A novel method of improving EEG signals for BCI classification

[摘要] ENGLISH ABSTRACT: Muscular dystrophy, spinal cord injury, or amyotrophic lateral sclerosis (ALS)are injuries and disorders that disrupts the neuromuscular channels of thehuman body thus prohibiting the brain from controlling the body. Brain computerinterface (BCI) allows individuals to bypass the neuromuscular channelsand interact with the environment using the brain. The system relies on theuser manipulating his neural activity in order to control an external device.Electroencephalography (EEG) is a cheap, non-invasive, real time acquisitiondevice used in BCI applications to record neural activity. However, noise,known as artifacts, can contaminate the recording, thus distorting the trueneural activity. Eye blinks are a common source of artifacts present in EEGrecordings. Due to its large amplitude it greatly distorts the EEG data makingit difficult to interpret data for BCI applications. This study proposes a newcombination of techniques to detect and correct eye blink artifacts to improvethe quality of EEG for BCI applications.Independent component analysis (ICA) is used to separate the EEG signalsinto independent source components. The source component containing eyeblink artifacts are corrected by detecting each eye blink within the source componentand using a trained wavelet neural network (WNN) to correct only asegment of the source component containing the eye blink artifact. Afterwards,the EEG is reconstructed without distorting or removing the source component.The results show a 91.1% detection rate and a 97.9% correction ratefor all detected eye blinks. Furthermore for channels located over the frontallobe, eye blink artifacts are corrected preserving the neural activity. The novelcombination overall reduces EEG information lost, when compared to existingliterature, and is a step towards improving EEG pre-processing in order toprovide cleaner EEG data for BCI applications.

[发布机构] Stellenbosch University