Validating Machine-Learned Classifiers of Sedentary Behavior and Physical Activit

验证久坐行为和体力活动的机器学习分类器

• 批准号: 8840546
• 负责人: Jacqueline Kerr
• 金额: $ 53.61万
• 依托单位: UNIVERSITY OF CALIFORNIA, SAN DIEGO
• 依托单位国家: 美国
• 财政年份: 2012
• 资助国家: 美国
• 起止时间: 2012-07-12 至 2016-04-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8840546
• 关键词: Acceleration; Accounting; Adult; Age; Agreement; Algorithms; Automobile Driving; Behavior; Behavior assessment; Behavioral; Bicycling; Cancer Control; Cardiovascular Diseases; Cardiovascular system; Child; Classification; Code; Complement; Computational Technique; Data; Data Analyses; Data Files; Data Set; Devices; Discrimination; Elderly; Environment; Exercise; Functional disorder; Funding; Generic Drugs; Genes; Geographic Information Systems; Gold; Graph; Health; Health Promotion; Health behavior; Hip region structure; Housekeeping; Image; Information Systems; Intervention; Intervention Studies; Laboratory Study; Life; Light; Light Exercise; Link; Location; Locomotion; Machine Learning; Malignant Neoplasms; Marshal; Measurement; Measures; Metabolic; Metabolic Marker; Methods; Modeling; Movement; National Health and Nutrition Examination Survey; Obesity; Online Systems; Participant; Patient Self-Report; Pattern; Persons; Physical activity; Population; Population Group; Positioning Attribute; Prevalence; Prevention strategy; Procedures; Recruitment Activity; Research; Resistance; Risk; Sampling; Science; Sensitivity and Specificity; Signal Transduction; Stream; Subgroup; Surface; System; Testing; Time; Training; United States National Institutes of Health; Validation; Wrist; base; cancer prevention; computerized data processing; epidemiologic data; improved; intervention effect; novel; sedentary; sensor; temporal measurement; vector

DESCRIPTION (provided by applicant): Sedentary behavior (SB) is a health risk, independent of moderate-to-vigorous physical activity (MVPA). Epidemiologic data reveal consistent associations between SB and numerous cancers, cardiovascular disease, as well as multiple markers of metabolic dysfunction. Reducing SB is recommended as a viable new cancer prevention strategy. Hip mounted accelerometry is a field-based criterion measure of PA but is inadequate for measuring SB. Misclassification most often occurs when movements are performed with limited trunk displacement, under load or on an incline, on a vibrating surface (e.g., in a car), or when they are too small to be distinguished from non-wear time. This is unacceptable because we may then mischaracterize the prevalence of both SB and PA. Measurement error obscures true relationships between behavior and health, and the effects of interventions may go undetected. [Our study will improve upon laboratory studies that do little to test SB in natural environments such as driving or watching TV. Lab-based machine learning algorithms for SB are aided by the artificial start and end points. Algorithms based upon research in free living settings will be more generalizable and applicable to intervention research]. In this study we will refine and validate new machine-learned classification algorithms for a continuum of behaviors from SB to MVPA using accelerometer, Global Positioning System (GPS), and Geographic Information System (GIS) data. This study will focus on behaviors that are most frequently misclassified: moderate intensity activities that are coded as light, light activities that are coded as sedentary, and sedentary activities that are coded as light or non wear time. [We will improve upon current self-report and accelerometer estimates by 30-50%.] We will focus on four primary behavioral classes: lying, sitting, standing, and ambulatory locomotion. A total of 210 participants (ages 6-10 yrs, n = 70; 16-55 yrs, n=70; 65-85 yrs, n= 70) will be recruited over a 2-yr period and will wear 3 ActiGraph accelerometers (two hip, one wrist); a GPS device, and a SenseCam (an automatic image capture device) for two weekdays and 1 weekend day. [A subsample will repeat the procedures for a further 3 days]. For a 6 hr period on each of these days, participants will also be directly observed by trained coders who will record free living behaviors using a novel portable behavioral assessment system developed for the iPad. Direct observation data will provide 'ground-truths' of behavior for an annotated data file recorded at one-second intervals. For free-living behaviors not directly observed, SenseCam images will be used. Machine learning Kernel methods will be employed. Sensitivity, specificity, accuracy and other ROC graph methods will be used to compare classifiers derived from: (a) single axis vs. multi axis accelerometer data; (b) movement 'counts' vs. raw acceleration data; and (c) hip vs. wrist mounted accelerometers. Analyses will determine the improvement in sensitivity and specificity when GPS and GIS data are added. We will evaluate the need for population specific classifiers and quantify measurement error in cut-points that are currently employed.

描述（由申请人提供）：久坐行为（SB）是一种健康风险，独立于中度到剧烈的体育锻炼（MVPA）。流行病学数据揭示了SB与众多癌症，心血管疾病以及代谢功能障碍的多个标记之间的一致关联。建议减少SB作为可行的新癌症预防策略。髋关节安装的加速度计是一种基于野外的PA的标准度量，但不足以测量SB。当在振动表面（例如，在汽车中）或太小而无法与非磨损时间区分开时，在有限的躯干位移，在负载下或倾斜的情况下进行有限的躯干位移进行运动时，通常会发生错误分类。这是不可接受的，因为然后我们可能会误解SB和PA的流行率。测量误差掩盖了行为与健康之间的真实关系，干预措施的影响可能未被发现。 [我们的研究将改进实验室研究，这些研究对在自然环境（例如开车或看电视）中几乎无济于事。 SB的基于实验室的机器学习算法得到了人工起点和终点的帮助。基于自由生活环境的研究的算法将更具普遍性，并且适用于干预研究。在这项研究中，我们将使用加速度计，全球定位系统（GPS）和地理信息系统（GIS）数据来完善并验证新的机器学习分类算法，以实现从SB到MVPA的连续行为。这项研究将重点关注最常见的错误分类的行为：中等强度的活动，这些活动被编码为轻型活动，被编码为久坐的光活动以及编码为轻度或非磨损时间的久坐活动。 [我们将将当前的自我报告和加速度计估计值提高30-50％。]我们将重点介绍四个主要的行为类别：撒谎，坐着，站立和卧床运动。共有210名参与者（6-10岁，n = 70; 16-55年，n = 70; 65-85岁，n = 70）将在2年内招募，并将佩戴3个行动式加速度计（两只臀部，一只手腕）； GPS设备和Sensecam（自动图像捕获设备）在两个工作日和1个周末。 [子样本将再重复3天的过程]。在这几天的每个日子里，参与者也将被训练有素的编码人员直接观察到，他们将使用为iPad开发的新型便携式行为评估系统记录自由生活行为。直接观察数据将为以一秒的间隔记录的带注释的数据文件提供“地面真相”。对于未直接观察到的自由生活行为，将使用Sensecam图像。将采用机器学习内核方法。灵敏度，特异性，准确性和其他ROC图方法将用于比较以下分类器：（a）单轴与多轴加速度计数据； （b）运动“计数”与原始加速度数据； （c）髋关节与腕部安装的加速度计。当添加GPS和GIS数据时，分析将确定灵敏度和特异性的提高。我们将评估对人群特定分类器的需求，并量化当前使用的切点的测量误差。

项目成果

Multi-sensor physical activity recognition in free-living.

自由生活中的多传感器身体活动识别。

• DOI: 10.1145/2638728.2641673
• 发表时间: 2014
• 期刊: Proceedings of the ... ACM International Conference on Ubiquitous Computing . UbiComp (Conference)
• 作者: Ellis K;Godbole S;Kerr J;Lanckriet G
• 通讯作者: Lanckriet G

A random forest classifier for the prediction of energy expenditure and type of physical activity from wrist and hip accelerometers.

• DOI: 10.1088/0967-3334/35/11/2191
• 发表时间: 2014-11
• 期刊: Physiological measurement
• 影响因子: 3.2
• 作者: Ellis K;Kerr J;Godbole S;Lanckriet G;Wing D;Marshall S
• 通讯作者: Marshall S