Hand and Foot Movement of Motor Imagery Classification using Wavelet Packet Decomposition and Multilayer Perceptron Backpropagation Prasetyo Cahyo Nugroho (a), Rahmat Widadi (b), Dodi Zulherman (c*)
a), b), c) Faculty of Telecommunication and Electrical Engineering, Institut Teknologi Telkom Purwokerto
Jalan D.I. Panjaitan 128, Purwokerto 53147, Indonesia
*zulherman.dodi[at]ittelkom-pwt.ac.id
Abstract
The development of bionic aids for paralyzed patients leads to the implementation of the Brain Computer Interface (BCI) that has various obstacles, especially in interpreting brain signals as triggers for the bionic organ. The reading of electrical signal activity in the brain in the BCI system uses signal electroencephalography (EEG), which comes from many electrodes in the head area and is non-stationary. The measured EEG signal contains much information, including information for the hands and feet motor imagery, so a classification system is needed to separate the information to be processed, such as hand and foot movements. This research aims to develop an imagery motor classification system for the hands and feet so that signals can be classified correctly. The system design is made through several stages of the signal processing process consisting of the pre-processing stage using centering, the feature extraction stage with Wavelet Packet Decomposition (WPD), and Multilayer Perceptron Back Propagation (MLP-BP) as the classifier. Based on the result, this study gets the highest accuracy value about 26.8% at level three and gain above 0.02. This small accuracy is due to the large error due to underfitting.
