Multi-Class Anxiety Classification using Error-related EEG Signals and Deep Learning Models

Anxiety disorders impact mental and physical health globally. This study classifies anxiety severity levels using Error-Related Negativity (ERN) signals from EEG data, analyzing 163 participants during a go/no-go task. Employing RNN, LSTM, and GRU models, anxiety was categorized as mild, moderate, o...

Full description

Bibliographic Details
Main Author: Chandrasekar, Ramya
Format: Thesis
Published: Curtin University 2024
Online Access:http://hdl.handle.net/20.500.11937/98033
_version_ 1848766352541614080
author Chandrasekar, Ramya
author_facet Chandrasekar, Ramya
author_sort Chandrasekar, Ramya
building Curtin Institutional Repository
collection Online Access
description Anxiety disorders impact mental and physical health globally. This study classifies anxiety severity levels using Error-Related Negativity (ERN) signals from EEG data, analyzing 163 participants during a go/no-go task. Employing RNN, LSTM, and GRU models, anxiety was categorized as mild, moderate, or severe. GRU achieved 97.6% accuracy under 10-fold cross-validation. Advanced pre-processing and feature extraction ensured robustness. This method outperforms existing techniques, offering a precise, automated approach to anxiety diagnosis using deep learning and EEG analysis.
first_indexed 2025-11-14T11:49:47Z
format Thesis
id curtin-20.500.11937-98033
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:49:47Z
publishDate 2024
publisher Curtin University
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-980332025-07-04T06:09:25Z Multi-Class Anxiety Classification using Error-related EEG Signals and Deep Learning Models Chandrasekar, Ramya Anxiety disorders impact mental and physical health globally. This study classifies anxiety severity levels using Error-Related Negativity (ERN) signals from EEG data, analyzing 163 participants during a go/no-go task. Employing RNN, LSTM, and GRU models, anxiety was categorized as mild, moderate, or severe. GRU achieved 97.6% accuracy under 10-fold cross-validation. Advanced pre-processing and feature extraction ensured robustness. This method outperforms existing techniques, offering a precise, automated approach to anxiety diagnosis using deep learning and EEG analysis. 2024 Thesis http://hdl.handle.net/20.500.11937/98033 Curtin University fulltext
spellingShingle Chandrasekar, Ramya
Multi-Class Anxiety Classification using Error-related EEG Signals and Deep Learning Models
title Multi-Class Anxiety Classification using Error-related EEG Signals and Deep Learning Models
title_full Multi-Class Anxiety Classification using Error-related EEG Signals and Deep Learning Models
title_fullStr Multi-Class Anxiety Classification using Error-related EEG Signals and Deep Learning Models
title_full_unstemmed Multi-Class Anxiety Classification using Error-related EEG Signals and Deep Learning Models
title_short Multi-Class Anxiety Classification using Error-related EEG Signals and Deep Learning Models
title_sort multi-class anxiety classification using error-related eeg signals and deep learning models
url http://hdl.handle.net/20.500.11937/98033