Detection of gait variations by using artificial neural networks.

Walking is an everyday activity and contains variations from person to person, from one step to another step. The variation may occur due to the uniqueness of each gait cycle, personal parameters, such as age, walking speed, etc., and the existence of a gait abnormality. Understanding the normal variation depending on personal parameters helps medical experts to identify deviations from normal gait and engineers to design compatible orthotic and prosthetic products. In the present study, we aimed to obtain normal gait variations based on age, sex, height, weight, and walking speed. For this purpose, a large dataset of walking trials was used to model normal walking. An artificial neural network-based gait characterization model is proposed to show the relation between personal parameters and gait parameters. The neural network model simulates normal walking by considering the effect of personal parameters. The predicted behavior of gait parameters by artificial neural network model has a similarity with existing literature. The differences between experimental data and the neural network model were calculated. To determine how much deviation between predictions and experiments can be considered excessive, the distributions of differences for each gait parameter were obtained. The phases of walking in which excessive differences were intensified were determined. It was revealed that the artificial neural network-based gait characterization model exhibits the behavior of the normal gait parameters depending on the personal parameters.