Human gait model based on a machine learning and filtering noisy signals with recursive algorithm

Gait analysis is widely used by doctors to detect anomalies and conclude possible treatments to patient. Conventionally, the gait analysis has been considered subjectively and now is use the technology to improve the data information. The sensors noises, however, causes errors in kinematic data to analyze any waveform, and this analysis requires a large amount of noiseless data for using artificial intelligent. In contrast, this paper presents an initial study about acquiring human gait parameters and data to get a model using computer learning. Therefore, we developed a portable acquisition system noninvasive using an online recursive algorithm in a micro-controller for processing and filtering signals of wearable sensors. The Data Acquisition Signal (DAS) system utilizes a Force Sensitive Resistor (FSR) on the heel and two inertial sensors, one in the thigh and one in the leg, to measure the knee angle; such system calibrates automatically the inertial sensors in each experiment. DAS system has a user-interface that includes intelligent algorithms to normalize, interpolate, and obtain the model curve with fitting of the data showing the gait phases. Our experiments were tested on non-pathology patients with different ages (young, adult and elder) with normal gait pattern selected by a physiotherapist. To know the reliability of the kinematic model, we altered the gait of each patient by shifting the floor and footwear. The results and the gait models seen by the physiotherapist were displayed on an interface.