基于可穿戴传感器的步态冻结检测:模板匹配方法
首发时间:2017-08-08
摘要:每年,意外跌倒给帕金森病(Parkinson's disease ,PD)人所带来的身体和财产损失都是巨大的。其中,步态冻结(Freezing of Gait, FOG)作为PD的主要症状,是引起意外的重要原因之一。尽管研究人员对FOG的特性分析与检测方法做了相当深入细致的研究,可是在高精度、高效率的FOG检测方法上,仍有较大的改进空间。相较于传统的统计机器学习方法,基于模板匹配的方法往往具有更高的精度和效率。本文主要针对上述需求,提出了一种基于模板匹配的改进Dynamic Template Wrapping(DTW)方法,并在开源实验数据上做了验证。实验结果显示,相对于传统模板匹配方法和统计学习方法,本文IsDTW方法不仅具有相对较高的实验精度(92%),在运行效率上也在一定程度上优于传统方法,对实际应用更具价值。
关键词: 帕金森 步态冻结 模板匹配 DTW 可穿戴传感器。
For information in English, please click here
Wearable Sensors Dependent Detection of Freezing of Gait Using Template-Match-Based Approaches
Abstract:Every year, injuries associated with fall incidences causes lots of human suffering and assets loss for Parkinson's disease (PD) patients. Thereinto, Freezing of Gait (FOG) which is one of the most common symptoms of PD, is quite responsible for most incidents. Although lots of research have been done on characterize analysis and detection methods of FOG, large room for improvement still exists in the high accuracy and high efficiency examination of FOG. Compared with traditional statistical machine learning methods, template-matching methods are generally of higher recognition accuracy and better efficiency. In view of the above requirements, this paper presents a template-matching-based improved subsequence Dynamic Time Warping (IsDTW) method, and experimental tests were conducted on typical open source datasets. Results show that compared with traditional template-matching and statisticWearable sensors dependent Detection of Freezing of Gait Using Template-Match-Based Approachesal learning methods, proposed IsDTW not only embodies higher experimental accuracy (92%), but also has a significant runtime efficiency. By contrast, IsDTW is far more available in real-time practice applications.
Keywords: Parkinson's disease freezing of gait template-matching DTW wearable sensors.
论文图表:
引用
No.4736051119435914****
同行评议
共计0人参与
勘误表
基于可穿戴传感器的步态冻结检测:模板匹配方法
评论
全部评论0/1000