Classification of EEG Signals by Using Transfer Learning on Convolutional Neural Networks via Spectrogram

Top A. E. , Kaya H.

International Conference on Engineering Technologies, Konya, Turkey, 26 - 28 October 2018, pp.156-161

  • Publication Type: Conference Paper / Full Text
  • City: Konya
  • Country: Turkey
  • Page Numbers: pp.156-161


Previous studies on classifying Electroencephalography (EEG) sleep data generally use the signal itself. Many of these studies need series of pre-processing operations, manual feature extraction, complex and hard application processes. There is no need for lots of pre-processing stages in Convolutional Neural Networks (CNN) and features can be learned automatically instead of using manually extracted features. Also CNNs have better performance over most of other methods in visual classification. The study presented in this paper is based on applying transfer learning with CNNs via spectrogram images, that were obtained by using Short-Time Fourier Transform (STFT), on ISRUC-Sleep dataset (ISRUC) for classifying EEG signals. AlexNet trained with 100 patient subjects from ISRUC was used as pre-trained CNN. For classifying sleep stages, single-channel EEG data, that was taken from 10 healthy people, was used as target domain. To reduce overfitting, we employed an image translation operation and images were augmented horizontally. The main purpose of using transfer learning method in this study is achieving better training duration and accuracy. Applying transfer learning increased the accuracy of the classification by 3.11%, when compared to the result of using non-pretrained AlexNet, which was trained from scratch. For the evaluation of the proposed methodology, non-pretrained AlexNet and AlexNet trained with ImageNet were also performed on the same target domain and the results were compared. When the source domain of transfer learning was ImageNet, the accuracy was decreased by 2.73% compared to the result of training from scratch. Results showed that transfer learning increases the accuracy when target and source domains are similar, but it may decrease the accuracy when used on different domains (i.e., ImageNet includes images and ISRUC consists of signals). Keywords - Electroencephalography (EEG), Convolutional Neural Network (CNN), transfer learning, spectrogram, Short-Time Fourier Transform (STFT).