A Study on Function Discrimination for EMG Signals Using Neural Network and Fuzzy Filter

신경회로망과 퍼지필터를 사용한 근전도신호의 기능변별에 관한 연구

  • 장영건 (인하대학교 전자공학과) ;
  • 홍승홍 (인하대학교 전자공학과)
  • Published : 1994.09.01

Abstract

The most important requirement for the controller of a prosthetic arm is that it has a high fidelity discriminator where the motion control may be performed open loop using EMG signals as a control source. Therefore, it is very effective method to reduce the influence of misclassification of classifier for the total system performance. This paper presents the new function discrimination method which combines MLP classifier and frizzy filter by stages for the requirement. The major advantage of MLP is a consistent learning capability for the easy adaptation to environments. The fuzzy filter uses all informations of MLP outputs and prior EMG activity informations which increase as the experience increases. That property is superior to one which uses maximum output of MLP in view of information amounts and quality. Simulation result shows that proposed method is superior to the probabilistic model, MLP model and the combined model of both in the respect of discrimination quaity.

Keywords

References

  1. 전자공학회지 v.91-28B-10-10 신경회로망과 확률모델을 이용한 근전도신호의 패턴분류에 관한 논문 장영건;권장우;홍승홍
  2. 의공학회지 v.13 no.1 근전도의 패턴분류와 근력 추정에 관한 연구 권장우;장영건;홍승홍
  3. Proceedings JTC-CSCC '93 The Muscle Force Estimation and the Hybrid Pattern Classifier considering Signal Dynamics Younggun Jang;Seunghong Hong(et al.)
  4. Proceedings of the 15th Annual International Conference of the IEEE EMBS Probabilistic Neural Pattern Classifier and Muscle Force Estimation Younggun Jang;Seunghong Hong(et al.)
  5. RESNA '94 Conference Neshvill, Tennessee EMG Paattern Analysis for Prosthesis Arm Control Younggun Jang;Seunghong Hong(et al.)
  6. Proceedings JTC-CSCC '94 Study on the Fuzzy Controller for Prosthesis Am Control using EMG Signals Younggun Jang;Seunghong Hong
  7. World Congress on Medical Physisc & Biomedical Engineering The Application of Counterpropagation Neural Networks for EMG pattern Classification Jangwoo Kwon;Younggun Jang;Seunghong Hong
  8. Psychological Review v.65 The perceptron : a probdbilistic model for information storage and organization in the brain F.Rosenblatt
  9. IEEE Transon SMC v.5 no.2 Functional Seperation of EMG sinals via ARMA identification methods for prosthesis control purposes Daniel Graupe(et al.)
  10. IEEE Trans on SMC v.29 no.6 EMG pattern analysis and classification for a prosthetic arm George N. Saridis(et al.)
  11. Annual International Conference of the IEEE Engineering in MBS v.12 no.3 EMG pattern classification based on Back propagation neural network for prosthesis contral Tony Khoshaba;Kambiz Badie(et al.)
  12. IEEE Trans on Neural Networks v.1 no.4 The Multilayer Perceptron as on Approximation to a Bayes Optimal Descriminant Function D.W.Ruck;S.K.Rogers(et al.)
  13. IEEE Trans on SMC v.35 no.4 The Electromyogram(EMG) as a control signal for Functional Neuromuscular Stimulation-Part I : Autoregressive Modelling as a Means of EMG Signature Discrimination Gisela Hefftner;Walter Zucchini;George G. Jaros
  14. IEEE Trans on SMC v.36 no.10 The Developement of a Multichannel Time Series Myoprocessor for Simultaneous Limb Function Detection and Muscle Force Estimation Ronald J. Triolo;Gordon D. Moskowitz
  15. Sequential Methods in Pattern Recognition and Machine Learning Fukunaga,K.S.
  16. IEEE Trans on SMC v.16 no.5 Fuzzy Approximation Scheme for Sequential Learning in Pattern Recognition Bharathi B. Devi(et al.)
  17. Inform. Control v.8 Fuzzy Sets L.A.Zadeh
  18. Fuzzy Control Systems Abraham Kandel(et al.)
  19. IEEE Trans on SMC v.41 no.2 Single Site Electromyograph Amplitude Estimation Edward A. Clancy;Neville Hogan
  20. Proceedings of the 1980 Joint Automatic Control Conference Mechanical Impedance Control in Assistive Devices and Manipulators Neville Hogan