Application of identity vectors for EEG classification

• Published in: Journal of neuroscience methods Vol. 311; pp. 338 - 350
• Main Authors: Ward, Christian, Obeid, Iyad
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.01.2019
• Subjects: Brain - physiology; Brain Waves; Data Interpretation, Statistical; Electroencephalogram; Electroencephalography; Humans; I-Vector; Pattern Recognition, Automated - methods; Signal Processing, Computer-Assisted; Subject Verification; Universal Background Model; Unsupervised Learning; Unsupervised Machine Learning; Subject Verification; I-Vector; Universal Background Model; Unsupervised Learning; Electroencephalogram
• ISSN: 0165-0270; 1872-678X; 1872-678X
• DOI: 10.1016/j.jneumeth.2018.09.015

•We show how to perform subject verification of EEGs using I-Vectors.•Three feature sets are tested over two data sets by three algorithms.•I-Vector performance meets or exceeds that of Mahalanobis and GMM classifiers.•I-Vector classification is steady for feature sets, datasets, and epochs. Finding an optimal EEG subject verification algorithm is a long standing goal within the EEG community. For every advancement made, another feature set, classifier, or dataset is often introduced; tracking improvements in classification without a consistent benchmark, such as a classifier-feature pairing tested on a publicly available dataset, makes it difficult to understand how and why these improvements occur. Following on previous biometric experiments, I-Vectors and Gaussian Mixture Model-Universal Background Models are compared to an established Mahalanobis classifier. A second experiment then addresses the impact of epoch duration as a function of classification performance across all three classifiers. The experimental classification results indicate that I-Vectors are more robust than the other classifiers displaying less sensitivity to epoch duration, data composition, and feature selection. This I-Vector based approach is compared against commonly used EEG classifiers, such as Mahalanobis and Gaussian mixture models. These classifiers are benchmarked using the publicly available PhysioNet database converted into three feature sets, spectral coherence, power spectral density, and cepstral coefficients. The experimental results suggests I-Vectors provide reliable baseline performance by leveling the field between feature set and datasets making them well suited for EEG signal processing tasks.