Automated exercise classification for wearable-sensor based weight training performance monitoring

基于可穿戴传感器的重量训练表现监控的自动运动分类

• 批准号: 490655-2015
• 负责人: Kulic, Danica
• 金额: $ 1.82万
• 依托单位: University of Waterloo
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2015
• 资助国家: 加拿大
• 起止时间: 2015-01-01 至 2016-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=586561
• 关键词: Automated; exercise; classification; wearable; sensor

Push Inc. is a Canadian startup based in Toronto, Ontario, focused on the development of wearable fitness devices for athletic weight training. Push has developed a wearable fitness device and accompanying mobile app that allows athletes to track their weight lifting exercises and compute performance metrics such as velocity, power, force and mechanical work, which they can use to monitor their training performance and progress. In the current implementation of the system, users must manually enter the exercise type and load into the app, to allow the system to know which exercise is currently being performed. If the system could detect the exercise being performed automatically, this would eliminate the need for the user to specify them manually, increasing usability and convenience, and reducing manual input errors. The aim of the proposed research is to develop the data processing and classification algorithms to enable the system to automatically detect the type of exercise being performed from the measured movement.

普什公司是一家位于安大略省多伦多的加拿大初创公司，专注于可穿戴健身的开发 用于运动员举重训练的器械。Push已经开发了一款可穿戴健身设备和配套的移动的 这款应用程序允许运动员跟踪他们的举重练习并计算性能指标， 速度、功率、力量和机械功，他们可以用来监测他们的训练表现， 中求进工作总在目前实施的系统中，用户必须手动输入运动类型和负荷 应用程序，让系统知道当前正在进行的锻炼。若是系统能 自动检测正在执行的练习，这将消除用户指定它们的需要 手动输入，增加了可用性和便利性，并减少了手动输入错误。建议的目的 研究是开发数据处理和分类算法，使系统能够自动 从所测量的运动中检测正在进行的锻炼的类型。