AE-CNN-Based Multisource Data Fusion for Gait Motion Step Length Estimation

Abstract

Step length estimation is essential for people to overcome different types of environmental obstacles in daily life. Aiming at the problem of low estimation accuracy based solely on surface electromyography (sEMG), in this article, a multisource (MS) data fusion method based on an auto-encoder-convolutional neural network (AE-CNN) is proposed to estimate the motion parameters of human lower limbs, which improve the accuracy of step length estimation. Specifically, the time-domain feature data (TDFD) of sEMG and insole pressure data from the lower limbs are first collected simultaneously to form the MS. Then, by applying auto-encoder (AE) as the fusion units, fused data are obtained and dimensionality reduction is realized. Finally, by integrating AE and convolutional neural network (CNN), the step length can be well estimated by utilizing the MS. For experimental validation, the performances of different data fusion units and regression units in step length estimation are compared. The results show that the proposed method can achieve good estimation. The normalized root-mean-square error (NRMSE) and Pearson correlation coefficient (PCC) of the proposed method reach 0.0479 ± 0.0263 and 0.8273 ± 0.1082, respectively. The NRMSE of the best trial is 0.0217 and the PCC is 0.9774. Furthermore, experiments at different walking speeds are carried out. The results show that the combination of AE and CNN has good performance with the increase in walking speed. In addition, a dimensionality reduction experiment based on AE is also carried out, and the optimal dimension is obtained.