Version 1
: Received: 19 June 2021 / Approved: 21 June 2021 / Online: 21 June 2021 (11:39:31 CEST)
Version 2
: Received: 29 June 2021 / Approved: 6 July 2021 / Online: 6 July 2021 (12:42:59 CEST)
How to cite:
Prakash, B.; Kumar Baboo, G.; Baths, V. A Novel Approach to Learning Models on EEG Data Using Graph Theory Features - A Comparative Study. Preprints2021, 2021060509. https://doi.org/10.20944/preprints202106.0509.v2
Prakash, B.; Kumar Baboo, G.; Baths, V. A Novel Approach to Learning Models on EEG Data Using Graph Theory Features - A Comparative Study. Preprints 2021, 2021060509. https://doi.org/10.20944/preprints202106.0509.v2
Prakash, B.; Kumar Baboo, G.; Baths, V. A Novel Approach to Learning Models on EEG Data Using Graph Theory Features - A Comparative Study. Preprints2021, 2021060509. https://doi.org/10.20944/preprints202106.0509.v2
APA Style
Prakash, B., Kumar Baboo, G., & Baths, V. (2021). A Novel Approach to Learning Models on EEG Data Using Graph Theory Features - A Comparative Study. Preprints. https://doi.org/10.20944/preprints202106.0509.v2
Chicago/Turabian Style
Prakash, B., Gautam Kumar Baboo and Veeky Baths. 2021 "A Novel Approach to Learning Models on EEG Data Using Graph Theory Features - A Comparative Study" Preprints. https://doi.org/10.20944/preprints202106.0509.v2
Abstract
Functional Connectivity analysis using Electroencephalography signals is common. The EEG signals are converted to networks by transforming the signals into a correlation matrix and analyzing the resulting networks. Here, four learning models, namely, Logistic Regression, Random Forest, Support Vector Machine, and Recurrent Neural Networks, are implemented on the correlation matrix data to classify them either on their psychometric assessment or the effect of therapy; The EEG data is trail-based/event-related. The classifications based on RNN provided higher accuracy( 74-88%) than the other three models( 50-78%). Instead of using individual graph features, a correlation matrix provides an initial test of the data. When compared with the time-resolved correlation matrix, it offered a 4-5% higher accuracy. The time-resolved correlation matrix is better suited for dynamic studies here; it provides lower accuracy when compared to the correlation matrix, a static feature.
Computer Science and Mathematics, Signal Processing
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Commenter: Bhargav Prakash
Commenter's Conflict of Interests: Author
Made minor changes in abstract and the main text.