Depression is a severe neurological disorder characterized by a loss of interest and may lead to suicide. Electroencephalography (EEG) measurement is a non-invasive tool for neural electrical activities measurement which can be further used for different neurological disorder detection such as depression. The number of EEG electrodes used for measurement directly affects the instrumentation and measurement complexity of the experiment. This paper proposes a fisher score–based method for electrode ranking. This paper selects only those electrodes whose fisher score is greater than the mean of fisher scores of all electrodes. It results in a reduced set of electrodes. A deep learning–based model has been proposed which uses the reduced set of electrodes for depression detection. The performance of the proposed model is evaluated on two benchmark data sets having varying numbers of electrodes. The proposed model significantly reduces the number of electrodes to 68.42% and 60.93% for data sets 1 and 2, respectively. The accuracy of 98.73%, precision of 98.50%, recall of 98.75%, F1 score of 98.62% and AUC of 99.91% are obtained for data set 1 and accuracy of 95.48%, precision of 91.93%, recall of 96.11%, F1 score of 93.97% and AUC of 99.49% are obtained for data set 2.
AfiaAGougamFRahmouneC, et al. (2024) Intelligent fault classification of air compressors using Harris Hawks optimization and machine learning algorithms. Transactions of the Institute of Measurement and Control46: 359–378.
2.
AfzaliAKhaleghiAHatefB, et al. (2023) Automated major depressive disorder diagnosis using a dual-input deep learning model and image generation from EEG signals. Waves in Random and Complex Media. Epub ahead of print March. DOI: 10.1080/17455030.2023.2187237.
3.
Al-QazzazNKSabirMKAliS, et al. (2019) Effective EEG channels for emotion identification over the brain regions using differential evolution algorithm. In: 2019 41st annual international conference of the IEEE engineering in medicine and biology society (EMBC), Berlin, 23–27 July, pp. 4703–4706. New York: IEEE.
4.
ArvanehMGuanCAngKK, et al. (2011) Optimizing the channel selection and classification accuracy in EEG-based BCI. IEEE Transactions on Biomedical Engineering58(6): 1865–1873.
5.
AydemirETuncerTDoganS, et al. (2021) Automated major depressive disorder detection using melamine pattern with EEG signals. Applied Intelligence51(9): 6449–6466.
6.
BavkarSIyerBDeosarkarS (2019) Rapid screening of alcoholism: An EEG based optimal channel selection approach. IEEE Access7: 99670–99682.
7.
BhartiKKSinghPK (2015) Hybrid dimension reduction by integrating feature selection with feature extraction method for text clustering. Expert Systems with Applications42(6): 3105–3114.
8.
ChaddadALuQLiJ, et al. (2023) Explainable, domain-adaptive, and federated artificial intelligence in medicine. IEEE/CAA Journal of Automatica Sinica10(4): 859–876.
9.
ChenYHuXXiaL (2023a) A local-global graph convolutional network for depression recognition using EEG signals. International Journal of Advanced Computer Science and Applications14(7): 182–192.
10.
ChenYWangSGuoJ (2023b) DCTNet: Hybrid deep neural network-based EEG signal for detecting depression. Multimedia Tools and Applications82: 41307–41321.
11.
CukicMPokrajacDStokicM, et al. (2018) EEG machine learning with Higuchi fractal dimension and Sample Entropy as features for successful detection of depression. arXiv preprint arXiv:1803.05985.
12.
El-HageenHMAlatwiAMRashedAZ (2021) Spatial optical transmitter based on on/off keying line coding modulation scheme for optimum performance of telecommunication systems. Indonesian Journal of Electrical Engineering and Computer Science21: 305–312.
13.
GaurPMcCreadieKPachoriRB, et al. (2021) An automatic subject specific channel selection method for enhancing motor imagery classification in EEG-BCI using correlation. Biomedical Signal Processing and Control68: 102574.
14.
HeLHuYLiY, et al. (2013) Channel selection by Rayleigh coefficient maximization based genetic algorithm for classifying single-trial motor imagery EEG. Neurocomputing121: 423–433.
15.
IdowuOPAdelopoOIlesanmiAE, et al. (2021) Neuro-evolutionary approach for optimal selection of EEG channels in motor imagery based BCI application. Biomedical Signal Processing and Control68: 102621.
16.
KourHGuptaMK (2022) An hybrid deep learning approach for depression prediction from user tweets using feature-rich CNN and bi-directional LSTM. Multimedia Tools and Applications81(17): 23649–23685.
17.
Kumar SinghKKumarSAntonakakisM, et al. (2022) Deep learning capabilities for the categorization of microcalcification. International Journal of Environmental Research and Public Health19(4): 2159.
18.
LiXLaRWangY, et al. (2019) EEG-based mild depression recognition using convolutional neural network. Medical & Biological Engineering & Computing57(6): 1341–1352.
19.
LinLChenXShenY, et al. (2020) Towards automatic depression detection: A BiLSTM/1D CNN-based model. Applied Sciences10(23): 8701.
20.
LiuCFuYYangJ, et al. (2016) Discrimination of motor imagery patterns by electroencephalogram phase synchronization combined with frequency band energy. IEEE/CAA Journal of Automatica Sinica4(3): 551–557.
21.
LohHWOoiCPAydemirE, et al. (2022) Decision support system for major depression detection using spectrogram and convolution neural network with EEG signals. Expert Systems39(3): e12773.
22.
MaYChengJWangP, et al. (2021) Rotating machinery fault diagnosis based on multivariate multiscale fuzzy distribution entropy and fisher score. Measurement179: 109495.
23.
MahatoSPaulS (2019) Detection of major depressive disorder using linear and non-linear features from EEG signals. Microsystem Technologies25(3): 1065–1076.
24.
MandrekarJN (2010) Receiver operating characteristic curve in diagnostic test assessment. Journal of Thoracic Oncology5(9): 1315–1316.
25.
MohammadiYMoradiMH (2021) Prediction of depression severity scores based on functional connectivity and complexity of the EEG signal. Clinical EEG and Neuroscience52(1): 52–60.
26.
MumtazWXiaLMohd YasinMA, et al. (2017) A wavelet-based technique to predict treatment outcome for major depressive disorder. PLoS ONE12(2): e0171409.
27.
ParkYChungW (2020) Optimal channel selection using correlation coefficient for CSP based EEG classification. IEEE Access8: 111514–111521.
28.
PengHWangYChaoJ, et al. (2017) Stability study of the optimal channel selection for emotion classification from EEG. In: 2017 IEEE international conference on bioinformatics and biomedicine (BIBM), Kansas City, MO, 13–16 November, pp. 2031–2036. New York: IEEE.
QiFWuWYuZL, et al. (2020) Spatiotemporal-filtering-based channel selection for single-trial EEG classification. IEEE Transactions on Cybernetics51(2): 558–567.
31.
RafieiAZahedifarRSitaulaC, et al. (2022) Automated detection of major depressive disorder with EEG signals: A time series classification using deep learning. IEEE Access10: 73804–73817.
32.
SaeediASaeediMMaghsoudiA, et al. (2021) Major depressive disorder diagnosis based on effective connectivity in EEG signals: A convolutional neural network and long short-term memory approach. Cognitive Neurodynamics15(2): 239–252.
33.
SaeediMSaeediAMaghsoudiA (2020) Major depressive disorder assessment via enhanced k-nearest neighbor method and EEG signals. Physical and Engineering Sciences in Medicine43: 1007–1018.
34.
ShenJZhangXHuangX, et al. (2020) An optimal channel selection for EEG-based depression detection via kernel-target alignment. IEEE Journal of Biomedical and Health Informatics25(7): 2545–2556.
35.
SunLZhangJDingW, et al. (2022) Mixed measure-based feature selection using the Fisher score and neighborhood rough sets. Applied Intelligence52: 17264–17288.
36.
ThoduparambilPPDominicAVargheseSM (2020) EEG-based deep learning model for the automatic detection of clinical depression. Physical and Engineering Sciences in Medicine43: 1349–1360.
37.
UyulanCErgüzelTTUnubolH, et al. (2021) Major depressive disorder classification based on different convolutional neural network models: Deep learning approach. Clinical EEG and Neuroscience52(1): 38–51.
38.
WangZMHuSYSongH (2019) Channel selection method for EEG emotion recognition using normalized mutual information. IEEE Access7: 143303–143311.
39.
WHO (2023) Institute of Health Metrics and Evaluation. Global Health Data Exchange (GHDx). Available at: https://vizhub.healthdata.org/gbd-results/ (accessed 4 March 2023).
40.
XiaMZhangYWuY, et al. (2023) An end-to-end deep learning model for EEG-based major depressive disorder classification. IEEE Access11: 41337–41347.
41.
XieWWangCLinZ, et al. (2022) Multimodal fusion diagnosis of depression and anxiety based on CNN-LSTM model. Computerized Medical Imaging and Graphics102: 102128.
42.
ZhangJWuYBaiJ, et al. (2016) Automatic sleep stage classification based on sparse deep belief net and combination of multiple classifiers. Transactions of the Institute of Measurement and Control38(4): 435–451.
43.
ZhangYWangKWeiY, et al. (2022) Minimal EEG channel selection for depression detection with connectivity features during sleep. Computers in Biology and Medicine147: 105690.
44.
ZhangZMengQJinL, et al. (2024) A novel EEG-based graph convolution network for depression detection: Incorporating secondary subject partitioning and attention mechanism. Expert Systems with Applications239: 122356.
