Multi-Class Anxiety Classification using Error-related EEG Signals and Deep Learning Models
Access Status
Open access
Date
2024Supervisor
Tom Gedeon
Md Zakir Hossain
Type
Thesis
Award
MPhil
Metadata
Show full item recordFaculty
Science and Engineering
School
School of Electrical Engineering, Computing and Mathematical Sciences
Collection
Abstract
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.
Related items
Showing items related by title, author, creator and subject.
-
Commons, D.; Greenwood, K.; Anderson, Rebecca (2015)Background: Worry about physical health is broadly referred to as health anxiety and can range from mild concern to severe or persistent anxiety such as that found in DSM-IV hypochondriasis. While much is known about ...
-
McEvoy, Peter; Grove, R.; Slade, T. (2011)Objective: The aims of this study were to report 12-month and lifetime prevalence for anxiety disorders in the Australian general population, identify sociodemographic and clinical correlates of anxiety disorders, and ...
-
Soares, S.; Boyes, Mark ; Parrila, R.; Badcock, N.A. (2023)Poor readers have lower academic achievement and increased anxiety, including reading anxiety, which may perpetuate lower academic achievement. We explored reading anxiety in university students, investigating whether the ...