Ensemble approach for detection of depression using EEG features
This work addresses depression detection for mental health applications, but it is incremental as it applies existing methods to a small, specific dataset.
The paper tackled detecting depression from EEG signals by comparing SVM, LDA, NB, kNN, and D3 classifiers using linear and non-linear features, achieving up to 90% accuracy on a dataset of 10 healthy and 10 depressed subjects.
Depression is a public health issue which severely affects one's well being and cause negative social and economic effect for society. To rise awareness of these problems, this publication aims to determine if long lasting effects of depression can be determined from electoencephalographic (EEG) signals. The article contains accuracy comparison for SVM, LDA, NB, kNN and D3 binary classifiers which were trained using linear (relative band powers, APV, SASI) and non-linear (HFD, LZC, DFA) EEG features. The age and gender matched dataset consisted of 10 healthy subjects and 10 subjects with depression diagnosis at some point in their lifetime. Several of the proposed feature selection and classifier combinations reached accuracy of 90% where all models where evaluated using 10-fold cross validation and averaged over 100 repetitions with random sample permutations.