This website requires JavaScript.

Designing Compact Features for Remote Stroke Rehabilitation Monitoring using Wearable Accelerometers

Xi ChenYu GuanJian Qing ShiXiu-Li DuJanet Eyre
Sep 2020
摘要
Stroke is known as a major global health problem, and for stroke survivors itis key to monitor the recovery levels. However, traditional strokerehabilitation assessment methods (such as the popular clinical assessment) canbe subjective and expensive, and it is also less convenient for patients tovisit clinics in a high frequency. To address this issue, in this work based onwearable sensing and machine learning techniques, we develop an automatedsystem that can predict the assessment score in an objective manner. Withwrist-worn sensors, accelerometer data is collected from 59 stroke survivors infree-living environments for a duration of 8 weeks, and we map the week-wiseaccelerometer data(3 days per week) to the assessment score by developingsignal processing and predictive model pipeline. To achieve this, we proposetwo types of new features, which can encode the rehabilitation information fromboth paralysed and non-paralysed sides while suppressing the high level noisessuch as irrelevant daily activities. Based on the proposed features, we furtherdevelop the longitudinal mixed-effects model with Gaussian process prior(LMGP), which can model the random effects caused by different subjects andtime slots (during the 8 weeks). Comprehensive experiments are conducted toevaluate our system on both acute and chronic patients, and the promisingresults suggest its effectiveness.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答