Human lower extremity joint moment prediction: A wavelet neural network approach

• Published in: Expert systems with applications Vol. 41; no. 9; pp. 4422 - 4433
• Main Authors: Ardestani, Marzieh Mostafavizadeh, Zhang, Xuan, Wang, Ling, Lian, Qin, Liu, Yaxiong, He, Jiankang, Li, Dichen, Jin, Zhongmin
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01.07.2014; Elsevier
• Subjects: Accuracy; Applied sciences; Artificial intelligence; Artificial neural network; Biological and medical sciences; Biomechanics; Biomechanics. Biorheology; Computer science; control theory; systems; Connectionism. Neural networks; Dynamics; Exact sciences and technology; Fundamental and applied biological sciences. Psychology; Gait; Ground reaction force; Human; Joint moment prediction; Marker trajectory; Mathematical models; Mathematics; Mutual information; Neural networks; Parametric inference; Probability and statistics; Sciences and techniques of general use; Simulation; Software; Statistics; Tissues, organs and organisms biophysics; Wavelet; Wavelet neural network; Joint moment prediction; Artificial neural network; Wavelet neural network; Ground reaction force; Mutual information; Marker trajectory; Gait; Input signal; N body system; Lower extremity; Human factor; Dynamic method; Mean square error; Posture; Electromyography; Metamodel; Correlation coefficient; Factor analysis; Motion estimation; Neural network; Real time; Biomechanics; Wavelet transformation; Cross correlation; Factorial design

•WNN is proposed as a real-time surrogate for joint moment prediction.•WNN predicts joint moments based on GRFs and EMG signals.•Generalization ability is tested for a new subject and a new gait pattern. Joint moment is one of the most important factors in human gait analysis. It can be calculated u...