Abstract:
Electroencephalography (EEG) is one of the most clinically and scientifically exploited signals recorded from humans. Hence, its measurement plays a prominent role in brain studies. In particular, the examination of EEG signals has been recognized as the most preponderant approach to the problem of extracting knowledge of the brain dynamics.
We proposed an EEG signals measurement and analysis methods for BCI. Our purpose of this study is to recognize subject’s intention when they move their arms. EEG signals are recorded during the imaginary movement of subject’s arms at electrode positions C3, CZ and C4. We analyzed ERS (Event-Related Synchronization) and ERD (Event-Related Desynchronization) which are detected when people move their limbs in the mu wave and beta wave. Results of this study showed that ERD occurred in mu waves and ERS occurred in beta waves at C3 during the imaginary movement of right arm. Similarly, ERD occurred in mu waves and ERS occurred in beta waves at C4 during the imaginary movement of left arm.
Deep learning approaches have been used successfully in many recent studies to learn features and classify different types of data. However, the number of studies that employ these approaches on BCI applications is very limited. In this study we aim to use deep learning methods to improve classification performance of EEG motor imagery signals. In this dissertation we investigate residual network architecture to classify EEG Motor Imagery signals. A new form of input is introduced to combine time, frequency information extracted from EEG signal and it is used as an input to convolutional layers.
The classification performance obtained by the proposed method on BCI competition IV dataset 2b in terms of accuracy is 84.9%, which is to the best of our knowledge is the highest accuracy on underlying dataset. Our results show that deep learning methods provide better classification performance compared to other state of art approaches. These methods can be applied successfully to BCI systems where the amount of data is large due to daily recording.
