Marker-based classification of young–elderly gait pattern differences via direct PCA feature extraction and SVMs

Abstract

This file was dowloaded from the institutional repository Brage NIH -brage.bibsys.no/nih Eskofier, B. M., Federolf, P., Kugler, P. F., Nigg, B. (2013 AbstractThe classification of gait patterns has great potential as a diagnostic tool, for example for injury diagnostic or to identify at-risk gait in the elderly. This paper has the purpose of presenting a method for classifying gait pattern group differences using the complete spatial and temporal information of the segment motion quantified by markers. The obtained classification rates are compared to previous studies using conventional classification features.For our analysis, 37 three-dimensional marker trajectories were collected from each of our 24 young and 24 elderly female subjects while they were walking on a treadmill. Principal component analysis was performed on these trajectories to retain the spatial and temporal information in the markers. Using a SupportVector Machine with linear kernel, a classification rate of 95.8% was obtained.This classification approach also allowed visualization of the contribution of individual markers to group differentiation in position and time.The approach made no specific assumptions and did not require prior knowledge of specific time points in the gait cycle. It is therefore directly applicable for group classification tasks in any study involving marker measurements.

Comparison of different marker sets for marker trajectory and principal component analysis based classification of simulated gait impairments

“…Subsequently, the data of each participant and condition were arranged in a row vector to construct a spatio-temporal representation of the gait pattern in a vector space. [4,8,[10][11][12] The waveforms of each marker and spatial direction were concatenated to form the gait pattern vectors with m × 303 dimensions (m markers × 3 spatial directions × 101 points in time). For further analysis, the gait pattern vectors (row vectors) were vertically concatenated to construct an input matrix.…”

“…For classification methods, the linear Support Vector Machine (SVM) algorithm has been used in several approaches. [7][8][9][10][11] Other state of the art classifiers such as Ada Boost, [15] Naïve Bayes [14] or Random Forest [16] are capable of solving non-linear classification problems and are commonly considered in machine learning applications.…”

“…[3] Several studies in the gait analysis domain have applied variations of this approach and various marker sets have been used across these studies. [1,[3][4][5][6][7][8][9][10][11][12] The marker sets can be differentiated based on two major aspects. Firstly, whether the marker set covers the full body or body parts; full body marker sets were used most frequently.…”

“…Firstly, whether the marker set covers the full body or body parts; full body marker sets were used most frequently. [1,[3][4][5][6]11] Body part marker sets include unilateral placement on the lower extremity, [7,10,12] unilateral placement on the upper and lower extremity [9] and bilateral placement on the lower body and thorax. [8] Secondly, marker sets can be differentiated based on whether the markers are placed exclusively on specific anatomical landmarks.…”

“…[8] Secondly, marker sets can be differentiated based on whether the markers are placed exclusively on specific anatomical landmarks. Marker placement exclusively on anatomical landmarks was used for most associated studies and these marker sets were based on Vicon's Plug-In-Gait R model [3,8,11] or on customized models. [6,7,9,10,12] Federolf, Boyer [4] included marker clusters in addition to the markers on anatomical landmarks.…”