show that the crowd evacuation efficiency and the utilization ratio of exits are improved by taking into account the cooperation among different guidance modals.

关键词： Public transportation computational modeling Behavioral sciences Force Broadcasting Rails Rail transportation computational experiment crowd evacuation efficiency multimodal cooperative guidance (MMCG) safety social force (SF) model subway station

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Research in Management: A computational Literature Review

引用

IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT 2023年 71卷 5088页

作者： Arsenyan, Jbid Piepenbrink, Anke Rennes Sch Business Rennes 35065 France

Artificial intelligence (AI) spring of the past decade created an increased interest into the topic in business as well as in academia. This resulted in an upward trend in academic publications, not only in computer science but also in management. This article presents a computational literature review with an abstract-based sampling approach to investigate the status of the management literature to take stock of academic research of the past two decades. We analyze 6324 papers from 1990 to 2020 published in five management-related domains and identify 41 distinct topics. We present the evolution of research pre and post AI spring, emerging topics as well as saturated areas. The findings show that the previously disjointed topic network structure is fully connected by early 2010s and the upward trend in management research starts in the period of 2014-2015. The results provide a comprehensive insight into the potential of AI in management versus underdeveloped areas, and presents, for management scholars and practitioners, suggestions about effective adoption of AI practices.

关键词： Artificial intelligence Business Machine learning Inspection Bibliographies Vocabulary computational modeling Artificial intelligence (AI) computational litera-ture review (CLR) latent Dirichlet allocation (LDA) management research

来源：评论

学校读者我要写书评

暂无评论

On the Impact of Prior Experiences in Car-Following Models: Model Development, computational Efficiency, Comparative Analyses, and Extensive Applications

引用

IEEE TRANSACTIONS ON CYBERNETICS 2023年第3期53卷 1405-1418页

作者： Yu, Yang He, Zhengbing Qu, Xiaobo Univ Technol Sydney FEIT Sydney NSW 2007 Australia Chalmers Univ Technol Dept Architecture & Civil Engn S-41296 Gothenburg Sweden Beijing Univ Technol Coll Metropolitan Transportat Beijing 100044 Peoples R China

A major shortcoming of the conventional car-following models is that these models only consider the current spacing and speeds of the target vehicle and its immediate leading vehicle, without taking into account prior driving actions, even for those from the same driver. In other words, the numerous prior experiences have no influence in predicting vehicular movements for the next time step. In this research, we propose a machine-learning-based data-driven methodology that is able to take advantage of the high-resolution historical traffic data in the current data-rich era, to predict vehicular movements in an accurate manner with high computational efficiency. The proposed car-following model has a simple model structure based on a fixed-radius near neighbors (FRNN) search algorithm and it can be applied to high-resolution, real-time vehicle movement prediction, modeling, and control. A comprehensive performance comparison is also conducted among the proposed car-following model, another similar data-driven model, and two conventional formula-based models. The results indicate that the FRNN algorithm-based car-following model is superior to all other three models in terms of prediction accuracy and is more computationally efficient compared to its data-driven-based counterpart. Some extensive applications of the proposed car-following model are also discussed at the end of this article.

关键词： Predictive models computational modeling Data models Prediction algorithms Analytical models Training Real-time systems computational efficiency data-driven car-following model fixed-radius near neighbors (FRNN) algorithm historical traffic data trajectory prediction

来源：评论

学校读者我要写书评

暂无评论

computational Intelligence and Deep Learning for Next-Generation Edge-Enabled Industrial IoT

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2023年第5期10卷 2881-2893页

作者： Tang, Shunpu Chen, Lunyuan He, Ke Xia, Junjuan Fan, Lisheng Nallanathan, Arumugam Guangzhou Univ Sch Comp Sci Guangzhou 510006 Peoples R China Guangzhou Univ Sch Elect & Commun Engn Guangzhou 510006 Peoples R China Guangzhou Univ Sch Comp Sci & Cyber Engn Guangzhou 510006 Peoples R China Univ Luxembourg Interdisciplinary Ctr Secur Reliabil & Trust SnT Signal Proc & Satell Commun Res Grp SIGCOM L-4365 Esch Sur Alzette Luxembourg Queen Mary Univ London Sch Elect Engn & Comp Sci London E1 4NS England

In this paper, we investigate how to deploy computational intelligence and deep learning (DL) in edge-enabled industrial IoT networks. In this system, the IoT devices can collaboratively train a shared model without compromising data privacy. However, due to limited resources in the industrial IoT networks, including computational power, bandwidth, and channel state, it is challenging for many devices to accomplish local training and upload weights to the edge server in time. To address this issue, we propose a novel multi-exit-based federated edge learning (ME-FEEL) framework, where the deep model can be divided into several sub-models with different depths and output prediction from the exit in the corresponding sub-model. In this way, the devices with insufficient computational power can choose the earlier exits and avoid training the complete model, which can help reduce computational latency and enable devices to participate into aggregation as much as possible within a latency threshold. Moreover, we propose a greedy approach-based exit selection and bandwidth allocation algorithm to maximize the total number of exits in each communication round. Simulation experiments are conducted on the classical Fashion-MNIST dataset under a non-independent and identically distributed (non-IID) setting, and it shows that the proposed strategy outperforms the conventional FL. In particular, the proposed ME-FEEL can achieve an accuracy gain up to 32.7% in the industrial IoT networks with the severely limited resources.

关键词： Training computational modeling Servers Data models Artificial intelligence Bandwidth Optimization computational intelligence edge computing exit selection federated learning

来源：评论

学校读者我要写书评

暂无评论

Plug-and-Play Methods for Integrating Physical and Learned Models in computational Imaging: Theory, algorithms, and applications

引用

IEEE SIGNAL PROCESSING MAGAZINE 2023年第1期40卷 85-97页

作者： Kamilov, Ulugbek S. Bouman, Charles A. Buzzard, Gregery T. Wohlberg, Brendt Washington Univ Computat Imaging Grp St Louis MO USA Purdue Univ Elect & Comp Engn & Biomed Engn W Lafayette IN USA Purdue Univ Math Fac W Lafayette IN 47907 USA Los Alamos Natl Lab Theoret Div Los Alamos NM USA

Plug-and-play (PnP) priors constitute one of the most widely used frameworks for solving computational imaging problems through the integration of physical models and learned models. PnP leverages high-fidelity physical sensor models and powerful machine learning methods for prior modeling of data to provide state-of-the-art reconstruction algorithms. PnP algorithms alternate between minimizing a data fidelity term to promote data consistency and imposing a learned regularizer in the form of an image denoiser. Recent highly successful applications of PnP algorithms include biomicroscopy, computerized tomography (CT), magnetic resonance imaging (MRI), and joint ptychotomography. This article presents a unified and principled review of PnP by tracing its roots, describing its major variations, summarizing main results, and discussing applications in computational imaging. We also point the way toward further developments by discussing recent results on equilibrium equations that formulate the problem associated with PnP algorithms.

关键词： Training data Machine learning algorithms computational modeling Magnetic resonance imaging Computed tomography Imaging Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Mathematical modeling of viral infection dynamics and immune response in SARS-CoV-2: A computational framework for testing drug efficacy 43

Mathematical modeling of viral infection dynamics and immune...

引用

43rd Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (IEEE EMBC)

作者： Sharma, Surbhi Saxena, Abha Chel, Soumita Mitra, Kishalay Giri, Lopamudra IIT Hyderabad Dept Chem Engn Sangareddy India

ISBN: (纸本)9781728111797

SARS-CoV-2 has emerged to cause the outbreak of COVID-19, which has expanded into a worldwide human pandemic. Although detailed experimental data on animal experiments would provide insight into drug efficacy, the scientists involved in these experiments would be exposed to severe risks. In this context, we propose a computational framework for studying infection dynamics that can be used to capture the growth rate of viral replication and lung epithelial cell in presence of SARS-CoV-2. Specifically, we formulate the model consisting of a system of non-linear ODEs that can be used for visualizing the infection dynamics in a cell population considering the role of T cells and Macrophages. The major contribution of the proposed simulation method is to utilize the infection progression model in testing the efficacy of the drugs having various mechanisms and analyzing the effect of time of drug administration on virus clearance.

关键词： Drugs COVID-19 Analytical models Pandemics computational modeling Sociology Coronaviruses

来源：评论

学校读者我要写书评

暂无评论

Role of computational modeling in Thoracic Aortic Pathology: A Review

引用

JOURNAL OF CARDIAC SURGERY 2014年第5期29卷 653-662页

作者： Lee, Jake J. D'Ancona, Giuseppe Amaducci, Andrea Follis, Fabrizio Pilato, Michele Pasta, Salvatore Univ Pittsburgh Sch Med Pittsburgh PA USA Mediterranean Inst Transplantat & Adv Specialize Palermo Italy Fdn RiMED I-90133 Palermo Italy

Thoracic aortic diseases are life-threatening conditions causing significant mortality and morbidity despite advances in diagnostic and surgical treatments. computational methods combined with imaging techniques provide quantitative information of disease progression, which may improve clinical treatments and therapeutic strategies for clinical practice. Since hemodynamic and wall mechanics play important roles in the natural history and progression of aortic diseases, we reviewed the potential application of computational modeling of the thoracic aorta. We placed emphasis on the clinical relevance of these techniques for the assessment of aortic dissection, thoracic aortic aneurysm, and aortic coarctation. Current clinical guidelines and treatment are also described. doi: 10.1111/jocs.12413 (J Card Surg 2014;29:653-662)

关键词： computational modeling Natural history Thoracic Aortic Aneurysm thoracic aorta Disease Progression Aorta clinical practice Hemodynamics Aortic Coarctation Morbidity Aortic Diseases

来源：评论

学校读者我要写书评

暂无评论

Biological networks 101: computational modeling for molecular biologists

引用

GENE 2014年第1期533卷 379-384页

作者： Scholma, Jetse Schivo, Stefano Camacho, Ricardo A. Urquidi van de Pol, Jaco Karperien, Marcel Post, Janine N. Univ Twente MIRA Inst Biomed Technol & Tech Med Dept Bioengn NL-7522 NH Enschede Netherlands Univ Twente Fac EEMCS NL-7522 NH Enschede Netherlands

computational modeling of biological networks permits the comprehensive analysis of cells and tissues to define molecular phenotypes and novel hypotheses. Although a large number of software tools have been developed, the versatility of these tools is limited by mathematical complexities that prevent their broad adoption and effective use by molecular biologists. This study clarifies the basic aspects of molecular modeling, how to convert data into useful input, as well as the number of time points and molecular parameters that should be considered for molecular regulatory models with both explanatory and predictive potential. We illustrate the necessary experimental preconditions for converting data into a computational model of network dynamics. This model requires neither a thorough background in mathematics nor precise data on intracellular concentrations, binding affinities or reaction kinetics. Finally, we show how an interactive model of crosstalk between signal transduction pathways in primary human articular chondrocytes allows insight into processes that regulate gene expression. (C) 2013 Elsevier B.V. All rights reserved.

关键词： Signal transduction Gene expression computational modeling Biologist Chondrocyte

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：