检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Zhou, Zongwei Rahman Siddiquee, Md Mahfuzur Tajbakhsh, Nima Liang, Jianming Department of Biomedical Informatics Arizona State University ScottsdaleAZ85259 United States School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ85281 United States

The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations: (1) their optimal depth is apriori unknown, requiring extensive architecture search or inefficient ensemble of models of varying depths;and (2) their skip connections impose an unnecessarily restrictive fusion scheme, forcing aggregation only at the same-scale feature maps of the encoder and decoder sub-networks. To overcome these two limitations, we propose UNet++, a new neural architecture for semantic and instance segmentation, by (1) alleviating the unknown network depth with an efficient ensemble of U-Nets of varying depths, which partially share an encoder and co-learn simultaneously using deep supervision;(2) redesigning skip connections to aggregate features of varying semantic scales at the decoder sub-networks, leading to a highly flexible feature fusion scheme;and (3) devising a pruning scheme to accelerate the inference speed of UNet++. We have evaluated UNet++ using six different medical image segmentation datasets, covering multiple imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI), and electron microscopy (EM), and demonstrating that (1) UNet++ consistently outperforms the baseline models for the task of semantic segmentation across different datasets and backbone architectures;(2) UNet++ enhances segmentation quality of varying-size objects-an improvement over the fixed-depth UNet;(3) Mask RCNN++ (Mask R-CNN with UNet++ design) outperforms the original Mask R-CNN for the task of instance segmentation;and (4) pruned UNet++ models achieve significant speedup while showing only modest performance degradation. Our implementation and pre-trained models are available at https://***/MrGiovanni/UNetPlusPlus. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Clone Swarms: Learning to Predict and Control Multi-Robot systems by Imitation

arXiv

引用

arXiv 2019年

作者： Zhou, Siyu Phielipp, Mariano J. Sefair, Jorge A. Walker, Sara I. Amor, Heni Ben Department of Physics Arizona State University Intel Corporation School of Computing Informatics and Decision Systems Engineering Arizona State University School of Earch and Space Exploration Arizona State University

— In this paper, we propose SwarmNet – a neural network architecture that can learn to predict and imitate the behavior of an observed swarm of agents in a centralized manner. Tested on artificially generated swarm motion data, the network achieves high levels of prediction accuracy and imitation authenticity. We compare our model to previous approaches for modelling interaction systems and show how modifying components of other models gradually approaches the performance of ours. Finally, we also discuss an extension of SwarmNet that can deal with nondeterministic, noisy, and uncertain environments, as often found in robotics applications. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Correction to: 3D Printing in Fiber-Device Technology

引用

Advanced Fiber Materials 2021年第5期3卷 347-347页

作者： van der Elst, Louis Faccini de Lima, Camila Gokce Kurtoglu, Merve Koraganji, Veda Narayana Zheng, Mengxin Gumennik, Alexander Department of Intelligent Systems Engineering Luddy School of Informatics Computing and Engineering Indiana University Bloomington Bloomington USA Fibers and Additive Manufacturing Enabled Systems Laboratory Bloomington USA

A correction to this paper has been published: https://***/10.1007/s42765-021-00074-y

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine learning for modelling unstructured grid data in computational physics: a review

arXiv

引用

arXiv 2025年

作者： Cheng, Sibo Bocquet, Marc Ding, Weiping Finn, Tobias Sebastian Fu, Rui Fu, Jinlong Guo, Yike Johnson, Eleda Li, Siyi Liu, Che Moro, Eric Newton Pan, Jie Piggott, Matthew Quilodran, Cesar Sharma, Prakhar Wang, Kun Xiao, Dunhui Xue, Xiao Zeng, Yong Zhang, Mingrui Zhou, Hao Zhu, Kewei Arcucci, Rossella CEREA ENPC EDF R&D Institut Polytechnique de Paris Île-de-France France School of Artificial Intelligence and Computer Science Nantong University Jiangsu Nantong226019 China School of Mathematical Sciences Key Laboratory of Intelligent Computing and Applications Tongji University Shanghai200092 China School of Engineering and Materials Science Faculty of Science and Engineering Queen Mary University of London LondonE1 4NS United Kingdom Zienkiewicz Centre for Modelling Data and AI Faculty of Science and Engineering Swansea University SwanseaSA1 8EN United Kingdom Department of Computer Science and Engineering Hong Kong university of science and technology Hong Kong Department of Earth Science & Engineering Imperial College London LondonSW7 2AZ United Kingdom Tianjin Key Laboratory of Imaging and Sensing Microelectronics Technology School of Microelectronics Tianjin University Tianjin300072 China Centre for Health Informatics Cumming School of Medicine University of Calgary CalgaryABT2N 1N4 Canada Department of Community Health Sciences Cumming School of Medicine University of Calgary CalgaryABT2N 1N4 Canada Undaunted Grantham Institute for Climate Change and the Environment Imperial College London LondonSW7 2AZ United Kingdom Culham Campus AbingdonOX14 3DB United Kingdom Centre for Computational Science Department of Chemistry University College London LondonWC1E 6BT United Kingdom Concordia Institute for Information Systems Engineering Concordia University MontrealQCH3G 1M8 Canada School of Mechanical Medical and Process Engineering Faculty of Engineering Queensland University of Technology BrisbaneQLD Australia Department of Chemical Engineering University College London LondonWC1E 6BT United Kingdom

Unstructured grid data are essential for modelling complex geometries and dynamics in computational physics. Yet, their inherent irregularity presents significant challenges for conventional machine learning (ML) techniques. This paper provides a comprehensive review of advanced ML methodologies designed to handle unstructured grid data in high-dimensional dynamical systems. Key approaches discussed include graph neural networks, transformer models with spatial attention mechanisms, interpolation-integrated ML methods, and meshless techniques such as physics-informed neural networks. These methodologies have proven effective across diverse fields, including fluid dynamics and environmental simulations. This review is intended as a guidebook for computational scientists seeking to apply ML approaches to unstructured grid data in their domains, as well as for ML researchers looking to address challenges in computational physics. It places special focus on how ML methods can overcome the inherent limitations of traditional numerical techniques and, conversely, how insights from computational physics can inform ML development. To support benchmarking, this review also provides a summary of open-access datasets of unstructured grid data in computational physics. Finally, emerging directions such as generative models with unstructured data, reinforcement learning for mesh generation, and hybrid physics-data-driven paradigms are discussed to inspire future advancements in this evolving field. © 2025, CC BY-NC-SA.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Using CNN with Bayesian optimization to identify cerebral micro-bleeds

Using CNN with Bayesian optimization to identify cerebral mi...

引用

作者： Doke, Piyush Shrivastava, Dhiraj Pan, Chichun Zhou, Qinghua Zhang, Yu-Dong School of Computer Science and Technology Henan Polytechnic University HenanJiaozuo China School of Mathematics and Computer Science Indian Institute of Technology Goa VelingGoa India Department of Mechanical Engineering Indian Institute of Technology Varanasi VaranasiUttar Pradesh India School of Business Nanjing Normal University NanjingJiangsu China Department of Informatics University of Leicester LeicesterLeicestershire United Kingdom Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

This article studies the problem of detecting cerebral micro-bleeds (CMBs) using a convolutional neural network (CNN). Cerebral micro-bleeds (CMBs) are increasingly recognized neuroimaging findings, occurring with cerebrovascular diseases, dementia, and normal aging. Naturally enough, it becomes necessary to detect CMBs in the early stages of life. The focus of this article is to infuse new techniques like Bayesian optimization to find the optimum set of hyper-parameters efficiently, making even the simplest of CNN architectures perform well on the problem. Experimentally, we observe our CNN (five layers, i.e., two convolution, two pooling, and one fully connected) achieves accuracy = 98.97%, sensitivity = 99.66%, specificity = 98.14%, and precision = 98.54% on the test set (hold-out validation) when calculated over an average of ten runs. The proposed model outperformed state-of-the-art methods. © 2020, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

AI recognition of patient race in medical imaging: a modelling study

引用

The Lancet Digital Health 2022年第6期4卷 e406-e414页

作者： Gichoya, Judy Wawira Banerjee, Imon Bhimireddy, Ananth Reddy Burns, John L Celi, Leo Anthony Chen, Li-Ching Correa, Ramon Dullerud, Natalie Ghassemi, Marzyeh Huang, Shih-Cheng Kuo, Po-Chih Lungren, Matthew P Palmer, Lyle J Price, Brandon J Purkayastha, Saptarshi Pyrros, Ayis T Oakden-Rayner, Lauren Okechukwu, Chima Seyyed-Kalantari, Laleh Trivedi, Hari Wang, Ryan Zaiman, Zachary Zhang, Haoran Department of Radiology Emory University Atlanta GA United States Department of Computer Science Emory University Atlanta GA United States School of Computing Informatics and Decision Systems Engineering Arizona State University Tempe AZ United States School of Informatics and Computing Indiana University–Purdue University Indianapolis IN United States Institute for Medical Engineering and Science Massachusetts Institute of Technology Cambridge MA United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA United States Department of Medicine Beth Israel Deaconess Medical Center Boston MA United States Department of Computer Science National Tsing Hua University Hsinchu Taiwan Department of Computer Science University of Toronto Toronto ON Canada Stanford University School of Medicine Palo Alto CA United States Australian Institute for Machine Learning University of Adelaide Adelaide SA Australia School of Public Health University of Adelaide Adelaide SA Australia Florida State University College of Medicine Tallahassee FL United States Dupage Medical Group Hinsdale IL United States Department of Computer Science Georgia Institute of Technology Atlanta GA United States Lunenfeld-Tanenbaum Research Institute Sinai Health Toronto ON Canada Vector Institute for Artificial Intelligence Toronto ON Canada

Background: Previous studies in medical imaging have shown disparate abilities of artificial intelligence (AI) to detect a person's race, yet there is no known correlation for race on medical imaging that would be obvious to human experts when interpreting the images. We aimed to conduct a comprehensive evaluation of the ability of AI to recognise a patient's racial identity from medical images. Methods: Using private (Emory CXR, Emory Chest CT, Emory Cervical Spine, and Emory Mammogram) and public (MIMIC-CXR, CheXpert, National Lung Cancer Screening Trial, RSNA Pulmonary Embolism CT, and Digital Hand Atlas) datasets, we evaluated, first, performance quantification of deep learning models in detecting race from medical images, including the ability of these models to generalise to external environments and across multiple imaging modalities. Second, we assessed possible confounding of anatomic and phenotypic population features by assessing the ability of these hypothesised confounders to detect race in isolation using regression models, and by re-evaluating the deep learning models by testing them on datasets stratified by these hypothesised confounding variables. Last, by exploring the effect of image corruptions on model performance, we investigated the underlying mechanism by which AI models can recognise race. Findings: In our study, we show that standard AI deep learning models can be trained to predict race from medical images with high performance across multiple imaging modalities, which was sustained under external validation conditions (x-ray imaging [area under the receiver operating characteristics curve (AUC) range 0·91–0·99], CT chest imaging [0·87–0·96], and mammography [0·81]). We also showed that this detection is not due to proxies or imaging-related surrogate covariates for race (eg, performance of possible confounders: body-mass index [AUC 0·55], disease distribution [0·61], and breast density [0·61]). Finally, we provide evidence to show that t

关键词：

来源：评论

学校读者我要写书评

暂无评论

The EMPOWER blended digital intervention for relapse prevention in schizophrenia: a feasibility cluster randomised controlled trial in Scotland and Australia

引用

The Lancet Psychiatry 2022年第6期9卷 477-486页

作者： Gumley, Andrew I Bradstreet, Simon Ainsworth, John Allan, Stephanie Alvarez-Jimenez, Mario Aucott, Lorna Birchwood, Maximillian Briggs, Andrew Bucci, Sandra Cotton, Sue M Engel, Lidia French, Paul Lederman, Reeva Lewis, Shôn Machin, Matthew MacLennan, Graeme McLeod, Hamish McMeekin, Nicola Mihalopoulos, Cathy Morton, Emma Norrie, John Schwannauer, Matthias Singh, Swaran P Sundram, Suresh Thompson, Andrew Williams, Chris Yung, Alison R Farhall, John Gleeson, John Glasgow Institute of Health and Wellbeing University of Glasgow Glasgow United Kingdom Division of Psychology and Mental Health School of Health Sciences Faculty of Biology Medicine and Health Manchester Academic Health Science Centre University of Manchester Manchester United Kingdom Division of Informatics Imaging and Data Sciences School of Health Sciences Faculty of Biology Medicine and Health Manchester Academic Health Science Centre University of Manchester Manchester United Kingdom Orygen Melbourne Melbourne VIC Australia Centre for Youth Mental Health University of Melbourne Melbourne VIC Australia School of Computing and Information Systems Faculty of Engineering and Information Technology University of Melbourne Melbourne VIC Australia Centre for Healthcare Randomised Trials (CHaRT) University of Aberdeen Aberdeen United Kingdom Centre for Mental Health and Wellbeing Research Warwick Medical School University of Warwick Warwick United Kingdom Department of Health Services Research and Policy London School of Hygiene & Tropical Medicine London United Kingdom Greater Manchester Mental Health NHS Foundation Trust Manchester United Kingdom School of Public Health and Preventive Medicine Monash University Melbourne VIC Australia Department of Psychiatry School of Clinical Sciences Monash University Melbourne VIC Australia School of Medicine Deakin University Melbourne VIC Australia Department of Psychiatry Manchester Metropolitan University Manchester United Kingdom Department of Psychiatry University of British Columbia Vancouver BC Canada The Usher Institute University of Edinburgh Edinburgh United Kingdom School for Health in Social Sciences University of Edinburgh Edinburgh United Kingdom Mental Health Program Monash Health Melbourne VIC Australia Department of Psychology and Counselling La Trobe University Melbourne VIC Australia NorthWestern Mental Health The Royal Melbourne Hospital Epping VIC Australia Healthy Brain and Mi

Background: Early warning signs monitoring by service users with schizophrenia has shown promise in preventing relapse but the quality of evidence is low. We aimed to establish the feasibility of undertaking a definitive randomised controlled trial to determine the effectiveness of a blended digital intervention for relapse prevention in schizophrenia. Methods: This multicentre, feasibility, cluster randomised controlled trial aimed to compare Early signs Monitoring to Prevent relapse in psychosis and prOmote Well-being, Engagement, and Recovery (EMPOWER) with treatment as usual in community mental health services (CMHS) in Glasgow and Melbourne. CMHS were the unit of randomisation, selected on the basis of those that probably had five or more care coordinators willing to participate. Participants were eligible if they were older than 16 years, had a schizophrenia or related diagnosis confirmed via case records, were able to provide informed consent, had contact with CMHS, and had had a relapse within the previous 2 years. Participants were randomised within stratified clusters to EMPOWER or to continue their usual approach to care. EMPOWER blended a smartphone for active monitoring of early warning signs with peer support to promote self-management and clinical triage to promote access to relapse prevention. Main outcomes were feasibility, acceptability, usability, and safety, which was assessed through face-to-face interviews. App usage was assessed via the smartphone and self-report. Primary end point was 12 months. Participants, research assistants and other team members involved in delivering the intervention were not masked to treatment conditions. Assessment of relapse was done by an independent adjudication panel masked to randomisation group. The study is registered at ISRCTN (99559262). Findings: We identified and randomised eight CMHS (six in Glasgow and two in Melbourne) comprising 47 care coordinators. We recruited 86 service users between Jan 19 and Au

关键词：

来源：评论

学校读者我要写书评

暂无评论

Translating P-log, LPMLN, LPOD, and CR-Prolog2 into standard answer set programs 34

Translating P-log, LPMLN, LPOD, and CR-Prolog2 into standard...

引用

Technical Communications of the 34th International Conference on Logic Programming, ICLP 2018

作者： Yang, Zhun School of Computing Informatics and Decision Systems Engineering Arizona State University P.O. Box 878809 TempeAZ85287 United States

ISBN: (纸本)9783959770903

Answer set programming (ASP) is a particularly useful approach for nonmonotonic reasoning in knowledge representation. In order to handle quantitative and qualitative reasoning, a number of different extensions of ASP have been invented, such as quantitative extensions LPMLN and P-log, and qualitative extensions LPOD, and CR-Prolog2. Although each of these formalisms introduced some new and unique concepts, we present reductions of each of these languages into the standard ASP language, which not only gives us an alternative insight into the semantics of these extensions in terms of the standard ASP language, but also shows that the standard ASP is capable of representing quantitative uncertainty and qualitative uncertainty. What's more, our translations yield a way to tune the semantics of LPOD and CR-Prolog2. Since the semantics of each formalism is represented in ASP rules, we can modify their semantics by modifying the corresponding ASP rules. For future work, we plan to create a new formalism that is capable of representing quantitative and qualitative uncertainty at the same time. Since LPOD rules are simple and informative, we will first try to include quantitative preference into LPOD by adding the concept of weight and tune the semantics of LPOD by modifying the translated standard ASP rules. © Zhun Yang;licensed under Creative Commons License CC-BY

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A clinical decision support system using multi-modality imaging data for disease diagnosis

引用

IISE Transactions on Healthcare systems engineering 2018年第1期8卷 36-46页

作者： Gaw, Nathan Schwedt, Todd J. Chong, Catherine D. Wu, Teresa Li, Jing School of Computing Informatics and Decision Systems Engineering Arizona State University Tempe AZ United States Department of Neurology Mayo Clinic Arizona Phoenix AZ United States

Readily available imaging technologies have made it possible to acquire multiple imaging modalities with complementary information for the same patient. These imaging modalities describe different properties about the organ of interest, providing an opportunity for better diagnosis, staging and treatment assessments. However, existing research in combining multi-modality imaging data has not been transformed into a clinical decision support system due to lack of flexibility, accuracy, and interpretability. This article proposes a multi-modality imaging-based diagnostic decision support system (MMI-DDS) that overcomes limitations of existing research. MMI-DDS includes three inter-connected components: (1) a modality-wise principal component analysis (PCA) that reduces data dimensionality and eliminates the need for co-registration of multi-modality images;(2) a novel constrained particle swarm optimization (cPSO) classifier that is built upon the joint set of the principal components (PCs) from all of the imaging modalities;(3) a clinical utility engine that employs inverse operations to identify contributing imaging features (a.k.a. biomarkers) in diagnosing the disease. To validate MMI-DDS, we apply it to a migraine dataset with multi-modality structural and functional magnetic resonance imaging (MRI) data. MMI-DDS shows significantly improved diagnostic accuracy than using single imaging modalities alone and also identifies biomarkers that are consistent with findings in migraine literature. © 2018 “IISE”.

关键词： classification Clinical decision support disease diagnosis headache migraine multi-modality imaging particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Deep predictive models for collision risk assessment in autonomous driving

Deep predictive models for collision risk assessment in auto...

引用

2018 IEEE International Conference on Robotics and Automation, ICRA 2018

作者： Strickland, Mark Fainekos, Georgios Amor, Heni Ben Informatics and Decision Systems Engineering Arizona State University School of Computing 660 S. Mill Ave TempeAZ85281 United States

ISBN: (纸本)9781538630815

In this paper, we investigate a predictive approach for collision risk assessment in autonomous and assisted driving. A deep predictive model is trained to anticipate imminent accidents from traditional video streams. In particular, the model learns to identify cues in RGB images that are predictive of hazardous upcoming situations. In contrast to previous work, our approach incorporates (a) temporal information during decision making, (b) multi-modal information about the environment, as well as the proprioceptive state and steering actions of the controlled vehicle, and (c) information about the uncertainty inherent to the task. To this end, we discuss Deep Predictive Models and present an implementation using a Bayesian Convolutional LSTM. Experiments in a simple simulation environment show that the approach can learn to predict impending accidents with reasonable accuracy, especially when multiple cameras are used as input sources. © 2018 IEEE.

关键词： Accidents

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：