A manifold learning approach to mapping individuality of human brain oscillations through beta-divergence

• Published in: Neuroscience research Vol. 156; pp. 188 - 196
• Main Authors: Suetani, Hiromichi, Kitajo, Keiichi
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.07.2020
• Subjects: Algorithms; Brain; EEG; Electroencephalography; Humans; Individuality; Information divergence; Manifold learning; Oscillology; Out-of-sample extension; Individuality; Information divergence; Manifold learning; Oscillology; EEG; Out-of-sample extension
• ISSN: 0168-0102; 1872-8111; 1872-8111
• DOI: 10.1016/j.neures.2020.02.004

•We propose a manifold learning approach for visualizing individuality of human brain oscillations.•To this end, the beta-divergence is employed for measuring the dissimilarities between multi-channel EEG signals.•Resting state EEG signals recorded from 100 healthy subjects were tested for analysis.•We obtained a fine low-dimensional visualization that enables each subject to be identified as an isolated point cloud. This paper proposes an approach for visualizing individuality and inter-individual variations of human brain oscillations measured as multichannel electroencephalographic (EEG) signals in a low-dimensional space based on manifold learning. Using a unified divergence measure between spectral densities termed the “beta-divergence”, we introduce an appropriate dissimilarity measure between multichannel EEG signals. Then, t-distributed stochastic neighbor embedding (t-SNE; a state-of-the-art algorithm for manifold learning) together with the beta-divergence based distance was applied to resting state EEG signals recorded from 100 healthy subjects. We were able to obtain a fine low-dimensional visualization that enabled each subject to be identified as an isolated point cloud and that represented inter-individual variations as the relationships between such point clouds. Furthermore, we also discuss how the performance of the low-dimensional visualization depends on the beta-divergence parameter and the t-SNE hyper parameter. Finally, borrowing from the concept of locally linear embedding (LLE), we propose a method for projecting the test sample to the t-SNE space obtained from the training samples and investigate that availability.