A New Approach for Motor Imagery Classification Based on Sorted Blind Source Separation, Continuous Wavelet Transform, and Convolutional Neural Network

• Published in: Sensors (Basel, Switzerland) Vol. 19; no. 20; p. 4541
• Main Authors: Ortiz-Echeverri, César J, Salazar-Colores, Sebastián, Rodríguez-Reséndiz, Juvenal, Gómez-Loenzo, Roberto A
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 18.10.2019; MDPI
• Subjects: Algorithms; blind source separation; Brain research; brain-computer interface; Classification; Continuous wavelet transform; convolutional neural network; Deep learning; Discriminant analysis; Electrodes; Electroencephalography; Human-computer interface; Image classification; movement related independent component; Neural networks; Normal distribution; Random variables; Separation; Signal processing; Signal to noise ratio; Spatial resolution; Spectral correlation; wavelet transform; Wavelet transforms; Blind Source Separation; Convolutional Neural Network; Wavelet Transform; Brain-Computer Interface; Movement Related Independent Component
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s19204541

Brain-Computer Interfaces (BCI) are systems that allow the interaction of people and devices on the grounds of brain activity. The noninvasive and most viable way to obtain such information is by using electroencephalography (EEG). However, these signals have a low signal-to-noise ratio, as well as a low spatial resolution. This work proposes a new method built from the combination of a Blind Source Separation (BSS) to obtain estimated independent components, a 2D representation of these component signals using the Continuous Wavelet Transform (CWT), and a classification stage using a Convolutional Neural Network (CNN) approach. A criterion based on the spectral correlation with a Movement Related Independent Component (MRIC) is used to sort the estimated sources by BSS, thus reducing the spatial variance. The experimental results of 94.66% using a k-fold cross validation are competitive with techniques recently reported in the state-of-the-art.