Linear predictive modelling of gait patterns

The use of a wearable triaxial accelerometer for unsupervised monitoring of human movement has become a major research focus in recent years. In this paper, the relationship between accelerometry signals and human gait is analysed using a linear prediction (LP) model. We explore the use of the LP model for analysing five gait patterns and show that the LP cepstrum can be used for gait pattern classification with high accuracy. This is then compared to a filterbank based approach to estimate the cepstral coefficients. Fifty subjects participated in collection of gait pattern data involving walking on level surfaces, and walking up and down stairs and ramps. The results show that an overall accuracy of 93% can be achieved using features derived from the cepstral coefficients for the five different walking patterns.