A hidden Markov model-based technique for gait segmentation using a foot-mounted gyroscope.

In this paper, we describe an application of hidden Markov models (HMMs) to the problem of time-locating specific events in normal gait movement patterns. The use of HMMs in this paper is mainly related to the opportunity they offer to segment gait data collected at different walking speeds and inclinations of the walking surface. A simple four-state left-right HMM is trained on a dataset of signals collected from a mono-axial gyro during treadmill walking trials performed at different speed and incline values. The gyro is mounted at the foot instep, with its sensitivity axis oriented in the medio-lateral direction. A rule based method applied to gyro signals is used for data annotation. Sensitivity and specificity of phase classification detection higher than 95% are obtained. The estimation accuracy of heel strike, flat foot, heel off and toe off events is about 35 ms on average.