检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina Aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential. © 2024, CC BY-NC-ND.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Determining clinically relevant features in cytometry data using persistent homology

arXiv

引用

arXiv 2022年

作者： Mukherjee, Soham Wethington, Darren Dey, Tamal K. Das, Jayajit Computer Science Department Purdue University West LafayetteIN United States Biomedical Science Graduate Program Wexner College of Medicine The Ohio State University ColumbusOH United States Biophysics Program The Ohio State University ColumbusOH United States Battelle Center for Mathematical Medicine Abigail Wexner Research Institute Nationwide Children’s Hospital ColumbusOH United States Departments of Pediatrics Biomedical Informatics Pelotonia Institute of Immuno-Oncology Wexner College of Medicine The Ohio State University ColumbusOH United States

Cytometry experiments yield high-dimensional point cloud data that is difficult to interpret manually. Boolean gating techniques coupled with comparisons of relative abundances of cellular subsets is the current standard for cytometry data analysis. However, this approach is unable to capture more subtle topological features hidden in data, especially if those features are further masked by data transforms or significant batch effects or donor-to-donor variations in clinical data. We present that persistent homology, a mathematical structure that summarizes the topological features, can distinguish different sources of data, such as from groups of healthy donors or patients, effectively. Analysis of publicly available cytometry data describing non-naïve CD8+ T cells in COVID-19 patients and healthy controls shows that systematic structural differences exist between single cell protein expressions in COVID-19 patients and healthy controls. We identify proteins of interest by a decision-tree based classifier, sample points randomly and compute persistence diagrams from these sampled points. The resulting persistence diagrams identify regions in cytometry datasets of varying density and identify protruded structures such as ‘elbows’. We compute Wasserstein distances between these persistence diagrams for random pairs of healthy controls and COVID-19 patients and find that systematic structural differences exist between COVID-19 patients and healthy controls in the expression data for T-bet, Eomes, and Ki-67. Further analysis shows that expression of T-bet and Eomes are significantly downregulated in COVID-19 patient non-naïve CD8+ T cells compared to healthy controls. This counter-intuitive finding may indicate that canonical effector CD8+ T cells are less prevalent in COVID-19 patients than healthy controls. This method is applicable to any cytometry dataset for discovering novel insights through topological data analysis which may be difficult to ascertain otherwise

关键词： T-cells

来源：评论

学校读者我要写书评

暂无评论

Precision Rehabilitation for Patients Post-Stroke based on Electronic Health Records and Machine Learning

arXiv

引用

arXiv 2024年

作者： Gao, Fengyi Zhang, Xingyu Sivarajkumar, Sonish Denny, Parker E. Aldhahwani, Bayan M. Visweswaran, Shyam Shi, Ryan Hogan, William Bove, Allyn Wang, Yanshan Department of Health Information Management University of Pittsburgh PittsburghPA United States Department of Communication Science and Disorders University of Pittsburgh PittsburghPA United States Intelligent Systems Program School of Computing and Information University of Pittsburgh PittsburghPA United States Department of Physical Therapy University of Pittsburgh PittsburghPA United States Department of Medical Rehabilitation Sciences Umm Al-Qura University Makkah Saudi Arabia Department of Biomedical Informatics University of Pittsburgh PittsburghPA United States Department of Computer Science University of Pittsburgh Medical Center PittsburghPA United States Data Science Institute Medical College of Wisconsin MilwaukeeWI United States Hillman Cancer Center University of Pittsburgh Medical Center PittsburghPA United States

Objective In this study, we utilized statistical analysis and machine learning methods to examine whether rehabilitation exercises can improve patients post-stroke functional abilities, as well as forecast the improvement in functional abilities. Our dataset is patients’ rehabilitation exercises and demographic information recorded in the unstructured electronic health records (EHRs) data and free-text rehabilitation procedure notes. Through this study, our ultimate goal is to pinpoint the specific rehabilitation exercises that can effectively aid post-stroke patients in improving their functional outcomes in basic mobility (BM) and applied cognitive (AC) domains. Data sources We collected data for 265 stroke patients from the University of Pittsburgh Medical Center, accessed through the Rehabilitation Datamart With informatics iNfrastructure for Research (ReDWINE). Methods We employed a pre-existing natural language processing (NLP) algorithm to extract data on rehabilitation exercises and developed a rule-based NLP algorithm to extract Activity Measure for Post-Acute Care (AM-PAC) scores, covering basic mobility (BM) and applied cognitive (AC) domains, from procedure notes. AM-PAC scores were collected at the initial rehabilitation visit and followed up at one and two months—key recovery periods. Changes in AM-PAC scores were classified based on the minimal clinically important difference (MCID), and significance was assessed using Friedman and Wilcoxon tests. To identify impactful exercises, we used Chi-square tests, Fisher's exact tests, and logistic regression for odds ratios. Additionally, we developed five machine learning models—logistic regression (LR), Adaboost (ADB), support vector machine (SVM), gradient boosting (GB), and random forest (RF)—to predict outcomes in functional ability. Results Statistical analyses revealed significant associations between functional improvements and specific exercises. In the AC domain, the BALANCE exercise showed substant

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

A Consensus Privacy Metrics Framework for Synthetic Data

arXiv

引用

arXiv 2025年

作者： Pilgram, Lisa Dankar, Fida K. Drechsler, Jörg Elliot, Mark Domingo-Ferrer, Josep Francis, Paul Kantarcioglu, Murat Kong, Linglong Malin, Bradley Muralidhar, Krishnamurty Myles, Puja Prasser, Fabian Raisaro, Jean Louis Yan, Chao El Emam, Khaled School of Epidemiology and Public Health University of Ottawa ON Canada CHEO Research Institute ON Canada Department of Nephrology and Medical Intensive Care Charité – Universitätsmedizin Berlin Berlin Germany Department for Statistical Methods Institute for Employment Research Nuernberg Germany Institute for Statistics Ludwig-Maximilians-Universität Munich Germany Joint Program in Survey Methodology University of Maryland United States The Cathie Marsh Institute Research School of Social Sciences University of Manchester Manchester United Kingdom Department of Computer Engineering and Mathematics Universitat Rovira i Virgili Catalonia Tarragona Spain Max Planck Institute for Software Systems Germany Department of Computer Science Virginia Tech United States Department of Mathematical and Statistical Sciences University of Alberta Alberta Canada Department of Biomedical Informatics Vanderbilt University Medical Center NashvilleTN United States Department of Biostatistics Vanderbilt University Medical Center NashvilleTN United States Department of Computer Science Vanderbilt University NashvilleTN United States Department of Marketing and Supply Chain Management University of Oklahoma Oklahoma United States Medicines and Healthcare products Regulatory Agency London United Kingdom Berlin Institute of Health at Charité Universitätsmedizin Berlin Medical Informatics Group Berlin Germany Biomedical Data Science Center University Hospital Lausanne Lausanne Switzerland

Synthetic data generation is one approach for sharing individual-level data. However, to meet legislative requirements, it is necessary to demonstrate that the individuals’ privacy is adequately protected. There is no consolidated standard for measuring privacy in synthetic data. Through an expert panel and consensus process, we developed a framework for evaluating privacy in synthetic data. Our findings indicate that current similarity metrics fail to measure identity disclosure, and their use is discouraged. For differentially private synthetic data, a privacy budget other than close to zero was not considered interpretable. There was consensus on the importance of membership and attribute disclosure, both of which involve inferring personal information about an individual without necessarily revealing their identity. The resultant framework provides precise recommendations for metrics that address these types of disclosures effectively. Our findings further present specific opportunities for future research that can help with widespread adoption of synthetic data. © 2025, CC BY.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Applying Graph Theory and Mathematical-Computational Modelling to Study a Neurophysiological Circuit

引用

Open Journal of Modelling and Simulation 2021年第2期9卷 159-171页

作者： Camila de Andrade Kalil Maria Clícia Stelling de Castro Dilson Silva Célia Martins Cortez Postgraduate Program in Computational Sciences Rio de Janeiro State University Rio de Janeiro Brazil Department of Informatics and Computer Science Rio de Janeiro State University Rio de Janeiro Brazil Department of Applied Mathematics Rio de Janeiro State University Rio de Janeiro Brazil

The aim of the present study is to contribute to the knowledge about the functioning of the neuronal circuits. We built a mathematical-computational model using graph theory for a complex neurophysiological circuit consisting of a reverberating neuronal circuit and a parallel neuronal circuit, which could be coupled. Implementing our model in C++ and applying neurophysiological values found in the literature, we studied the discharge pattern of the reverberant circuit and the parallel circuit separately for the same input signal pattern, examining the influence of the refractory period and the synaptic delay on the respective output signal patterns. Then, the same study was performed for the complete circuit, in which the two circuits were coupled, and the parallel circuit could then influence the functioning of the reverberant. The results showed that the refractory period played an important role in forming the pattern of the output spectrum of a reverberating circuit. The inhibitory action of the parallel circuit was able to regulate the reverberation frequency, suggesting that parallel circuits may be involved in the control of reverberation circuits related to motive activities underlying precision tasks and perhaps underlying neural work processes and immediate memories.

关键词： Mathematical-Computational Modelling Neurophysiological Circuit Reverberating Circuit Parallel Circuit

来源：评论

学校读者我要写书评

暂无评论

Detection Of CT - Scan Lungs COVID-19 Image Using Convolutional Neural Network And CLAHE

Detection Of CT - Scan Lungs COVID-19 Image Using Convolutio...

引用

International Conference on Information and Communications Technology (ICOIACT)

作者： Ronaldus Morgan James Andi Sunyoto Master Program of Informatics Engineering Universitas Amikom Yogyakarta Yogyakarta Indonesia Faculty of Computer Science Universitas Amikom Yogyakarta Yogyakarta Indonesia

ISBN: (数字)9781728173566

ISBN: (纸本)9781728173573

Detecting COVID-19 is a significant task for medical professionals today because of its rapid spread. To overcome this problem, medical professionals have used various techniques and methods to detect to inhibit the proliferation of COVID-19. CT (Computed Tomography) Scan is currently the best method for detecting COVID-19. This diagnostic method is very accurate because it can see organs in three dimensions. However, this method requires a radiologist to detect the disease and requires a long time, which means it will cut valuable time for medical practitioners if a patient is sick. Therefore it is necessary to implement a system to detect the coronavirus automatically as an alternative quickly. This study intends to help medical practitioners to detect computed tomography (CT) Scans of lungs infected with COVID-19. The methods to be used are Limited Adaptive histogram equalization (CLAHE) contrast to improve the quality of CT (Computed Tomography) Scan images of COVID-19 lungs and Convolutional Neural Network (CNN) for the image classification process. The dataset used is 698 RGB images. This study uses three convolutional layers, 3 Max-Pooling layers, and two fully connected layers, resulting in 83.28% accuracy.

关键词： COVID-19 Histograms Computed tomography Neural networks Lung Convolutional neural networks Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

The Smart Analysis of Performing Scalable Inference for Big Data Analytics

The Smart Analysis of Performing Scalable Inference for Big ...

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Vishakha D Bhandarkar Aruna Sri Rongali Mohamed Dawood Shamout Prof. Sachin Pund Gigih Forda Nama Shrishailappa Patil Applied Mathematics and Humanities Yeshwantrao Chavan College of Engineering India Graduate Doctoral Information Technology/Graduate (Information Technology Emphasis/Information Technology Ph.D.) University of The Cumberlands US Department of Management College of Business Administration University of Sharjah Sharjah United Arab Emirates Department of Industrial Engineering Shri Ramdeobaba College of Engineering and Management Nagpur Maharashtra India Department of Informatics Doctoral Program of Environtmental Science University of Lampung Bandar Lampung Computer engineering Vishwakarma Institute of Technology Pune

This paper examines the reproducibility of massive information analytics under particular factors. The paper proposes the “performing Scalable Inference” technique to cope with scalability troubles and to exploit current big statistics platforms for efficient computing and statistics garage of the statistics. In particular, the paper describes how to perform leak-free, parallelizable visible analytics over massive datasets using present extensive records analytics frameworks such as Apache Flink. This method presents an automated manner to execute analytics that preserves reproducibility and the ability to make adjustments without re-running the entire technique. The paper also demonstrates how these analytics may help several real-world use instances, explore affected person cohorts for studies, and develop stratified patient cohorts for hospital therapy. In the end, the paper observes how the proposed method may be exercised within the real world. Actively scalable inference for massive information analytics is pivotal in optimizing decision-making and allocation of assets. Typically, such inferences are made based on information accumulated from numerous sources, databases, unstructured data, and different digital sources. So one can ensure scalability, a complete cloud-primarily based platform has to be hired. This solution will permit the ***, deploying the essential records series and evaluation algorithms are prime here. It could permit the platform to recognize the styles inside the statistics and discover any ability correlations or traits. Additionally, predictive analytics and system mastering strategies may be incorporated to provide insights into the results of the information. In the long run, by leveraging those techniques, the platform can draw efficient inferences and appropriately compare situations in an agile and green way..

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feasibility study of Information Technology Investment (a case study of ODOO ERP: Project Management Module Implementation in Indonesia Based Company) 10

Feasibility study of Information Technology Investment (a ca...

引用

10th International Conference on ICT for Smart Society, ICISS 2019

作者： Jingga, Fredy Kosala, Raymond Supangkat, Suhono Harso Ranti, Benny School of Information Systems Bina Nusantara University Computer Science Department BINUS Graduate Program-Doctor of Computer Science Information Systems Department Jakarta11480 Indonesia Bina Nusantara University Computer Science Department BINUS Graduate Program-Doctor of Computer Science Jakarta11480 Indonesia Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9781728148809

IT Governance are one of the needs in managing Enterprise Level IT. This study shows part of the decision domain of IT Governance Help, which are IT Investment and Prioritization. The purpose of this study is to determine feasibility of implementation open source ERP system Odoo project management module that replaces current system based on operational, economic, and technical aspects. The method used are Fit/Gap Analysis and Cost Benefit model using economic impact worksheet. The analysis is done by comparing the requirement with features owned by current system and Odoo ERP system. This research resulted that Odoo ERP System is feasible in the 3 aspects, the operational feasibility Odoo reaching 72% Fit, the economic feasibility with ROI of 84%, and technical feasibility indicating the technical requirement can be fulfilled by leasing AWS server. The conclusion is the open source ERP system Odoo project management module is feasible to be applied in terms of 3 aspects that have been studied, those are operational, economic, and technical. © 2019 IEEE.

关键词： Cost benefit analysis

来源：评论

学校读者我要写书评

暂无评论

Crowdsourcing Urban Narratives for a Post-Pandemic World

Crowdsourcing Urban Narratives for a Post-Pandemic World

引用

International Conference on computer Supported Cooperative Work in Design

作者： Ramon Chaves Daniel Schneider Claudia Motta António Correia Hugo Paredes Bárbara Caetano Jano Moreira de Souza Postgraduate Program in Informatics PPGI/UFRJ Rio de Janeiro Brazil Tércio Pacitti Institute of Computer Applications and Research (NCE) Federal University of Rio de Janeiro Brazil INESC TEC and University of Trás-os-Montes e Alto Douro UTAD Vila Real Portugal Systems Engineering and Computer Science Program (PESC/COPPE/UFRJ) Rio de Janeiro Brazil

ISBN: (纸本)9781728165974;9781728165981

Over the past decades, the use of digital technologies to support participatory urban planning and design has been repeatedly described as a crucial instrument and critical building block for tackling historical problems of participation in such processes. Social media, e-participation platforms, and crowdsourcing applications are examples of technologies that can involve citizens in decision-making processes and thus leverage the benefits of collective intelligence. However, despite the extensive use of social media platforms, old problems related to engagement and participation still occur in digital initiatives. Successful collaboration examples between citizens, policymakers, and strategic stakeholders are still scarce based on online social practices. This study aims to introduce a collective intelligence model, which combines crowdsourcing and social storytelling to support participatory urban planning and design from a bottom-up perspective. The paper concludes by discussing a scenario where citizens can engage in mapping, taking photos, sending ideas, or even creating collective stories about their university issues in a post-pandemic future.

关键词： Crowdsourcing Social networking (online) Smart cities Instruments Urban planning Collective intelligence Tools

来源：评论

学校读者我要写书评

暂无评论

Model-Based Analysis of Microservice Resiliency Patterns

Model-Based Analysis of Microservice Resiliency Patterns

引用

Working IEEE/IFIP Conference on Software Architecture

作者： Nabor C. Mendonca Carlos M. Aderaldo Javier Camara David Garlan Post Graduate Program in Applied Informatics University of Fortaleza Brazil Post Graduate Program in Applied Informatics University of Fortaleza CE Brazil University of York York UK School of Computer Science Carnegie Mellon University Pittsburgh PA USA

ISBN: (数字)9781728146591

ISBN: (纸本)9781728146607

Microservice application developers try to mitigate the impact of partial outages typically by implementing service-to-service interactions that use well-known resiliency patterns, such as Retry, Fail Fast, and Circuit Breaker. However, those resiliency patterns-as well as their available open-source implementations-are often documented informally, leaving it up to application developers to figure out when and how to use those patterns in the context of a particular microservice application. In this paper, we take a first step towards improving on this situation by introducing a model checking-based approach in which we use the PRISM probabilistic model checker to analyze the behavior of the Retry and Circuit Breaker resiliency patterns as continuous-time Markov chains (CTMC). This approach has enabled us to quantify the impact of applying each resiliency pattern on multiple quality attributes, as well as to determine how to best tune their parameters to deal with varying service availability conditions, in the context of a simple client-service interaction scenario.

关键词： Circuit breakers Resilience Integrated circuit modeling Probabilistic logic Transient analysis Circuit faults Analytical models

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：