检索结果-内蒙古大学图书馆

2018 IEEE MIT Undergraduate Research Technology Conference, URTC 2018

作者： Friend, Julia Hauck, Alec Kurada, Sruthi Hartvigsen, Thomas Sen, Cansu Rundensteiner, Elke A. Oberlin College Department of Computer Science United States Valparaiso University United States Advanced Math and Science Academy Charter School Marlborough United Kingdom Data Science Program Worcester Polytechnic Institute Worcester Polytechnic Institute Computer Science Department United States

ISBN: (纸本)9781538693742

Multivariate time series data are littered with missing values across many domains. Often the patterns of missing data points reflect conscious decisions by the data collector, and thus may contain correlations that can be used to more accurately classify the data. Previous works propose machine learning models that are capable of detecting these correlations in order to achieve highly accurate results. We review the literature and identify a rich variety of strategies along the machine learning pipeline for handling missing values, including forward imputation, appending additional missing indicators, and others. We also study different deep learning methods for handling time series data, namely GRU and LSTM cells. We then design an experimental study for investigating the relative effectiveness of different state-of-the-art methods for handling missing values to more fully comprehend the intricacies of missing data. For the experimental evaluation study, we utilize MIMIC-III, a publicly available critical care dataset composed of Electronic Health Records (EHR) for over 58,000 hospital admissions collected at Beth Israel Deaconess Medical Center from 2001 to 2012. In particular, our experimental study compares variety of missingness-aware machine learning methods for predicting patient mortality, a benchmark task for this database. We validate in general that extracting information from missing values indeed improves predictive accuracy, and we observe that GRU and LSTM cells perform comparably with the forward imputation method further impacting the resulting accuracy for both models. © 2018 IEEE.

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

Forecasting Smart Meter Energy Usage Using Distributed Systems and Machine Learning

Forecasting Smart Meter Energy Usage Using Distributed Syste...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Chris Dong Lingzhi Du Feiran Ji Zizhen Song Yuedi Zheng Alexander Howard Paul Intrevado Diane Myung-kyung Woodbridge Alexander J. Howard Data Science Program University of San Francisco Data Science ProgramUniversity of San Francisco

In this research, we explore the technical and computational merits of a machine learning algorithm on a large data set, employing distributed systems. Using 167 million (10 GB) energy consumption observations collected by smart meters from residential consumers in London, England, we predict future residential energy consumption using a Random Forest machine learning algorithm. Distributed systems such as AWS S3 and EMR, MongoDB and Apache Spark are used. Computational times and predictive accuracy are evaluated. We conclude that there are significant computational advantages to using distributed systems when applying machine learning algorithms on large-scale data. We also observe that distributed systems can be computationally burdensome when the amount of data being processed is below a threshold at which it can leverage the computational efficiencies provided by distributed systems.

关键词： Sparks Energy consumption Distributed databases Smart meters Machine learning Machine learning algorithms Meteorology

来源：评论

学校读者我要写书评

暂无评论

A T cell resilience model associated with response to immunotherapy in multiple tumor types (May, 10.1038/s41591-022-01799-y, 2022)

引用

NATURE MEDICINE 2022年第10期28卷 2219-2219页

作者： Zhang, Yu Vu, Trang Palmer, Douglas C. Kishton, Rigel J. Gong, Lanqi Huang, Jiao Nguyen, Thanh Chen, Zuojia Smith, Cari Livak, Ferenc Paul, Rohit Day, Chi-Ping Wu, Chuan Merlino, Glenn Aldape, Kenneth Guan, Xin-yuan Jiang, Peng Cancer Data Science Laboratory Center for Cancer Research National Cancer Institute National Institutes of Health Bethesda MD USA Department of Clinical Oncology The University of Hong Kong Hong Kong China Sun Yat-sen University Cancer Center State Key Laboratory of Oncology in South China Collaborative Innovation Center for Cancer Medicine Guangzhou China Surgery Branch National Cancer Institute National Institutes of Health Bethesda MD USA Laboratory of Pathology Center for Cancer Research National Cancer Institute National Institutes of Health Bethesda MD USA Experimental Immunology Branch Center for Cancer Research National Cancer Institute National Institutes of Health Bethesda MD USA Laboratory Animal Science Program Leidos Biomedical Research Inc Frederick MD USA Flow Cytometry Core Center for Cancer Research National Cancer Institute National Institutes of Health Bethesda MD USA Office of the Director Center for Cancer Research National Cancer Institute National Institutes of Health Bethesda MD USA Laboratory of Cancer Biology and Genetics Center for Cancer Research National Cancer Institute National Institutes of Health Bethesda MD USA

Despite breakthroughs in cancer immunotherapy, most tumor-reactive T cells cannot persist in solid tumors due to an immunosuppressive environment. We developed Tres (tumor-resilient T cell, https://***/), a computational model utilizing single-cell transcriptomic data to identify signatures of T cells that are resilient to immunosuppressive signals, such as transforming growth factor-β1, tumor necrosis factor-related apoptosis-inducing ligand and prostaglandin E2. Tres reliably predicts clinical responses to immunotherapy in melanoma, lung cancer, triple-negative breast cancer and B cell malignancies using bulk T cell transcriptomic data from pre-treatment tumors from patients who received immune-checkpoint inhibitors (n = 38), infusion products for chimeric antigen receptor T cell therapies (n = 34) and pre-manufacture samples for chimeric antigen receptor T cell or tumor-infiltrating lymphocyte therapies (n = 84). Further, Tres identified FIBP, whose functions are largely unknown, as the top negative marker of tumor-resilient T cells across many solid tumor types. FIBP knockouts in murine and human donor CD8+ T cells significantly enhanced T cell-mediated cancer killing in in vitro co-cultures. Further, Fibp knockout in murine T cells potentiated the in vivo efficacy of adoptive cell transfer in the B16 tumor model. Fibp knockout T cells exhibit reduced cholesterol metabolism, which inhibits effector T cell function. These results demonstrate the utility of Tres in identifying biomarkers of T cell effectiveness and potential therapeutic targets for immunotherapies in solid tumors.

关键词： Cancer immunotherapy Computational biology and bioinformatics Predictive markers T cells

来源：评论

学校读者我要写书评

暂无评论

Development and Evaluation of a Process to Link Cancer Patients in the SEER Registries to National Medicaid Enrollment data

引用

Journal of the National Cancer Institute - Monographs 2020年第55期2020卷 89-95页

作者： Warren, Joan L. Benner, Suzie Stevens, Jennifer Enewold, Lindsey Huang, Bin Zhao, Lirong Tilahun, Negussie Bradley, Cathy J. Healthcare Assessment Research Branch Healthcare Delivery Research Program Division of Cancer Control and Population Science National Cancer Institute Bethesda MD United States Fu Associates Ltd Arlington VA United States Information Management Services Calverton MD United States Department of Biostatistics College of Public Health Markey Cancer Center University of Kentucky Lexington KY United States Division of Data Research and Analytic Methods Center for Medicare and Medicaid Innovation Centers for Medicare and Medicaid Services Baltimore MD United States Department of Health Systems Management and Policy School of Public Health University of Colorado Aurora CO United States

Cancer patients receiving Medicaid have worse prognosis. Patients in 14 Surveillance, Epidemiology, and End Results (SEER) cancer registries were linked to national Medicaid enrollment files, 2006-2013, to determine enrollment status during the year before and after diagnosis. A deterministic algorithm based on Social Security number, Medicare Health Insurance Claim number, sex, and date of birth was utilized. Results were compared with an independent linkage of Kentucky-based SEER and Medicaid data. A total 559 484 cancer cases were linked to national Medicaid enrollment files, representing 15-17% of persons with cancer yearly. About 60% of these cases were a complete match on all variables. There was 99% agreement on enrollment status compared with the Kentucky linked data. SEER data were successfully linked to national Medicaid enrollment data. NCI will make the linked data available to researchers, allowing for more detailed assessments of the impact Medicaid enrollment has on cancer diagnosis and outcomes. © 2020 Published by Oxford University Press. This work is written by US Government employees and is in the public domain in the US.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Role of Lactate Metabolism in Heart Failure and Cardiogenic Shock: Clinical Insights and Therapeutic Implications

引用

Journal of Cardiac Failure 2025年

作者： YUZEFPOLSKAYA, MELANA SCHWARTZ, SARAH LADANYI, ANNAMARIA ABRAHAM, JACOB GALE, CHRIS P. GRINSTEIN, JONATHAN KLEIN, LIVIU MAJURE, DAVID T. PHANCAO, ANITA SHEIKH, FAROOQ H. COLOMBO, PAOLO C. JANUZZI, JAMES L. MOLINA, EZEQUIEL J. Division of Cardiovascular Medicine Department of Cardiology New York Presbyterian Hospital Columbia University New York NY United States Center for Cardiovascular Analytics Research & Data Science (CARDS) Providence St. Joseph Research Network Portland OR United States Leeds Institute of Cardiovascular and Metabolic Medicine University of Leeds Leeds UK Leeds Institute for Data Analytics University of Leeds Leeds UK Leeds Teaching Hospitals NHS Trust Leeds United Kingdom Division of Cardiovascular Medicine Department of Cardiology University of Chicago Chicago IL United States Division of Cardiovascular Medicine Department of Cardiology University of San Francisco San Francisco CA United States Division of Cardiovascular Medicine Department of Cardiology New York Presbyterian Hospital Weill Cornell Medical College New York NY United States Division of Cardiovascular Medicine Department of Cardiology University of Miami Miami FL United States Advanced Heart Failure Program MedStar Health Georgetown University School of Medicine Washington D.C. United States Cardiology Division Massachusetts General Hospital Harvard Medical School Baim Institute for Clinical Research Boston MA United States Division of Cardiothoracic Surgery Department of Surgery Piedmont Heart Institute Atlanta GA United States

Heart failure (HF) is associated with poor prognosis, especially when it progresses to cardiogenic shock (CS), where survival rates substantially decline. A key area of interest is the role of blood lactate as a biomarker in these conditions. Lactate is produced under normal physiological conditions but increases with impaired tissue perfusion, a hallmark of HF and CS. Elevated lactate levels result from increased production, reduced clearance or both and are often associated with worse outcomes. Traditionally considered a byproduct of anaerobic metabolism, lactate is now recognized as an important energy substrate, particularly in myocardial tissue during periods of metabolic stress. Recent studies suggest that dynamic lactate monitoring, including lactate clearance (LC), may provide critical insights into patients’ prognoses and responses to therapy. Serial measurements of lactate have been shown to predict survival in critically ill patients, including those with HF and CS. In CS, elevated lactate levels correlate with increased mortality risk, and LC is emerging as an important parameter in treatment protocols. Despite growing evidence of lactate's clinical relevance, research is needed to establish standardized thresholds and optimal monitoring timelines. Understanding the complexities of lactate metabolism and its role in HF and CS could lead to improved risk stratification and more personalized treatment approaches. © 2025

关键词： cardiogenic shock Heart failure lactate levels

来源：评论

学校读者我要写书评

暂无评论

An overview of facial micro-expression analysis: data, methodology and challenge

arXiv

引用

arXiv 2020年

作者： Xie, Hong-Xia Lo, Ling Shuai, Hong-Han Cheng, Wen-Huang The Institute of of Electronics National Chiao Tung Univresity Hsinchu300 Taiwan The Department of Electrical and Computer Engineering National Chiao Tung Univresity Hsinchu300 Taiwan The Institute of Electronics National Chiao Tung Univresity Hsinchu300 Taiwan The Artificial Intelligence and Data Science Program National Chung Hsing University Taichung400 Taiwan

Facial micro-expressions indicate brief and subtle facial movements that appear during emotional communication. In comparison to macro-expressions, micro-expressions are more challenging to be analyzed due to the short span of time and the fine-grained changes. In recent years, micro-expression recognition (MER) has drawn much attention because it can benefit a wide range of applications, e.g. police interrogation, clinical diagnosis, depression analysis, and business negotiation. In this survey, we offer a fresh overview to discuss new research directions and challenges these days for MER tasks. For example, we review MER approaches from three novel aspects: macro-to-micro adaptation, recognition based on key apex frames, and recognition based on facial action units. Moreover, to mitigate the problem of limited and biased ME data, synthetic data generation is surveyed for the diversity enrichment of micro-expression data. Since micro-expression spotting can boost micro-expression analysis, the state-of-the-art spotting works are also introduced in this paper. At last, we discuss the challenges in MER research and provide potential solutions as well as possible directions for further investigation. Copyright © 2020, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Generative models of simultaneously heavy-tailed distributions of inter-event times on nodes and edges

arXiv

引用

arXiv 2020年

作者： dos Reis, Elohim Fonseca Li, Aming Masuda, Naoki Department of Mathematics State University of New York at Buffalo BuffaloNY United States Department of Zoology University of Oxford Oxford United Kingdom Department of Biochemistry University ofOxford Oxford United Kingdom Computational and Data-Enabled Science and Engineering Program State University of New York at Buffalo BuffaloNY United States

Intervals between discrete events representing human activities, as well as other types of events, often obey heavy-tailed distributions, and their impacts on collective dynamics on networks such as contagion processes have been intensively studied. The literature supports that such heavy-tailed distributions are present for inter-event times associated with both individual nodes and individual edges in networks. However, the simultaneous presence of heavy-tailed distributions of inter-event times for nodes and edges is a non-trivial phenomenon, and its origin has been elusive. In the present study, we propose a generative model and its variants to explain this phenomenon. We assume that each node independently transits between a high-activity and low-activity state according to a continuous-time two-state Markov process and that, for the main model, events on an edge occur at a high rate if and only if both end nodes of the edge are in the high-activity state. In other words, two nodes interact frequently only when both nodes prefer to interact with others. The model produces distributions of inter-event times for both individual nodes and edges that resemble heavy-tailed distributions across some scales. It also produces positive correlation in consecutive inter-event times, which is another stylized observation for empirical data of human activity. We expect that our modeling framework provides a useful benchmark for investigating dynamics on temporal networks driven by non-Poissonian event sequences. Copyright © 2020, The Authors. All rights reserved.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based frozen section to FFPE translation

arXiv

引用

arXiv 2021年

作者： Ozyoruk, Kutsev Bengisu Can, Sermet Gokceler, Guliz Irem Başak, Kayhan Demir, Derya Serin, Gurdeniz Hacisalihoglu, Uguray Payam Kurtuluş, Emirhan Darbaz, Berkan Lu, Ming Y. Chen, Tiffany Y. Williamson, Drew F.K. Yilmaz, Funda Mahmood, Faisal Turan, Mehmet Institute of Biomedical Engineering Bogazici University Istanbul Turkey Uk Biocentre Tilbrook United Kingdom Department of Pathology Brigham and Women's Hospital Harvard Medical School BostonMA United States Cancer Data Science Program Dana-Farber Cancer Institute BostonMA United States Cancer Program Broad Institute of Harvard and Mit CambradgeMA United States Saǧlik Bilimleri University Kartal Dr.Lütfi Kirdar City Hospital Department of Pathology Istanbul Turkey Faculty of Medicine Department of Pathology Ege University Izmir Turkey Istanbul Yeni Yuzyil University Medical Faculty Gaziosmanpasa Hospital Pathology Department Turkey

Frozen sectioning (FS) is the preparation method of choice for microscopic evaluation of tissues during surgical operations. The high speed of procedure allows pathologists to rapidly assess the key microscopic features, such as tumor margins and malignant status to guide surgical decision-making and minimise disruptions to the course of the operation. However, FS is prone to introducing many misleading artificial structures (histological artefacts), such as nuclear ice crystals, compression, and cutting artefacts, hindering timely and accurate diagnostic judgement of the pathologist. Additional training and prolonged experience is often required to make highly effective and time critical diagnosis on frozen sections. On the other hand, the gold standard tissue preparation technique of formalin-fixation and paraffin-embedding (FFPE) provides significantly superior image quality, but is a very time-consuming process (12-48 hours), making it unsuitable for intra-operative use. In this paper, we propose an artificial intelligence (AI) method that improves FS image quality by computationally transforming frozen-sectioned whole-slide images (FS-WSIs) into whole-slide FFPE-style images in minutes. AI-FFPE rectifies FS artefacts with the guidance of an attention-mechanism that puts a particular emphasis on artefacts while utilising a self-regularization mechanism established between FS input image and synthesized FFPE-style image that preserves clinically relevant features. As a result, AI-FFPE method successfully generates FFPE-style images without significantly extending tissue processing time and consequently improves diagnostic accuracy. We demonstrate the efficacy of AI-FFPE on lung and brain frozen sections using a variety of different qualitative and quantitative metrics including visual Turing tests from 20 board certified pathologists. Additionally, we demonstrate that deep models trained on FFPE tissue can adapt to frozen sections which a much higher efficacy whe

关键词： Surgery

来源：评论

学校读者我要写书评

暂无评论

Concurrency measures in the era of temporal network epidemiology: A review

arXiv

引用

arXiv 2020年

作者： Masuda, Naoki Miller, Joel C. Holme, Petter Department of Mathematics State University of New York Buffalo United States Computational and Data-Enabled Science and Engineering Program State University of New York Buffalo United States School of Engineering and Mathematical Sciences La Trobe University Australia Institute of Innovative Research Tokyo Institute of Technology Yokohama226-8503 Japan

Diseases spread over temporal networks of interaction events between individuals. Structures of these temporal networks hold the keys to understanding epidemic propagation. One early concept of the literature to aid in discussing these structures is concurrency-quantifying individuals' tendency to form time-overlapping "partnerships". Although conflicting evaluations and an overabundance of operational definitions have marred the history of concurrency, it remains important, especially in the area of sexually transmitted infections. Today, much of theoretical epidemiology uses more direct models of contact patterns, and there is an emerging body of literature trying to connect methods to the concurrency literature. In this review, we will cover the development of the concept of concurrency and these new approaches. © 2020, CC BY.

关键词： Epidemiology

来源：评论

学校读者我要写书评

暂无评论

Perspectives on How To Conduct Responsible Anti-Human Trafficking Research in Operations and Analytics

arXiv

引用

arXiv 2020年

作者： Konrad, Renata A. Maass, Kayse Lee Dimas, Geri L. Trapp, Andrew C. School of Business Worcester Polytechnic Institute 100 Institute Road WorcesterMA01609 United States Department of Mechanical and Industrial Engineering Northeastern University 360 Huntington Ave BostonMA02115 United States Data Science Program Worcester Polytechnic Institute 100 Institute Road WorcesterMA01609 United States

Human trafficking, the commercial exploitation of individuals, is a gross violation of human rights;harming societies, economies, health and development. The related disciplines of Operations Research (OR) and Analytics are uniquely positioned to support trafficking prevention and intervention efforts by efficiently evaluating a plethora of decision alternatives and providing quantitative, actionable insights. As operations and analytical efforts in the counter-trafficking field emerge, it is imperative to grasp subtle, yet distinctive, nuances associated with human trafficking. This paper is intended to inform those practitioners working in the Operations and Analytics fields by highlighting key features of human trafficking activity. We grouped ten themes around two broad categories: (1) representation of human trafficking and (2) consideration of survivors and communities. These insights are derived from our collective experience in working in this area and substantiated by domain expertise. Based on these areas, we then suggest avenues for future work. © 2020, CC BY-NC-SA.

关键词： Operations research

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：