Advanced Time Series Analysis of EEG Signals for Major Depressive Disorder Detection through an Attention Augmented Residual Convolutional Neural Network
Keywords:
Attention Augmented Residual Convolutional Neural Network, EEG Psychiatric Disorders Dataset, Regularized bias-aware ensemble Kalman filter, Lotus Effect Optimization Algorithm, Major Depressive DisorderAbstract
The Major Depressive Disorder (MDD) has been regarded as a serious and prevalent illness that affects functional frailty, but its precise symptoms are unknown. Manually detecting MDD is therefore a difficult and individualised task. Electroencephalography signals have demonstrated promise in supporting diagnosis; nevertheless, more development is needed to increase precision, clinical usefulness, and effectiveness. In this paper, Advanced Time Series Analysis of EEG Signals for Major Depressive Disorder Detection through an Attention Augmented Residual Convolutional Neural Network (TSA-EEGS-MDDD-AARCNN)is proposed. Initially, the signals are collected from EEG Psychiatric Disorders Dataset. Then, the input signals are fed into preprocessing stage. In pre-processing, Regularized Bias-Aware Ensemble Kalman Filter (RBAEKF) is used to remove the noise and artifacts in electroencephalography signal. After that, the pre-processed data are given into Attention Augmented Residual Convolutional Neural Network (AARCNN) for Major Depressive Disorder Detection as normal and Major Depressive Disorder. After that a channel-selection strategy, consisting of three steps, is applied to eliminate redundant channels utilizing Lotus Effect Optimization Approach (LEOA).Then effectiveness of the proposed approach is compared with other existing approaches. The proposed technique attains 16.28%, 30.78% and 25.29% higher accuracy and 19.45%, 20.22% and 22.28% higher precision comparing with existing techniques such as an automated detection of most depressive diseases with electroencephalography signals: a time series categorization utilizing DL (AD-MDD-EEGS-DL), Decision Support Scheme For Most Depression Detection Utilizing Spectrogram and CNN with electroencephalography signals (DSS-MDD-CNN-EEGS) and End-To-End DL Method for Electroencephalography -derived major depressive disorder categorization (ETE-DL-EEG-MDDC) respectively
Downloads
Metrics
References
Cui, W., Sun, M., Dong, Q., Guo, Y., Liao, X.F. and Li, Y., 2023. A multiview sparse dynamic graph convolution-based region-attention feature fusion network for major depressive disorder detection.IEEE Transactions on Computational Social Systems.
Zhang, B., Wei, D., Yan, G., Li, X., Su, Y. and Cai, H., 2023. Spatial–temporal eeg fusion based on neural network for major depressive disorder detection. Interdisciplinary Sciences: Computational Life Sciences, 15(4), pp.542-559.
Price, G.D., Heinz, M.V., Collins, A.C. and Jacobson, N.C., 2024. Detecting major depressive disorder presence using passively-collected wearable movement data in a nationally-representative sample.Psychiatry research, 332, p.115693.
Sharma, G., Joshi, A.M., Gupta, R. and Cenkeramaddi, L.R., 2023. DepCap: a smart healthcare framework for EEG based depression detection using time-frequency response and deep neural network. IEEE Access, 11, pp.52327-52338.
Ravan, M., Noroozi, A., Sanchez, M.M., Borden, L., Alam, N., Flor-Henry, P. and Hasey, G., 2023. Discriminating between bipolar and major depressive disorder using a machine learning approach and resting-state EEG data.Clinical Neurophysiology, 146, pp.30-39.
Rafiei, A., Zahedifar, R., Sitaula, C. and Marzbanrad, F., 2022. Automated detection of major depressive disorder with EEG signals: a time series classification using deep learning. IEEE Access, 10, pp.73804-73817.
Loh, H.W., Ooi, C.P., Aydemir, E., Tuncer, T., Dogan, S. and Acharya, U.R., 2022. Decision support system for major depression detection using spectrogram and convolution neural network with EEG signals. Expert Systems, 39(3), p.e12773.
Xia, M., Zhang, Y., Wu, Y. and Wang, X., 2023. An end-to-end deep learning model for EEG-based major depressive disorder classification.IEEE Access, 11, pp.41337-41347.
Khadidos, A.O., Alyoubi, K.H., Mahato, S., Khadidos, A.O. and Mohanty, S.N., 2023. Computer aided detection of major depressive disorder (MDD) using electroencephalogram signals. IEEE Access, 11, pp.41133-41141.
Bashir, N., Narejo, S., Naz, B., Ismail, F., Anjum, M.R., Butt, A., Anwar, S. and Prasad, R., 2023. A machine learning framework for Major depressive disorder (MDD) detection using non-invasive EEG signals. Wireless Personal Communications, pp.1-23.
https://www.kaggle.com/datasets/shashwatwork/eeg-psychiatric-disorders-dataset
Nóvoa, A., Racca, A. and Magri, L., 2024. Inferring unknown unknowns: regularized bias-aware ensemble Kalman filter. Computer Methods in Applied Mechanics and Engineering, 418, p.116502.
Zhang, B., Sifaou, H. and Li, G.Y., 2023. Csi-fingerprinting indoor localization via attention-augmented residual convolutional neural network.IEEE Transactions on Wireless Communications, 22(8), pp.5583-5597.
Dalirinia, E., Jalali, M., Yaghoobi, M. and Tabatabaee, H., 2024. Lotus effect optimization algorithm (LEA): a lotus nature-inspired algorithm for engineering design optimization. The Journal of Supercomputing, 80(1), pp.761-799.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
