A Deep Learning Approach to Classify Motor Imagery Based on The Combination of Discrete Wavelet Transform and Convolutional Neural Network for Brain Computer Interface System

Elnaz Azizi | 2018

4 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: English
  3. Document No: 51986 (58)
  4. University: Sharif University of Technology, International Campus, Kish Island
  5. Department: Science and Engineering
  6. Advisor(s): Selk Ghafari, Ali; Zabihollah, Abolghssem
  7. Abstract:
  8. A Brain-Computer Interface (BCI) is a communication system that does not need any peripheral muscular activity. The huge goal of BCI is to translate brain activity into a command for a computer. One of the most important topics in the brain-computer interface is motor imagery (MI), which shows the reconstruction of subjects. The electrical activities of the brain are measured as electroencephalogram (EEG). EEG signals behave as low to noise ratio also show the dynamic behaviors.In the present work, a novel approach has been employed which is based on feature extraction with discretion wavelet transform (DWT), support vector machine (SVM), Artificial Neural Network (ANN) and Convolutional Neural Network (CNN) for classification, which will show the time and frequency features. It is essential to clearly understand the left-hand and right-hand features are used in different channels.The EEG signals do not have any useful frequency components above 30 Hz, and the number of decomposition levels was chosen to be 4. Thus, the EEG signals were decomposed into details D5–D8 and one final approximation, A8.The features were extracted by DWT and then were classified with different classifiers such as ANN, SVM, and CNN, therefore, the cost of the processing will reduce dramatically. By applying SVM classifier with the utilization of the RBF kernel, we categorized the features that separate the right hand from the left. The features extracted by DWT, and CNN, with respect to other classifiers, show the more accurate response for the utilization of right hand and left-hand features. The result shows that CNN classifier has more careful performance in separation of two class features including Right-hand and Left-hand than that of SVM and ANN. However, by using right C3 and Cz, the average accuracy increases to 99.56%, which shows CNN trains and test in the best way
  9. Keywords:
  10. Deep Learning ; Machine Learning ; Signal Processing ; Discrete Wavelet Transform (DWT) ; Electroencphalogram ; Brain-Computer Interface (BCI) ; Convolutional Neural Network ; Artificial Neural Network

 Digital Object List