Ensemble Approach for Detection of Depression Using EEG Features
Depression is a public health issue that severely affects one’s well being and can cause negative social and economic effects to society. To raise awareness of these problems, this research aims at determining whether the long-lasting effects of depression can be determined from electroencephalograp...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/24/2/211 |
| _version_ | 1827655146742480896 |
|---|---|
| author | Egils Avots Klāvs Jermakovs Maie Bachmann Laura Päeske Cagri Ozcinar Gholamreza Anbarjafari |
| author_facet | Egils Avots Klāvs Jermakovs Maie Bachmann Laura Päeske Cagri Ozcinar Gholamreza Anbarjafari |
| author_sort | Egils Avots |
| collection | DOAJ |
| description | Depression is a public health issue that severely affects one’s well being and can cause negative social and economic effects to society. To raise awareness of these problems, this research aims at determining whether the long-lasting effects of depression can be determined from electroencephalographic (EEG) signals. The article contains an accuracy comparison for SVM, LDA, NB, kNN, and D3 binary classifiers, which were trained using linear (relative band power, alpha power variability, spectral asymmetry index) and nonlinear (Higuchi fractal dimension, Lempel–Ziv complexity, detrended fluctuation analysis) EEG features. The age- and gender-matched dataset consisted of 10 healthy subjects and 10 subjects diagnosed with depression at some point in their lifetime. Most of the proposed feature selection and classifier combinations achieved accuracy in the range of 80% to 95%, and all the models were evaluated using a 10-fold cross-validation. The results showed that the motioned EEG features used in classifying ongoing depression also work for classifying the long-lasting effects of depression. |
| first_indexed | 2024-03-09T22:01:39Z |
| format | Article |
| id | doaj.art-827fe02d5a3b42c2a9bc9b32c303e1ea |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-09T22:01:39Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-827fe02d5a3b42c2a9bc9b32c303e1ea2023-11-23T19:47:46ZengMDPI AGEntropy1099-43002022-01-0124221110.3390/e24020211Ensemble Approach for Detection of Depression Using EEG FeaturesEgils Avots0Klāvs Jermakovs1Maie Bachmann2Laura Päeske3Cagri Ozcinar4Gholamreza Anbarjafari5iCV Lab, Institute of Technology, University of Tartu, 51009 Tartu, EstoniaiCV Lab, Institute of Technology, University of Tartu, 51009 Tartu, EstoniaBiosignal Processing Laboratory, Tallinn University of Technology, 19086 Tallinn, EstoniaBiosignal Processing Laboratory, Tallinn University of Technology, 19086 Tallinn, EstoniaiCV Lab, Institute of Technology, University of Tartu, 51009 Tartu, EstoniaiCV Lab, Institute of Technology, University of Tartu, 51009 Tartu, EstoniaDepression is a public health issue that severely affects one’s well being and can cause negative social and economic effects to society. To raise awareness of these problems, this research aims at determining whether the long-lasting effects of depression can be determined from electroencephalographic (EEG) signals. The article contains an accuracy comparison for SVM, LDA, NB, kNN, and D3 binary classifiers, which were trained using linear (relative band power, alpha power variability, spectral asymmetry index) and nonlinear (Higuchi fractal dimension, Lempel–Ziv complexity, detrended fluctuation analysis) EEG features. The age- and gender-matched dataset consisted of 10 healthy subjects and 10 subjects diagnosed with depression at some point in their lifetime. Most of the proposed feature selection and classifier combinations achieved accuracy in the range of 80% to 95%, and all the models were evaluated using a 10-fold cross-validation. The results showed that the motioned EEG features used in classifying ongoing depression also work for classifying the long-lasting effects of depression.https://www.mdpi.com/1099-4300/24/2/211depressionelectroencephalogram (EEG)feature extraction and selectionmachine learningensemble learning |
| spellingShingle | Egils Avots Klāvs Jermakovs Maie Bachmann Laura Päeske Cagri Ozcinar Gholamreza Anbarjafari Ensemble Approach for Detection of Depression Using EEG Features Entropy depression electroencephalogram (EEG) feature extraction and selection machine learning ensemble learning |
| title | Ensemble Approach for Detection of Depression Using EEG Features |
| title_full | Ensemble Approach for Detection of Depression Using EEG Features |
| title_fullStr | Ensemble Approach for Detection of Depression Using EEG Features |
| title_full_unstemmed | Ensemble Approach for Detection of Depression Using EEG Features |
| title_short | Ensemble Approach for Detection of Depression Using EEG Features |
| title_sort | ensemble approach for detection of depression using eeg features |
| topic | depression electroencephalogram (EEG) feature extraction and selection machine learning ensemble learning |
| url | https://www.mdpi.com/1099-4300/24/2/211 |
| work_keys_str_mv | AT egilsavots ensembleapproachfordetectionofdepressionusingeegfeatures AT klavsjermakovs ensembleapproachfordetectionofdepressionusingeegfeatures AT maiebachmann ensembleapproachfordetectionofdepressionusingeegfeatures AT laurapaeske ensembleapproachfordetectionofdepressionusingeegfeatures AT cagriozcinar ensembleapproachfordetectionofdepressionusingeegfeatures AT gholamrezaanbarjafari ensembleapproachfordetectionofdepressionusingeegfeatures |