Predicting Gait Parameters of Leg Movement with sEMG and Accelerometer Using CatBoost Machine Learning

Abstract

This study aims to evaluate leg movement by integrating gait analysis with surface electromyography (sEMG) and accelerometer (ACC) data from the lower limbs. We employed a wireless, self-made, and multi-channel measurement system in combination with commercial GaitUp Physilog® 5 shoe-worn inertial sensors to record the walking patterns and muscle activations of 17 participants. This approach generated a comprehensive dataset comprising 1452 samples. To accurately predict gait parameters, a machine learning model was developed using features extracted from the sEMG signals of thigh and calf muscles, and ACCs from both legs. The study utilized evaluation metrics including accuracy (R2), Pearson correlation coefficient (PCC), root mean squared error (RMSE), mean absolute percentage error (MAPE), mean squared error (MSE), and mean absolute error (MAE) to evaluate the performance of the proposed model. The results highlighted the superiority of the CatBoost model over alternatives like XGBoost and Decision Trees. The CatBoost’s average PCCs for 17 temporospatial gait parameters of the left and right legs are 0.878 ± 0.169 and 0.921 ± 0.047, respectively, with MSE of 7.65, RMSE of 1.48, MAE of 1.00, MAPE of 0.03, and Accuracy (R2-Score) of 0.91. This research marks a significant advancement by providing a more comprehensive method for detecting and analyzing gait statuses.