Multiclass Classification of Spatially Filtered Motor Imagery EEG Signals Using Convolutional Neural Network for BCI Based Applications

• Published in: Journal of medical and biological engineering Vol. 40; no. 5; pp. 663 - 672
• Main Authors: Shajil, Nijisha, Mohan, Sasikala, Srinivasan, Poonguzhali, Arivudaiyanambi, Janani, Arasappan Murrugesan, Arunnagiri
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.10.2020; Springer Nature B.V
• Subjects: Artificial neural networks; Bandpass filters; Biomedical Engineering and Bioengineering; Cell Biology; Classification; Classifiers; EEG; Electroencephalography; Engineering; Feet; Frequency ranges; Human-computer interface; Image classification; Imaging; Machine learning; Mental task performance; Muscles; Neural networks; Neuromuscular diseases; Original Article; Paralysis; Radiology; Signal classification; Signal processing; Skeletal muscle; Spectrograms; Training; Brain-computer interface; EEG data; Motor imagery; Common spatial pattern; Convolutional neural network; Spectrogram
• ISSN: 1609-0985; 2199-4757
• DOI: 10.1007/s40846-020-00538-3

Purpose Brain–Computer Interface (BCI) system offers a new means of communication for those with paralysis or severe neuromuscular disorders. BCI systems based on Motor Imagery (MI) Electroencephalography (EEG) signals enable the user to convert their thoughts into actions without any voluntary muscle movement. Recently, Convolutional neural network (CNN) is used for the classification of MI signals. However, to produce good MI classification, it is necessary to effectively represent the signal as an input image to the CNN and train the deep learning classifier using large training data. Methods In this work, EEG signals are acquired over 16 channels and are filtered using a bandpass filter with the frequency range of 1 to 100 Hz. The processed signal is spatially filtered using Common Spatial Pattern (CSP) filter. The spectrograms of the spatially filtered signals are given as input to CNN. A single convolutional layer CNN is designed to classify left hand, right hand, both hands, and feet MI EEG signals. The size of the training data is increased by augmenting the spectrograms of the EEG signals. Results The CNN classifier was evaluated using MI signals acquired from twelve healthy subjects. Results show that the proposed method achieved an average classification accuracy of 95.18 ± 2.51% for two-class (left hand and right hand) and 87.37 ± 1.68% for four-class (Left hand, Right hand, Both hands, and Feet) MI. Conclusion Thus, the method manifests that this 2D representation of 1D EEG signal along with image augmentation shows a high potential for classification of MI EEG signals using the designed CNN model.