Open AccessComparison of different marker sets for marker trajectory and principal component analysis based classification of simulated gait impairments
Author(s) -
Josef Christian,
Felix Kluge,
Bjoern M. Eskofier,
Hermann Schwameder
Publication year - 2016
Publication title -
journal of biomedical engineering and informatics
Language(s) - English
Resource type - Journals
eISSN - 2377-939X
pISSN - 2377-9381
DOI - 10.5430/jbei.v3n1p10
Subject(s) - principal component analysis , gait , set (abstract data type) , trajectory , computer science , gait analysis , artificial intelligence , pattern recognition (psychology) , physical medicine and rehabilitation , medicine , physics , astronomy , programming language
Objective: Many different marker sets have been used in marker trajectory based gait classification approaches. Little knowledge exists about the effects of specific marker sets on the subsequent statistical modeling. Such analysis is often based on principal component analysis. The aim of this study was to test the effect of marker set choice on marker trajectory and principal component analysis based gait classification. Methods: This study tested the performance of principal component analysis based gait classification models with various marker sets on the basis of simulated gait impairments. Simulated gait impairments were used to enable a high level of control of the gait patterns. Results: Classification accuracies were similar across most tested marker sets. Improved performance could be detected for some marker sets depending on the type of impairment. Conclusion: Several potentially valid marker sets exist for a specific gait classification task even though trends could be found suggesting that optimal marker set choice is dependent on functional aspects of the movement.