KLASIFIKASI SINYAL EMG BERBASIS WAVELET DAN JARINGAN SYARAF TIRUAN

• Main Authors: , ikhwan mustiadi, , Prof. Dr. Thomas Sri Widodo, D.E.A
• Format: Theses and Dissertations NonPeerReviewed
• Published: [Yogyakarta] : Universitas Gadjah Mada 2013
• Subjects: ETD
• Online Access: https://repository.ugm.ac.id/126173/; http://etd.ugm.ac.id/index.php?mod=penelitian_detail&sub=PenelitianDetail&act=view&typ=html&buku_id=66371
• Institution: Universitas Gadjah Mada

Electromyograph (EMG) Signal is a biomedical signal that non-stationary, making it difficult to determine a pattern. The method is usually used for signal analysis is the Fast Fourier Transform (FFT), but has a number of lack of due have to stable signal. To answer this deficiency used wavelet transform, especially discrete wavelet transform to analyze signals in both time and frequency domains. The method used in this study is the wavelet transform for signal analysis by decomposition up to level 7 using wavelet symlet 8. Results of feature extraction is used as input Neural Network (ANN) with back propagation architecture type 8 units of input layer, 5 units of hidden layer and 3 units of output layer ANN can recognize patterns of EMG signals with the architecture of the EMG signal success rate for a healthy 74%, myopathy 96% and neuropathy 84%. So that the architecture is proposed for classification EMG signals.