Prediction of Motor Imagery Performance based on Pre-Trial Spatio-Spectral Alertness Features.

Electroencephalogram (EEG) based brain-computer interfaces (BCIs) enable communication by interpreting the user intent based on measured brain electrical activity. Such interpretation is usually performed by supervised classifiers constructed in training sessions. However, changes in cognitive states of the user, such as alertness and vigilance, during test sessions lead to variations in EEG patterns, causing classification performance decline in BCI systems. This research focuses on effects of alertness on the performance of motor imagery (MI) BCI as a common mental control paradigm. It proposes a new protocol to predict MI performance decline by alertness-related pre-trial spatio-spectral EEG features. The proposed protocol can be used for adapting the classifier or restoring alertness based on the cognitive state of the user during BCI applications.

EEG Artifacts Handling in a Real Practical Brain-Computer Interface Controlled Vehicle.

One of the main issues restricting the practical efficiency of brain-computer interface (BCI) systems is the inevitable occurrence of physiological artifacts during electroencephalography (EEG) recordings. The effects of the artifacts are, however, mostly discarded in practical BCI systems, due to the time-consuming and complicated computational processes. This paper presents the influences of the artifacts and the efficiency of reducing these influences in a practical BCI. Ocular and muscular artifacts are considered due to the high-amplitude and frequent presence. The paradigm is designed based on the mental controlling of a radio-control (RC) car. Two motor imagery commands, containing the imagination of movement of left/right hand, are used to navigate the BCI-based RC car to turn left/right. The results indicate that the artifacts can highly affect the system performance; reducing their influence significantly improves the efficiency.