Title :
A diagonal recurrent neural network based FES system for the knee joint position control
Author :
Luh, Jer-Junn ; Chang, Gwo-Ching ; Lai, Jin-Shin ; Cheng, Cheng-Kung ; Kuo, Te-Son ; Lee, Jau-Fa
Author_Institution :
Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
fDate :
28 Oct-1 Nov 1998
Abstract :
A diagonal recurrent neural network (DRNN) based functional electrical stimulation (FES) system was designed to control the knee joint to move in accordance with the desired trajectory of movement through stimulation of quadriceps muscle. This system, which consisted of a DRNN controller and a DRNN identifier, could learn the nonlinearity of the plant (knee joint) and control it both in on-line condition. The knee joint angle was controlled with only small deviations along the desired trajectory with the aid of the neural controller
Keywords :
backpropagation; biocontrol; neurocontrollers; neuromuscular stimulation; position control; recurrent neural nets; FES system; backpropagation; desired trajectory; diagonal recurrent neural network based; knee joint angle; knee joint position control; neural controller; on-line condition; plant nonlinearity learning; quadriceps muscle stimulation; Artificial neural networks; Backpropagation algorithms; Control systems; Knee; Muscles; Neural networks; Neuromuscular stimulation; Neurons; Position control; Recurrent neural networks;
Conference_Titel :
Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE
Conference_Location :
Hong Kong
Print_ISBN :
0-7803-5164-9
DOI :
10.1109/IEMBS.1998.744985