Estimating gait parameters from sEMG signals using machine learning techniques under different power capacity of muscle

• Published in: Scientific reports Vol. 15; no. 1; pp. 12575 - 15
• Main Authors: Liu, Shing-Hong, Sharma, Alok Kumar, Wu, Bo-Yan, Zhu, Xin, Chang, Chun-Ju, Wang, Jia-Jung
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 12.04.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166/985; 692/700/139; Adult; CatBoost; Correlation coefficient; Electromyography; Electromyography - methods; Fatigue; Female; Gait; Gait - physiology; Gait Analysis - methods; Gait parameters; Humanities and Social Sciences; Humans; Learning algorithms; Machine Learning; Male; multidisciplinary; Muscle fatigue; Muscle Fatigue - physiology; Muscle, Skeletal - physiology; Muscles; Neuromuscular diseases; Random forest; Science; Science (multidisciplinary); Sensors; Surface electromyogram; XGBoost; Young Adult; Surface electromyogram; Random forest; Gait parameters; XGBoost; CatBoost; Machine learning
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-025-95973-0

The gait analysis has been applied in many fields, such as the assessment of falling, force evaluation in sports, and gait disorder detection for neuromuscular diseases. Its main recording techniques include video cameras and wearable sensors. However, the present methods involve measuring surface electromyograms (sEMGs) to analyze muscle activities. The primary goal of this study is to estimate gait parameters under different power capacity of muscle by sEMGs measured from lower limbs. A self-made wireless device recorded sEMGs from two muscles of each foot, and GaitUp Physilog ® 5 sensors captured gait parameters from 18 participants under running as references. Four features including median frequency (MDF), waveform length (WL), standard deviation (SD), and sample entropy (SampEn), were extracted from the sEMG data. The analysis utilized three machine learning models (Random Forest, CatBoost, XGBoost), evaluated through various evaluation metrics. Additionally, 5-fold cross-validation was conducted to assess the influence of muscle fatigue on the estimation of gait parameters. The results show that all models successfully estimated 20 gait parameters, all showing a Pearson correlation coefficient (PCC) above 0.800. However, the performance of models significantly depends on the condition of muscle fatigue. This study represents a significant advancement in gait analysis, providing a comprehensive method for estimating gait parameters from sEMG signals, with important implications for mobile health applications.