KCS-FCnet: Kernel Cross-Spectral Functional Connectivity Network for EEG-Based Motor Imagery Classification

García-Murillo, Daniel Guillermo; Álvarez-Meza, Andrés Marino; Castellanos-Dominguez, Cesar German

doi:10.3390/diagnostics13061122

Open AccessArticle

KCS-FCnet: Kernel Cross-Spectral Functional Connectivity Network for EEG-Based Motor Imagery Classification

by

Daniel Guillermo García-Murillo

^*,†,

Andrés Marino Álvarez-Meza

^†

and

Cesar German Castellanos-Dominguez

^†

Signal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170003, Colombia

^*

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Diagnostics 2023, 13(6), 1122; https://doi.org/10.3390/diagnostics13061122

Submission received: 28 January 2023 / Revised: 25 February 2023 / Accepted: 2 March 2023 / Published: 16 March 2023

(This article belongs to the Special Issue Artificial Intelligence and Pattern Recognition Methods for the Automatic Detection and Evaluation of Neurological Disorders)

Download

Browse Figures

Review Reports Versions Notes

Abstract

This paper uses EEG data to introduce an approach for classifying right and left-hand classes in Motor Imagery (MI) tasks. The Kernel Cross-Spectral Functional Connectivity Network (KCS-FCnet) method addresses these limitations by providing richer spatial-temporal-spectral feature maps, a simpler architecture, and a more interpretable approach for EEG-driven MI discrimination. In particular, KCS-FCnet uses a single 1D-convolutional-based neural network to extract temporal-frequency features from raw EEG data and a cross-spectral Gaussian kernel connectivity layer to model channel functional relationships. As a result, the functional connectivity feature map reduces the number of parameters, improving interpretability by extracting meaningful patterns related to MI tasks. These patterns can be adapted to the subject’s unique characteristics. The validation results prove that introducing KCS-FCnet shallow architecture is a promising approach for EEG-based MI classification with the potential for real-world use in brain–computer interface systems.

Keywords: functional connectivity; kernel methods; motor imagery; EEG; cross-spectral distribution; deep learning

Share and Cite

MDPI and ACS Style

García-Murillo, D.G.; Álvarez-Meza, A.M.; Castellanos-Dominguez, C.G. KCS-FCnet: Kernel Cross-Spectral Functional Connectivity Network for EEG-Based Motor Imagery Classification. Diagnostics 2023, 13, 1122. https://doi.org/10.3390/diagnostics13061122

AMA Style

García-Murillo DG, Álvarez-Meza AM, Castellanos-Dominguez CG. KCS-FCnet: Kernel Cross-Spectral Functional Connectivity Network for EEG-Based Motor Imagery Classification. Diagnostics. 2023; 13(6):1122. https://doi.org/10.3390/diagnostics13061122

Chicago/Turabian Style

García-Murillo, Daniel Guillermo, Andrés Marino Álvarez-Meza, and Cesar German Castellanos-Dominguez. 2023. "KCS-FCnet: Kernel Cross-Spectral Functional Connectivity Network for EEG-Based Motor Imagery Classification" Diagnostics 13, no. 6: 1122. https://doi.org/10.3390/diagnostics13061122

APA Style

García-Murillo, D. G., Álvarez-Meza, A. M., & Castellanos-Dominguez, C. G. (2023). KCS-FCnet: Kernel Cross-Spectral Functional Connectivity Network for EEG-Based Motor Imagery Classification. Diagnostics, 13(6), 1122. https://doi.org/10.3390/diagnostics13061122

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

KCS-FCnet: Kernel Cross-Spectral Functional Connectivity Network for EEG-Based Motor Imagery Classification

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI