Abstract

Gait cycle analysis is widely practiced to determine alterations of normal walking. The challenge is to choose the ideal systems that suit the studies. One possibility is to measure the interaction of the sole and the support surface and detect gait events related to the positioning of the foot. This work proposes a gait subphase classification based on Hidden Markov Model that identifies gait stance subphases from a foot pressure measurement. A sensorized insole was used to record the pressure under the foot with eight custom-made capacitive sensors. Tests were performed on six volunteers with a 10-meter trial test. Mean cadence and stance/swing ratio were calculated. These parameters match the normal range for the age of the volunteers found in the literature. The results show that the proposed model can classify the gait in 5 subphases using the Center of Pressure (CoP) anteroposterior position and velocity as input. Changes in the slope of the CoP marks the step between subphases. Clinical Relevance - Most gait studies are performed in highly equipped gait laboratories. Due to technical requirements and the high cost of implementing a gait laboratory, access to these services is difficult for a large population. For this reason, it is necessary to develop equipment, devices, and algorithm to further study pathological and healthy gait.