Study on the effect of different electrode channel combinations of motor imagery EEG signals on classification accuracy

Abstract

In order to improve the performance of motor imagery brain–computer interface (BCI) based on deep learning algorithm, here, the authors propose an electrode channel combination method. Although motor imagery electro-encephalography (EEG) signals which contain different electrode channels on the scalp surface have an effect on the classification performance, the effect of different electrode channel combinations has not been systematically explored. With the two deep learning models the authors constructed, the authors list some different electrode channel combinations to classify the left fist and right fist motor imagery EEG signals. The results show that the more the number of channels in these combinations, the higher the classification accuracy. However, when the number of channels exceeds 11, the classification accuracy increases slowly, and the classification effect is rarely improved. Therefore, the authors obtain an optimal electrode channel combination to use the electrode channels efficiently and to improve the performance of motor imagery BCI based on deep learning algorithms.

Keywords

• brain-computer interfaces
• signal classification
• electroencephalography
• learning (artificial intelligence)
• medical signal processing
• different electrode channel combinations
• motor imagery eeg
• classification accuracy
• motor imagery brain–computer interface
• deep learning algorithm
• electrode channel combination method
• motor imagery electro-encephalography signals
• different electrode channels
• fist motor imagery
• classification effect
• optimal electrode channel combination
• motor imagery bci