FORCe: Fully Online and Automated Artifact Removal for Brain-Computer Interfacing

Abstract

A fully automated and online artifact removal method for the electroencephalogram (EEG) is developed for use in brain-computer interfacing (BCI). The method (FORCe) is based upon a novel combination of wavelet decomposition, independent component analysis, and thresholding. FORCe is able to operate on a small channel set during online EEG acquisition and does not require additional signals (e.g., electrooculogram signals). Evaluation of FORCe is performed offline on EEG recorded from 13 BCI particpants with cerebral palsy (CP) and online with three healthy participants. The method outperforms the state-of the-art automated artifact removal methods Lagged Auto-Mutual Information Clustering (LAMIC) and Fully Automated Statistical Thresholding for EEG artifact Rejection (FASTER), and is able to remove a wide range of artifact types including blink, electromyogram (EMG), and electrooculogram (EOG) artifacts.

Hybrid Brain–Computer Interface Techniques for Improved Classification Accuracy and Increased Number of Commands: A Review

“…Also, entailing the removal of EOG signals (using eye tracking), thresholding has been reported to increase classification accuracy [usingstep-wise LDA (SW-LDA)] from 44.7 to 73.1% in hBCI (Yong et al, 2012). Independent component analysis (ICA), genetic algorithm (GA), and particle swarm optimization for EOG artifact detection and removal also have been reported in the literature (Hsu, 2013a,b; Daly et al, 2015; Li et al, 2015; Yang et al, 2015). Bai et al (2016) has recently proposed an ICA-based method to reduce the muscular/blink artifacts appearing in the prefrontal cortex after brain stimulation.…”

“…Second, classification accuracy can be improved by utilizing one device’s signal in the artifact removal in another device’s brain signal. For instance, the peak value of electrooculography (EOG) caused by an eye blink (i.e., a motion artifact) can be subtracted from EEG’s data, in which the eye blink (or muscular movement) induces a false-positive value (McFarland and Wolpaw, 2011; Daly et al, 2015). The most common artifact removal means from brain signals are EOG (Bashashati et al, 2007; Jiang et al, 2014) and electromyography (EMG) (Fatourechi et al, 2007).…”

Heading for new shores! Overcoming pitfalls in BCI design

“…Artifacts are interference signals that share some of the characteristic features of EEG and can produce misleading EEG signals or destroy them altogether. When developing BCIs, one has to take care that cortical signals are used for communication and control and not artifacts [96-98]. Muscle artifacts, for example, are highly correlated to the user’s behavior and have much higher amplitudes.…”

Affective brain–computer music interfacing

“…The automated artefact removal method "Fully automated and online artefact removal for Brain-computer interfacing" (FORCe), was used to remove artefacts from this offline data by decomposing the signal via, first, wavelets and then independent component analysis, before applying a combination of pre-trained soft and hard thresholds (Daly, Scherer, Billinger and Muller-Putz 2014). The accelerometer signal was also used to inform the application of the FORCe method as detailed in (Daly, Billinger, Scherer and Mueller-Putz 2013).…”