신경회로망과 유전알고리즘을 이용한 근전신호 인식기법

A new recognition technique using neural network coupled with Genetic Algorithms (GAs) was proposed. This technique concentrate on efficient Electromyography signal recognition through put improving neural network's several demerits. GAs play a role of selecting Multilayer PerceptrorTs optimized initial connection weights by its typical global search. Electro Myography signal was pre-processed with Hidden Markov Model (HMM) in order to reflect its time-varying property into input pattern except other features such as Zero Crossing Number (ZCN) and Integral Absolute Value (IAV). Results for 6 primitive motions show that the surges ted technique has better performance in learning time and recognition rates than already established ordinary methods. Moreover, it performed stable recognition without convergence into a local minimum.