Simultaneous Control of Artificial Limbs Based On Hybrid Extreme Learning Machine Algorithm
English

Daniel C, Aruna R
2015 International Journal of Innovative Research in Computer and Communication Engineering  
Highly developed artificial limb prostheses able of actuating many degrees of freedom (DOF) at the present open access obtainable. Pattern identification based algorithms with the purpose of make use of surface electromyography (EMG) signals calculated beginning residual muscles demonstrate huge assure as multi-DOF controllers. Unfortunately, existing pattern recognition scheme is restricted to sequential manage of every DOF. The prediction of instantaneous limb movement is an extremely
more » ... ve feature designed to manage of synthetic limbs. In this work, we proposed novel Hybrid Extreme Learning Machine (HELM) classification methods for the prediction of the limb movement and control them for individual through myoelectric signals. The HELM pattern recognition methods create a hybrid kernel function through fully mingle local kernel function forecast of the limb group. HELM pattern recognition suggests with the purpose of whichever classifier be able to be potentially working in the calculation of instantaneous actions if prearranged in a distributed topology. In another way the proposed pattern recognition classifiers essentially able of simultaneous predictions, such as the HELM, were found to be present technique more cost efficient, as they are able to be successfully working in their simplest form. The high accuracy of the HELM method suggests with the intention of pattern recognition techniques is able to be extensive to allow simultaneous control, life-like actions, finally increasing their feature of life.
doi:10.15680/ijircce.2015.0306014 fatcat:exnebbag7fcipdyd6ctpzu5vie