Continuous estimation of kinetic variables while walking using an accelerometer and artificial neural networks

Abstract

Measuring the gait variables outside the laboratory is so important because they can be used to analyze walking in the long run and during real life situations. Wearable sensors like accelerometer show high potential in these applications. So, the aim of this study was continuous estimation of kinetic variables while walking using an accelerometer and artificial neural networks. Seventy-three subjects (26 women and 47 men) voluntarily participated in this study. The subjects walked at the slow, moderate, and fast speeds on a walkway which covered with 10 Vicon camera. Acceleration was used as input for a Feedforward Neural Networks (FFNN) to predict the lower limb moments (in sagittal, frontal, and transverse planes), power, and Grand Reaction Force (GRF) (in medial-lateral (M-L), anterior-posterior (A-P), and vertical directions during walking. Normalized Root Mean Square Error (nRMSE), and Pearson correlation coefficient () were computed between the measured and predicted variables. Statistical Parametric Mapping (SPM) was used to compare the measured and predicted variables. The results of this study showed approximately values of 91 to 99 and nRMSE values of 4 to 15 percent for GRF, power, and moment between the measured and predicted data. The SPM showed no significant difference between the measured and predicted variables in throughout stance phase. This work has shown the potential of predicting kinetic variables (GRF, moment, and power) in various speeds of walking using the accelerometer. The proposed estimation procedure utilizing a mixture of biomechanics and Artificial Neural Networks (ANN) can be used to solve the tradeoff between richness of data and ease of measuring inherent in wearable sensors