A Hybrid Meta-Learning Model in Depression Classification of EEG

DOI

10.2991/978-94-6239-616-6_60How to use a DOI?

Keywords

Depression detection; EEG signals; machine learning; ANN; random forest; decision tree; biomarkers; offline system; early diagnosis; mental health

Abstract

Depression is one of the most widespread mental wellbeing problems, which, being untreated, may lead to severe social, psychological and actual working issues. The most important aspect of DAC is early diagnosis, through which appropriate medical care, treatment, and planning is achieved. This paper introduces an offline machine learning-based depression detector using electroencephalogram (EEG) brainwave signals that were recorded in advance. The developed framework, unlike the traditional methods, where it is necessary to invoke the living user to provide a stimulus at the time of prediction (as in case of the BCI paradigms) analyzed previously obtained EEG data and, therefore, could predict them repeatably and effectively under clinical and research conditions. Using this system, researchers managed to identify key patterns and biomarkers in the brain in relation to a depressed state. Decision trees and artificial neural networks (ANNs) were trained and learned as some of the machine learning models to demonstrate strong classification results and to enhance the accuracy of the prediction. The findings indicated that the system could differentiate between depressed and non-depressed subjects with high accuracy which is an advantage to psychometric test as well as offering an objective and data-driven tool to complement a traditional psychiatrist diagnostic work. This structure can help the doctors diagnose depression earlier, which results in faster treatment interventions and favorable prognoses of the patient through accurate predictions in an offline fashion.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - M. Prathmesh
AU  - A. Nithis Kanna
AU  - K. Suruthika
PY  - 2026
DA  - 2026/03/31
TI  - A Hybrid Meta-Learning Model in Depression Classification of EEG
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 799
EP  - 811
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_60
DO  - 10.2991/978-94-6239-616-6_60
ID  - Prathmesh2026
ER  -