Walking Speed Estimation From a Wearable Insole Pressure System Embedded With an Accelerometer Using Bayesian Neural Network

Abstract

In this study, we introduced a machine learning method for estimating human walking speed using plantar pressure and acceleration data. A pressure-derivative method using pretest feature selection was proposed to extract speed-related features from plantar pressure sensors. The maximum, minimum, and standard deviation of acceleration data were also selected as neural network inputs. To improve the generalization ability of the neural network, Bayesian regularization method was adopted. Experiments were conducted under seven different walking speeds to validate the performance of the proposed method. The results show that a strong linear correlation (R = 0.995) exists between the estimated and actual walking speed. The average error of the proposed method is 0.003 ± 0.043 m/s (mean ± root-mean-square error), which is better than previous works. It is suggested that including the speed-related information of both stance and swing phase would give a new insight for achieving a high accuracy of walking speed estimation.