Improving pre-movement patterns detection with multi-dimensional EEG features for readiness potential decrease

Abstract Objective : The Readiness Potential (RP) is an important neural characteristic in motor preparation-based brain-computer interface (MP-BCI). In our previous research, we observed a significant decrease of the RP amplitude in some cases, which severely affects the pre-movement patterns detection. In this paper, we aimed to improve the accuracy of pre-movement patterns detection in the condition of RP decrease.
Approach : We analyzed multi-dimensional EEG features in terms of time-frequency, brain networks, and cross-frequency coupling. And, a multi-dimensional Electroencephalogram feature combination (MEFC) algorithm was proposed. The features used include: 1) waveforms of the RP; 2) energy in alpha and beta bands; 3) brain network in alpha and beta bands; and 4) cross-frequency coupling value between 2 and 10 Hz. 
Main results: By employing support vector machines, the MEFC method achieved an average recognition rate of 88.9% and 85.5% under normal and RP decrease conditions, respectively. Compared to classical algorithm, the average accuracy for both tasks improved by 7.8% and 8.8% respectively. 
Significance: This method can effectively improve the accuracy of pre-movement patterns decoding in the condition of RP decrease.