Removal of EEG artifacts for BCI applications using fully Bayesian tensor completion

• Published in: Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 819 - 823
• Main Authors: Yu Zhang, Qibin Zhao, Guoxu Zhou, Jing Jin, Xingyu Wang, Cichocki, Andrzej
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.03.2016
• Subjects: Artefacts; Bayes methods; Bayesian analysis; Bayesian inference; Brain modeling; Brain-computer interface; Brain-computer interfaces; Electric potential; Electroencephalogram; Electroencephalography; Feature extraction; Human-computer interface; Mathematical analysis; Mathematical models; Segments; Tensile stress; Tensor completion; Tensors
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP.2016.7471789

High accuracy of electroencephalogram (EEG) classification can hardly be achieved if the signals are contaminated by severe artefacts. One helpless way to avoid such artefacts is usually to directly discard the severely disturbed EEG segments. This study considers a more elegant way that tries to recover the disturbed segments from other undisturbed segments. The possible artefacts in EEG are treated as missing values. A Bayesian tensor factorization (BTF) based method is proposed to implement EEG completion for artefact removal. By specifying a sparsity-inducing hierarchical prior, the underlying low-rank tensor is discovered from incomplete EEG tensor with automatically inferred model parameters. The EEG missing values are effectively predicted with robustness to overfitting. Effectiveness of the BTF algorithm is demonstrated on EEG data recorded from seven subjects in a brain-computer interface paradigm based on event-related potentials.