Investigating improvements to neural network based EMG to joint torque estimation

Paladyn - 2011
Mervin Chandrapal1, Xiaoqi Chen1, Wenhui Wang1, Benjamin Stanke2, Nicolas Le Pape3
1Mechatronics Research Laboratory, Department of Mechanical Engineering, University of Canterbury, Christchurch, New Zealand
2University of Applied Sciences, Factorial 5: Nature and Engineering, School of Biomimetics, Bremen, Germany
3Ecole Nationale Supérieure d’Ingénieurs de Limoges, 16 rue Atlantis, Parc ESTER Technopole, Limoges, France

Tóm tắt

Abstract Although surface electromyography (sEMG) has a high correlation to muscle force, an accurate model that can estimate joint torque from sEMG is still elusive. Artificial neural networks (NN), renowned as universal approximators, have been employed to capture this complex nonlinear relation. This work focuses on investigating possible improvements to the NN methodology and algorithm that would consistently produce reliable sEMG-to-knee-joint torque mapping for any individual. This includes improvements in number of inputs, data normalization techniques, NN architecture and training algorithms. Data (sEMG) from five knee extensor and flexor muscle from one subject were recorded on 10 random days over a period of 3 weeks whilst subject performed both isometric and isokinetic movements. The results indicate that incorporating more muscles into the NN and normalizing the data at each isometric angle prior to NN training improves torque estimation. The mean lowest estimation error achieved for isometric motion was 10.461% (1.792), whereas the lowest estimation errors for isokinetic motion were larger than 20%.

Từ khóa


Tài liệu tham khảo

Thông tin
Thông tin xuất bản

Paladyn

Thông tin tác giả