Senanayake Chathuri M, Senanayake S M N Arosha
School of Engineering, Monash University, Sunway Campus, Jalan Lagoon Selatan, Bandar Sunway, 46150 Petaling Jaya, Selangor, Malaysia.
IEEE Trans Inf Technol Biomed. 2010 Sep;14(5):1173-9. doi: 10.1109/TITB.2010.2058813. Epub 2010 Aug 26.
An intelligent gait-phase detection algorithm based on kinematic and kinetic parameters is presented in this paper. The gait parameters do not vary distinctly for each gait phase; therefore, it is complex to differentiate gait phases with respect to a threshold value. To overcome this intricacy, the concept of fuzzy logic was applied to detect gait phases with respect to fuzzy membership values. A real-time data-acquisition system was developed consisting of four force-sensitive resistors and two inertial sensors to obtain foot-pressure patterns and knee flexion/extension angle, respectively. The detected gait phases could be further analyzed to identify abnormality occurrences, and hence, is applicable to determine accurate timing for feedback. The large amount of data required for quality gait analysis necessitates the utilization of information technology to store, manage, and extract required information. Therefore, a software application was developed for real-time acquisition of sensor data, data processing, database management, and a user-friendly graphical-user interface as a tool to simplify the task of clinicians. The experiments carried out to validate the proposed system are presented along with the results analysis for normal and pathological walking patterns.
本文提出了一种基于运动学和动力学参数的智能步态阶段检测算法。每个步态阶段的步态参数变化并不明显；因此，根据阈值区分步态阶段很复杂。为了克服这一复杂性，应用模糊逻辑的概念根据模糊隶属度值来检测步态阶段。开发了一个实时数据采集系统，该系统由四个力敏电阻和两个惯性传感器组成，分别用于获取足部压力模式和膝关节屈伸角度。检测到的步态阶段可进一步分析以识别异常情况的发生，因此，适用于确定反馈的准确时机。高质量步态分析所需的大量数据需要利用信息技术来存储、管理和提取所需信息。因此，开发了一个软件应用程序，用于实时采集传感器数据、数据处理、数据库管理以及一个用户友好的图形用户界面，作为简化临床医生任务的工具。文中展示了为验证所提出系统而进行的实验以及对正常和病理行走模式的结果分析。
