Canonical Correlation Analysis Applied to Remove Muscle Artifacts From the Electroencephalogram

Clercq, Wim De; Vergult, Anneleen; Vanrumste, Bart; Paesschen, Wim Van; Huffel, Sabine Van

doi:10.1109/tbme.2006.879459

Cited by 441 publications

(292 citation statements)

References 14 publications

Supporting

Mentioning

275

Contrasting

Unclassified

Order By: Relevance

“…In Fig. 1, the artificial noise is added to a complete 12.5 hour EEG recording (using the publicly available data from [27], [28]). This long EEG record is then split into multiple shorter duration EEG sections, and the correlation in each section plotted against the duration of these shorter sections.…”

Section: Noise Correlationmentioning

confidence: 99%

Towards Noise-Enhanced Augmented Cognition

Casson

2013

Foundations of Augmented Cognition

View full text Add to dashboard Cite

Abstract. Workload classification Augmented Cognition systems aim to detect when an operator is in a high or low workload state, and then to modify their work flow and operating environment based upon this knowledge. This paper reviews state-of-the-art electroencephalography (EEG) recorders for use in such systems and investigates the impact of EEG noise on an example system performance. It is found that adding up to 15 µV RMS of artificially generated noise still leaves EEG signals that have correlations in-line with the correlations found between conventional wet EEG electrodes and new dry electrodes. The workload classification system is found to be robust in the presence of small amounts of noise, and there is initial evidence of small stochastic resonance effects whereby better performance can actually be obtained in the noisy case compared to the traditional noise-less case.

show abstract

Section: Noise Correlationmentioning

confidence: 99%

Towards Noise-Enhanced Augmented Cognition

Casson

2013

Foundations of Augmented Cognition

View full text Add to dashboard Cite

show abstract

“…The amplitude of these artifacts commonly generated by ocular and muscle activities can be quite large and may thus mask the cortical signals of interest, bias the analysis and interpretation, and affect the performance of the BCI [14], [15]. Several blind source separation techniques have been proposed for signal preprocessing to remove such artifacts.…”

Section: Introductionmentioning

confidence: 99%

“…In these novel EEG devices, dry electrodes act as substitutes for traditional wet electrodes; these dry electrodes can acquire real-time EEG signals for operational workplaces without requiring conductive gel/paste or scalp preparation in BCI applications. An online artifact removal technique based on canonical correlation analysis (CCA) [15] as a blind source separation used to remove artifacts is presented in Section III.A. The feasibility of rapid P3 detection using a radial basis function network (RBFN) [27] under a small number of EEG trials is demonstrated in Section III.B.…”

Section: Introductionmentioning

confidence: 99%

EEG-Based Brain-Computer Interfaces: A Novel Neurotechnology and Computational Intelligence Method

Lin

Liu

et al. 2017

IEEE Syst. Man Cybern. Mag.

View full text Add to dashboard Cite

Abstract-Significant advances in neuroscience, sensor technologies, and efficient signal processing algorithms have greatly facilitated the transition from laboratory-oriented neuroscience research to practical applications. Brain-computer interfaces (BCIs) represent major strides in translating brain signals into actionable decisions and primarily consist of hardware and software that guide the communications between users and systems. This article presents several current neurotechnologies and computational intelligence methods applied to EEG-based BCIs. In the hardware aspect, novel portable EEG devices featuring dry electrodes are introduced as substitutes for traditional BCIs with wet electrodes and its bulky size. With these advantages, these novel EEG devices can acquire real-time EEG signals for operational workplaces without requiring conductive gel/paste or scalp preparations. As for the software aspect, blind source separation, artificial neural networks, effective connectivity measurements and information fusion techniques are introduced to address the technical issues of artifact removal, rapid event-related potential detection, complex brain network description, and decision fusion, respectively. For instance, information fusion technique has been utilized to attack the individual differences problem of motor imagery applications in the real-world environment. With continuous improvements in the development of a convenient approach to record brain signals and extract knowledge regarding intentions, BCI techniques are envisioned to lead to a wide range of real-life applications in the near future.

show abstract

“…In addition, the method is applied to a real ictal EEG recording contaminated with muscle artifacts. The proposed method removed successfully the muscle artifact without altering the recorded underlying ictal activity [3,7].…”

Section: Introductionmentioning

confidence: 99%