Multiclass Classification of Spatially Filtered Motor Imagery EEG Signals Using Convolutional Neural Network for BCI Bas
- PDF / 1,131,106 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 62 Downloads / 202 Views
ORIGINAL ARTICLE
Multiclass Classification of Spatially Filtered Motor Imagery EEG Signals Using Convolutional Neural Network for BCI Based Applications Nijisha Shajil1 · Sasikala Mohan1 · Poonguzhali Srinivasan1 · Janani Arivudaiyanambi1 · Arunnagiri Arasappan Murrugesan1 Received: 5 February 2020 / Accepted: 28 May 2020 © Taiwanese Society of Biomedical Engineering 2020
Abstract 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. Keywords Brain-computer interface · EEG data · Motor imagery · Convolutional neural network · Common spatial pattern · Spectrogram
1 Introduction Brain–Computer Interface (BCI) translates signals from the brain and transforms them into useful output with no use of muscles. This technology offers people with impaired motor skills or severely paralyzed patients to perform day-to-day activities by controlling a computer or a peripheral device like a robotic arm or wheelchair only with their thought [1, 2]. * Sasikala Mohan [email protected] 1
Centre for Medical Electronics, Department of Electronics and Communication Engineering, College of Engineering Guindy (CEG), Anna University, Chennai 600025, India
Electroencephalography (EEG) is the most convenient and prominent signal used in the BCI field currently. Motor imagery (MI) EEG signals are produced in the sensorimotor cortex of the brain when a person imagines moving a body part without the actual movement execution. These signals can be used as control commands
Data Loading...
