检索结果-内蒙古大学图书馆

Patient-Generated Data Analytics of Health Behaviors of People Living with Type 2 Diabetes: Scoping Review

JMIR Diabetes 2021年第4期6卷 e29027页

作者： Nagpal, Meghan S. Barbaric, Antonia Sherifali, Diana Morita, Plinio P. Cafazzo, Joseph A. Institute of Health Policy Management and Evaluation University of Toronto Toronto ON Canada Centre for Global eHealth Innovation Techna Institute University Health Network Toronto ON Canada Institute of Biomedical Engineering University of Toronto Toronto ON Canada School of Nursing McMaster University Hamilton ON Canada School of Public Health and Health Systems University of Waterloo Waterloo ON Canada Department of Computer Science University of Toronto Toronto ON Canada

Background: Complications due to type 2 diabetes (T2D) can be mitigated through proper self-management that can positively change health behaviors. Technological tools are available to help people living with, or at risk of developing, T2D to manage their condition, and such tools provide a large repository of patient-generated health data (PGHD). Analytics can provide insights into the health behaviors of people living with T2D. Objective: The aim of this review is to investigate what can be learned about the health behaviors of those living with, or at risk of developing, T2D through analytics from PGHD. Methods: A scoping review using the Arksey and O’Malley framework was conducted in which a comprehensive search of the literature was conducted by 2 reviewers. In all, 3 electronic databases (PubMed, IEEE Xplore, and ACM Digital Library) were searched using keywords associated with diabetes, behaviors, and analytics. Several rounds of screening using predetermined inclusion and exclusion criteria were conducted, after which studies were selected. Critical examination took place through a descriptive-analytical narrative method, and data extracted from the studies were classified into thematic categories. These categories reflect the findings of this study as per our objective. Results: We identified 43 studies that met the inclusion criteria for this review. Although 70% (30/43) of the studies examined PGHD independently, 30% (13/43) combined PGHD with other data sources. Most of these studies used machine learning algorithms to perform their analysis. The themes identified through this review include predicting diabetes or obesity, deriving factors that contribute to diabetes or obesity, obtaining insights from social media or web-based forums, predicting glycemia, improving adherence and outcomes, analyzing sedentary behaviors, deriving behavior patterns, discovering clinical correlations from behaviors, and developing design principles. Conclusions: The increas

关键词： Artificial intelligence Big data Data science Health behavior Machine learning Mobile phone Obesity management Patient-generated health data Type 2 diabetes

来源：评论

学校读者我要写书评

暂无评论

Ethical Machine Learning in Healthcare

引用

Biomedical Data Science 2021年第1期4卷 123-144页

作者： Irene Y. Chen Emma Pierson Sherri Rose Shalmali Joshi Kadija Ferryman Marzyeh Ghassemi 1Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA email: iychen@mit.edu 2Microsoft Research Cambridge Massachusetts 02143 USA 3Center for Health Policy and Center for Primary Care and Outcomes Research Stanford University Stanford California 94305 USA 4Vector Institute Toronto Ontario M5G 1M1 Canada 5Department of Technology Culture and Society Tandon School of Engineering New York University Brooklyn New York 11201 USA 6Institute for Medical and Evaluative Sciences Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA

The use of machine learning (ML) in healthcare raises numerous ethical concerns, especially as models can amplify existing health inequities. Here, we outline ethical considerations for equitable ML in the advancement of healthcare. Specifically, we frame ethics of ML in healthcare through the lens of social justice. We describe ongoing efforts and outline challenges in a proposed pipeline of ethical ML in health, ranging from problem selection to postdeployment considerations. We close by summarizing recommendations to address these challenges.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Shedding light on inequities of power outages through data transparency

Progress in Energy

引用

Progress in Energy 2025年第3期7卷 033003-033003页

作者： Kelly A Stevens Sanam K Aksha Mohammad Siddiqur Rahman Elizabeth Trader Herbert Longenecker Rebecca Entress Thomas Wahl Christopher Emrich Kristopher O Davis School of Public Administration University of Central Florida Orlando FL United States of America Resilient Intelligent and Sustainable Energy Systems (RISES) Research Center University of Central Florida Orlando FL United States of America Florida Solar Energy Center (FSEC) University of Central Florida Orlando FL United States of America Department of Civil Environmental and Construction Engineering University of Central Florida Orlando FL United States of America National Center for Integrated Coastal Research University of Central Florida Orlando FL United States of America Department of Electrical and Computer Engineering University of Central Florida Orlando FL United States of America Department of Political Science University of South Carolina Columbia SC United States of America Department of Materials Science and Engineering University of Central Florida Orlando FL United States of America

In a changing climate, the electricity grid is increasingly exposed to more extreme weather that results in significant power outages. Further, lower income and racial-ethnic minority households are more likely to experience a higher frequency and duration of power outages compared to less socially vulnerable groups. The literature on the unequal impacts of power outages is a new, growing area of research that has been stymied in part due to the difficulty acquiring high spatial resolution, historical power outage data from utilities. In this Perspectives article, we review the availability of power outage data, and what can be learned from higher spatial resolution data about the uneven distribution of power outages. We illustrate this with a case study evaluating power outage data in Florida from 2018–2022 at the county and zip-code level. We compare this to literature on spatial heterogeneity of social vulnerability indicators to identify ways that higher spatial resolution outage data can better measure inequities of power outages. Last, we provide feedback from stakeholders in Central Florida in local government, utilities, and community groups on the ways that higher resolution outage data could be used for improving equitable grid resilience.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of test scenarios and bicyclist surrogate for the evaluation of bicyclist automatic emergency braking systems

引用

Journal of Intelligent and Connected Vehicles 2018年第1期1卷 15-27页

作者： Qiang Yi Stanley Chien Lingxi Li Wensen Niu Yaobin Chen David Good Chi-Chih Chen Rini Sherony Department of Electrical and Computer Engineering Indiana University-Purdue UniversityIndianapolisIndianaUSA School of Public and Environmental Affairs Indiana UniversityBloomingtonIndianaUSA Department of Electrical and Computer Engineering Ohio State UniversityColumbusOhioUSA Toyota Collaborative Safety Research Center Ann ArborMichiganUSA

Purpose–To support the standardized evaluation of bicyclist automatic emergency braking(AEB)systems,test scenarios,test procedures and test system hardware and software tools have been investigated and developed by the Transportation Active Safety Institute(TASI)at Indiana University-Purdue University *** paper aims to focus on the development of test scenarios and bicyclist surrogate for evaluating vehicle–bicyclist AEB ***/methodology/approach–The harmonized general estimates system(GES)/FARS 2010-2011 crash data and TASI 110-car naturalistic driving data(NDD)are used to determine the crash geometries and environmental factors of crash scenarios including lighting conditions,vehicle speeds,bicyclist speeds,etc.A surrogate bicyclist including a bicycle rider and a bicycle surrogate is designed to match the visual and radar characteristics of bicyclists in the USA.A bicycle target is designed with both leg pedaling and wheel rotation to produce proper micro-Doppler features and generate realistic motion for camera-based AEB ***–Based on the analysis of the harmonized GES/FARS crash data,five crash scenarios are recommended for performance testing of bicyclist AEB *** with TASI 110-car naturalistic driving data,the crash environmental factors including lighting conditions,obscuring objects,vehicle speed and bicyclist speed are *** surrogate bicyclist was designed to represent the visual and radar characteristics of the real bicyclists in the *** height of the bicycle rider mannequin is 173 cm,representing the weighted height of 50th percentile US male and female *** size and shape of the surrogate bicycle were determined as 26-inch wheel and mountain/road bicycle frame,*** leg pedaling motion and wheel rotation are suggested to produce proper micro-Doppler features and support the camera-based AEB ***/value–The results have demonstrated that the developed scenarios,

关键词： Bicyclist Surrogate bicyclist Automatic emergency braking(AEB) Crash scenarios Crash testing Naturalistic driving Radar cross section(RCS) Micro-Doppler

来源：评论

学校读者我要写书评

暂无评论

Double-port slotted-antenna with multiple miniaturized radiators for wideband wireless communication systems and portable devices

引用

Progress In Electromagnetics Research C 2019年 90卷 1-13页

作者： Alibakhshikenari, Mohammad Khalily, Mohsen Virdee, Bal Singh Ali, Abdul Shukla, Panchamkumar See, Chan Hwang Abd-Alhameed, Raed A. Falcone, Francisco J. Limiti, Ernesto Electronic Engineering Department University of Rome "Tor Vergata" Via del Politecnico 1 Roma00133 Italy University of Surrey GuildfordGU2 7XH United Kingdom School of Computing and Digital Media Center for Communications Technology London Metropolitan University LondonN7 8DB United Kingdom School of Engineering University of Bolton BoltonBL3 5AB United Kingdom School of Engineering & the Built Environment Edinburgh Napier University Merchiston Campus 10 Colinton Road EdinburghEH10 5DT United Kingdom School of Electrical Engineering and Computer Science University of Bradford BradfordBD7 1DP United Kingdom Electrical and Electronic Engineering Department Public University of Navarre Pamplona31006 Spain

Proof-of-concept is presented of a novel slot antenna structure with two excitation ports. Although this antenna provides a wide impedance bandwidth, its peak gain and optimum radiation efficiency are observed at its mid-band operational frequency. The antenna structure is etched on the top side of a dielectric substrate with a ground plane. The antenna essentially consists of a rectangular patch with two dielectric slots in which multiple coupled patch arms embedded with H-shaped slits are loaded. The two dielectric slots are isolated from each other with a large H-shaped slit. The radiation characteristics of the proposed antenna in terms of impedance bandwidth, gain and efficiency can be significantly improved by simply increasing the number of radiation arms and modifying their dimensions. The antenna’s performance was verified by building and testing three prototype antennas. The final optimized antenna exhibits a fractional bandwidth of 171% (0.5–6.4 GHz) with a peak gain and maximum radiation efficiency of 5.3 dBi and 75% at 4.4 GHz, respectively. The antenna has physical dimensions of 27×37×1.6 mm3 corresponding to electrical size of 0.0452λ0 ×0.0627λ0 ×0.0026λ0,where λ0 is freespace wavelength at 0.5 GHz. The antenna is compatible for integration in handsets and other broadband wireless systems that operate over L-, S-, and C-bands. © 2019, Electromagnetics Academy. All rights reserved.

关键词： Slot antennas

来源：评论

学校读者我要写书评

暂无评论

Management of extra-articular manifestations in spondyloarthritis

引用

International journal of rheumatic diseases 2023年第2期26卷 183-186页

作者： Kevin Sheng-Kai Ma Yung-Heng Lee Chia-Jen Lin Po-Cheng Shih James Cheng-Chung Wei Department of Epidemiology Harvard T.H. Chan School of Public Health Boston Massachusetts USA. Center for Global Health Perelman School of Medicine University of Pennsylvania Philadelphia Pennsylvania USA. Graduate Institute of Biomedical Electronics and Bioinformatics College of Electrical Engineering and Computer Science National Taiwan University Taipei Taiwan. Department of Dermatology Massachusetts General Hospital Boston USA. Department of Orthopedics Cishan Hospital Ministry of Health and Welfare Kaohsiung Taiwan. Institute of Medical Science and Technology National Sun Yat-sen University Kaohsiung Taiwan. Department of Senior Services Industry Management Minghsin University of Science and Technology Hsinchu Taiwan. Department of Recreation and Sport Management Shu-Te University Kaohsiung Taiwan. School of Medicine Chung Shan Medical University Taichung Taiwan. Division of Allergy Immunology & Rheumatology Department of Internal Medicine Changhua Christian Hospital Changhua Taiwan. Institute of Medicine Chung Shan Medical University Taichung Taiwan. Division of Allergy Immunology & Rheumatology Chung Shan Medical University Hospital Taichung Taiwan. Graduate Institute of Integrated Medicine China Medical University Taichung Taiwan.

来源：评论

学校读者我要写书评

暂无评论

Network-based identification of genetic factors in ageing, lifestyle and type 2 diabetes that influence to the progression of Alzheimer's disease

引用

Informatics in Medicine Unlocked 2020年 19卷

作者： Chowdhury, Utpala Nanda Islam, M. Babul Ahmad, Shamim Moni, Mohammad Ali Dept. of Computer Science and Engineering University of Rajshahi Rajshahi Bangladesh Department of Electrical and Electronic Engineering University of Rajshahi Bangladesh Pabna University of Science and Technology Pabna Bangladesh WHO Collaborating Centre for eHealth School of Public Health and Community Medicine Faculty of Medicine UNSW Sydney Australia

Alzheimer's disease (AD) is a progressive neurodegenerative disease, the causes of which are poorly understood, although a number of strong risk factors for AD are known. Understanding how these risk factors affect cell pathways that are altered in AD could identify important causal pathways that could be targeted by therapeutics. We thus pro- posed network-based quantitative frameworks to investigate these risk factor-AD relation- ships. We analyzed gene expression microarray datasets from tissues affected by AD as well as by ageing, high alcohol consumption, type II diabetes (T2D), high dietary fat, obesity, high dietary red meat, sedentary lifestyle, and smoking. These datasets derived from studies that compared tissues affected by these factors with control tissues (not exposed to these factors) to identify differentially expressed genes (DEGs) specific to the risk factors. We employed these to develop gene association and diseasome networks based on neighborhood-based benchmarking and multilayer network topology. We identified 484 DEGs from AD brain tissue, of which 27 were also seen in the smoking DEGs gene set. AD data also showed 21 DEGs in common with T2D, and 12 with sedentary lifestyle datasets. AD shared less than ten DEGs with the other factors, but 3 (HLA-DRB4, IGH and IGHA2) were commonly up-regulated among the AD, T2D and high alcohol consumption datasets. IGHD and IGHG1 were up-regulated among AD, T2D, alcohol and sedentary lifestyle datasets. Protein-protein interaction networks identified 10 hub genes: CREBBP, PRKCB, ITGB1, GAD1, GNB5, PPP3CA, CABP1, SMARCA4, SNAP25 and GRIA1. Ontological and pathway analyses identified significant gene ontology and molecular pathways that could enhance our understanding of the mechanisms of AD progression by suggesting new therapeutic approaches to affect the development of AD. We verified genes from ontological and pathway analyses with gold benchmark gene-disease associations databases including Online Mendelia

关键词： Ageing Alzheimer's Lifestyle Network-based Topological Type 2 diabetes

来源：评论

学校读者我要写书评

暂无评论

Using undersampling with ensemble learning to identify factors contributing to preterm birth

arXiv

引用

arXiv 2020年

作者： Dong, Shi Feric, Zlatan Li, Guangyu Wu, Chieh T. Gu, April Z. Dy, Jennifer Meeker, John Padilla, Ingrid Y. Cordero, Jose Vega, Carmen Velez Rosario, Zaira Alshawabkeh, Akram Kaeli, David Dept. of Electrical and Computer Engineering Northeastern University United States Dept. of Civil and Environmental Engineering Northeastern University United States Department of Civil and Environmental Engineering Cornell University United States University of Michigan United States University of Puerto Rico Mayaguez Puerto Rico University of Georgia Georgia Graduate School of Public Health University of Puerto Rico Medical Campus Puerto Rico

In this paper, we propose Ensemble Learning models to identify factors contributing to preterm birth. Our work leverages a rich dataset collected by a NIEHS P42 Center that is trying to identify the dominant factors responsible for the high rate of premature births in northern Puerto Rico. We investigate analytical models addressing two major challenges present in the dataset: 1) the significant amount of incomplete data in the dataset, and 2) class imbalance in the dataset. First, we leverage and compare two types of missing data imputation methods: 1) mean-based and 2) similarity-based, increasing the completeness of this dataset. Second, we propose a feature selection and evaluation model based on using undersampling with Ensemble Learning to address class imbalance present in the dataset. We leverage and compare multiple Ensemble Feature selection methods, including Complete Linear Aggregation (CLA), Weighted Mean Aggregation (WMA), Feature Occurrence Frequency (OFA) and Classification Accuracy Based Aggregation (CAA). To further address missing data present in each feature, we propose two novel methods: 1) Missing Data Rate and Accuracy Based Aggregation (MAA), and 2) Entropy and Accuracy Based Aggregation (EAA). Both proposed models balance the degree of data variance introduced by the missing data handling during the feature selection process, while maintaining model performance. Our results show a 42% improvement in sensitivity versus fallout over previous state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Capacity/cost trade-off for 5G small cell networks in the UHF and SHF bands

Capacity/cost trade-off for 5G small cell networks in the UH...

引用

International Symposium on Wireless Personal Multimedia Communications (WPMC)

作者： Emanuel B. Teixeira Anderson R. Ramos Marisa S. Lourenço Fernando J. Velez Jon M. Peha Instituto de Telecomunicacções DEM Universidade da Beira Interior Covilhã Portugal Dept. of Electrical and Computer Engineering Dept. of Engineering & Public Policy Carnegie Mellon University Pittsburgh USA

ISBN: (数字)9781728154190

ISBN: (纸本)9781728154206

To fulfill the demand for high data rates from a wide number of users, higher frequencies can be used to provide the required capacity but with a different cost structure. 5G allows for very high data rates, which needs large bandwidths and requires very high throughput. This paper studies the economic trade-off of small cell networks deployed in Ultra High Frequency (UHF) and Super High Frequency (SHF) bands. Aiming at evaluating the variation of the carrier-to-noise-plus-interference ratio with the cell radius one considers the two-slope urban micro Line-of-Sight (UMiLoS) path loss model (ITU-R 2135 Report). The system capacity is analysed by the implicit function formulation to compute the supported cell throughput through the mapping of the PHY throughput into the step distances that correspond to the minimum carrier-to-interference-plus-noise ratio for each consecutive modulation and coding scheme. The variation of the equivalent supported throughput with the cell size at the 2.6, 3.5 and 5.62 GHz frequency bands facilitates to study the influence of the carrier-to-noise-plus-interference ratio in the dimensioning process. It is possible to conclude that, for the shortest cell radii, the profit is very low, starting to increase at a distance equal to the ratio between the break-point distance and the co-channel reuse factor attaining maxima for values of the cell radius approximately equal to 310, 390 and 740 m, at 2.6, 3.5 and 5.62 GHz, respectively (by assuming that the 5.62 GHz frequency band is unlicensed).

关键词： Throughput 5G mobile communication computer architecture Bandwidth Microprocessors Topology Modulation

来源：评论

学校读者我要写书评

暂无评论

Aberration detection of pertussis from the Mazandaran province, Iran, from 2012 to 2018: Application of discrete wavelet transform

引用

Journal of Acute Disease 2020年第3期9卷 114-120页

作者： Yousef Alimohamadi Seyed Mohsen Zahraei Manoochehr Karami Mehdi Yaseri MojtabaLotfizad Kourosh Holakouie-Naieni Department of Epidemiology and Biostatistics School of Public HealthTehran University of Medical SciencesTehranIran Center for Communicable Diseases Control Ministry of Health and Medical EducationTehranIran Research Center for Health Sciences Hamadan University of Medical SciencesHamadanIran School of Electrical&Computer Engineering Tarbiat Modares UniversityTehranIran

Objective:To define the level of alarm threshold for pertussisaberrations and to detect the aberrations of the reported suspectedcases of pertussis from the Mazandaran province in the north ***:The included cases were composed of the suspectedpertussis patients who came from Mazandaran province andregistered in the Center for Disease Control and Prevention from20 March 2012 to 20 March 2018.A discrete wavelet transformbasedmethod was used to detect the *** analyseswere performed using MATLAB Software version 2018a andExcel ***:A total of 1162 cases were recruited in the study,including 545(46.90%)males and 617(53.10%)females,withmedian age of 1.47(0.22-9.56)*** median age of maleswas 1.18(0.21-8.24)years,while that of females was 1.82(0.21-10.75)*** the level of the alarm threshold,it was1.28 case/d when k=2,while it was 1.34 case/d when k=*** detected aberration days were 123 d and 57 d by consideringk=2 and 3,*** most defined alarm threshold wasrelated to spring(>2 cases/d)and summer(>1 case/d),***:The sensitivity of the surveillance system issubjected to a different ***,determining the level of alarmthreshold periodically using different methods is recommended.

关键词： Aberration detection Pertussis Mazandaran Iran Discrete wavelet transform

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：