The Impact of Enriching Electroencephalogram in Spatial Metadata on Interpretability and Generalization Ability of Graph Neural Networks

• Published in: Pattern recognition and image analysis Vol. 34; no. 4; pp. 1255 - 1263
• Main Authors: Sidorov, L. S., Maysuradze, A. I.
• Format: Journal Article
• Language: English
• Published: Moscow Pleiades Publishing 01.12.2024; Springer Nature B.V
• Subjects: Computer Science; Electroencephalography; Emotion recognition; Graph neural networks; Image Processing and Computer Vision; Pattern Recognition; PRIA JOURNAL SPECIAL ISSUE 21ST ALL-RUSSIAN CONFERENCE WITH INTERNATIONAL PARTICIPATION “MATHEMATICAL METHODS OF PATTERN RECOGNITION” (MMPR-2023); Recording; Section Papers—Applications in Medicine and Biometry; Time series; spatial data; deep learning; multimodal data integration; multivariate time series; P300 wave; graph neural network; emotion recognition; electroencephalogram
• ISSN: 1054-6618; 1555-6212
• DOI: 10.1134/S1054661824701323

This paper proposes a formalization of current approaches to processing electroencephalograms, as well as a generalization of the original problem of processing multidimensional time series in terms of graph neural networks. The proposed architecture exploits information about the recording device by encoding information about the relative position of the recording electrodes as a graph. The effectiveness of the method has been demonstrated in tasks of emotion recognition, as well as P300 impulse recognition. The model achieved outstanding results on the considered datasets using the same set of hyperparameters. The experiments conducted demonstrate the usefulness of graphs composed of metainformation, as well as the dependence of the structure of the optimal graph on the problem being solved. Potentially, this technique can be extended to other subject areas where additional information about the connectivity of multivariate time series channels is available.