The development of a Gait Waveform Classifier

点击翻译按钮获取中文摘要

Gait analysis aims to quantify and assess the mechanics of normal and abnormal movement patterns during walking.  Biomechanists use state of the art motion capture systems to record gait patterns and describe the mechanics of movement.  Gait data provides many challenges to researchers as it consists of vast numbers of waveforms that are difficult to analyze and compare.  An accepted method of gait curve comparison has not been developed.  As a result, many researchers extract discrete points (peaks) from the waveforms and ignore the valuable temporal information and patterns of motion.  Numerical tools that classify and compare gait patterns based on the entire waveform are needed.This study aims to further my work on the design and implementation of algorithms that reduce the vast quantities of mechanical data to a series of one-dimensional indices of normality based on age-matched normative data.  The indices, or classifiers, use an automatic system (motion capture and subsequent data analysis) to detect movement abnormalities based on magnitude, pattern of motion, and correlations between gait curves.  The output is a series of numerical scores that make mechanical and physiological sense and yield interpretable results.  Very few classifiers exist that can satisfy the two-fold constraint of incorporating correlated multi-dimensional input data and providing readily interpretable output.  The proposed work is novel in that it incorporates mechanical data, myoelectric signals, and functional measures.  To date, no other classifiers include all of these measures, which are considered integral to a typical gait analysis.  The development of the classifier will provide researchers with an automated tool to reduce mechanical and myoelectric data and quantify differences in gait waveforms.  This will lead to a greater understanding of the differences in gait patterns between populations or individuals.