Wireless smart shoe for gait analysis with automated thresholding using PSO

This paper proposes a novel decision system for segregation of five normal gait phases (stance, heel-off, swing 1, swing 2 and heel-strike) by using a real-time wireless smart shoe. The classification employs four force sensitive resistors (FSR) to measure the force underneath a foot together with an inertia measurement unit (IMU) that is attached at the back of the shoe. IMU gives the magnitude of acceleration and inclination angle of the foot with respect to the ground. Data acquisition is collected through XBee wireless network protocol in order to be processed serially by a computer. State transition theorem and threshold-based classification are used to distinguish gait phases according to received data, where the thresholds are optimized by particle swarm optimization. Video recording with real-time data and embedded interfacing is used to verify the output of the proposed state transition algorithm when tested in an indoor environment on a stationary treadmill. Experimentation and verification is conducted on a subject with a normal walking gait cycle.