An Improved Extreme Learning Machine (ELM) Algorithm for Intent Recognition of Transfemoral Amputees With Powered Knee Prosthesis

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 32; pp. 1757 - 1766
• Main Authors: Zhang, Yao, Wang, Xu, Xiu, Haohua, Chen, Wei, Ma, Yongxin, Wei, Guowu, Ren, Lei, Ren, Luquan
• Format: Journal Article
• Language: English
• Published: United States IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Adult; Algorithms; Amputees - rehabilitation; Artificial neural networks; Classification; Classification algorithms; Classifiers; Extreme learning machine; Femur; human locomotion intent recognition; Humans; Intent recognition; Intention; Knee; Knee Prosthesis; Learning algorithms; Locomotion; Locomotion - physiology; Logistic Models; Machine Learning; Male; Mathematical models; Parameters; Pattern Recognition, Automated - methods; Portable equipment; powered knee prosthesis; Prediction algorithms; Prostheses; Prosthetics; Real time; real-time prediction; Real-time systems; Recognition; Slime molds; Sociology; Training; Trans-femoral amputees; Walking
• ISSN: 1534-4320; 1558-0210
• DOI: 10.1109/TNSRE.2024.3394618

To overcome the challenges posed by the complex structure and large parameter requirements of existing classification models, the authors propose an improved extreme learning machine (ELM) classifier for human locomotion intent recognition in this study, resulting in enhanced classification accuracy. The structure of the ELM algorithm is enhanced using the logistic regression (LR) algorithm, significantly reducing the number of hidden layer nodes. Hence, this algorithm can be adopted for real-time human locomotion intent recognition on portable devices with only 234 parameters to store. Additionally, a hybrid grey wolf optimization and slime mould algorithm (GWO-SMA) is proposed to optimize the hidden layer bias of the improved ELM classifier. Numerical results demonstrate that the proposed model successfully recognizes nine daily motion modes including low-, mid-, and fast-speed level ground walking, ramp ascent/descent, sit/stand, and stair ascent/descent. Specifically, it achieves 96.75% accuracy with 5-fold cross-validation while maintaining a real-time prediction time of only 2 ms. These promising findings highlight the potential of onboard real-time recognition of continuous locomotion modes based on our model for the high-level control of powered knee prostheses.