Subject Recognition Based on Ground Reaction Force Measurements of Gait Signals

• Published in: IEEE transactions on systems, man and cybernetics. Part B, Cybernetics Vol. 38; no. 6; pp. 1476 - 1485
• Main Authors: Moustakidis, S.P., Theocharis, J.B., Giakas, G.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.12.2008
• Subjects: Algorithms; Anthropometry; Artificial Intelligence; Biometry - methods; Classification; Computer Simulation; Cybernetics; Feature extraction; Feature selection; Force measurement; Gait; Gait - physiology; ground reaction forces (GRFs) of gait; Grounds; Human; human gait analysis; Humans; kernel-based support vector machine (SVM) classification; Models, Biological; Pattern Recognition, Automated - methods; Recognition; Stress, Mechanical; subject recognition; Support vector machine classification; Support vector machines; Time frequency analysis; Wavelet; Wavelet domain; wavelet packet (WP) decomposition; Wavelet packets; Wavelet transforms; Feature selection; wavelet packet (WP) decomposition; ground reaction forces (GRFs) of gait; human gait analysis; kernel-based support vector machine (SVM) classification; subject recognition
• ISSN: 1083-4419; 1941-0492; 1941-0492
• DOI: 10.1109/TSMCB.2008.927722

An effective subject recognition approach is designed in this paper, using ground reaction force (GRF) measurements of human gait. The method is a three-stage procedure: 1) The original GRF data are translated through wavelet packet (WP) transform in the time-frequency domain. Using a fuzzy-set-based criterion, we determine an optimal WP decomposition, involving feature subspaces with distinguishing gait characteristics. 2) A feature extraction scheme is employed next for wavelet feature ranking, according to discrimination power. 3) The classification task is accomplished by means of a kernel-based support vector machine. The design parameters of the classifier are tuned through a genetic algorithm to improve recognition rates. The method is evaluated on a database comprising GRF records obtained from 40 subjects. To account for the natural variability of human gait, the experimental setup is designed, allowing different walking speeds and loading conditions. Simulation results demonstrate that high recognition rates can be achieved with moderate number of features and for different training/testing settings. Finally, the performance of our approach is favorably compared with the one obtained using other traditional classification algorithms.