EEG Classification based on Image Configuration in Social Anxiety Disorder
This work addresses a limitedly studied problem in mental health diagnostics for patients with Social Anxiety Disorder, but it is incremental as it builds on existing EEG classification methods.
The paper tackled the problem of detecting Social Anxiety Disorder using EEG data by comparing classification models that ignore versus exploit EEG sensor spatial configuration, finding that the configuration-aware model achieved 6-7% higher accuracy across algorithms.
The problem of detecting the presence of Social Anxiety Disorder (SAD) using Electroencephalography (EEG) for classification has seen limited study and is addressed with a new approach that seeks to exploit the knowledge of EEG sensor spatial configuration. Two classification models, one which ignores the configuration (model 1) and one that exploits it with different interpolation methods (model 2), are studied. Performance of these two models is examined for analyzing 34 EEG data channels each consisting of five frequency bands and further decomposed with a filter bank. The data are collected from 64 subjects consisting of healthy controls and patients with SAD. Validity of our hypothesis that model 2 will significantly outperform model 1 is borne out in the results, with accuracy $6$--$7\%$ higher for model 2 for each machine learning algorithm we investigated. Convolutional Neural Networks (CNN) were found to provide much better performance than SVM and kNNs.