Accelerometry based classification of gait patterns using empirical mode decomposition

Abstract

This paper describes accelerometry based classification of walking patterns. A feature extraction technique based on empirical mode decomposition (EMD) is proposed for the classification of unsupervised walking activities from accelerometry data. The front-end 20 dimensional features representing the gait patterns were obtained from the first three modes of decomposition of the acceleration data in anterior-posterior, medio-lateral, and vertical direction. The back-end of the system was a 64-mixture Gaussian Mixture Model (QMM) classifier. Overall classification accuracy of 96.02% was achieved for the five different human gait patterns including walking on flat surfaces, walking up and down paved ramps and walking up and down stairways.