Abstract
Recently, Electroencephalography (EEG) is wildly used in depression detection. Researchers have successfully used machine learning methods to build depression detection models based on EEG signals. However, the scarcity of samples and individual differences in EEG signals limit the generalization performance of machine learning models. This study proposed a synthesis-based data augmentation strategy to improve the diversity of raw EEG signals and train more robust classifiers for depression detection. Firstly, we use the determinantal point processes (DPP) sampling method to investigate the individual differences of the raw EEG signals and generate a more diverse subset of subjects. Then we apply the empirical mode decomposition (EMD) method on the subset and mix the intrinsic mode functions (IMFs) to synthesize augmented EEG signals under the guidance of diversity of subjects. Experimental results show that compared with the traditional signal synthesis methods, the classification accuracy of our method can reach 75% which substantially improve the generalization performance of classifiers for depression detection. And DPP sampling yields relatively higher classification accuracy compared to prevailing approaches.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Sharma, M., Achuth, P., Deb, D., Puthankattil, S.D., Acharya, U.R.: An automated diagnosis of depression using three-channel bandwidth-duration localized wavelet filter bank with EEG signals. Cogn. Syst. Res. 52, 508–520 (2018)
Kessler, R.C., Chiu, W.T., Demler, O., Walters, E.E.: Prevalence, severity, and comorbidity of 12-month dsm-iv disorders in the national comorbidity survey replication. Arch. Gen. Psychiatry 62(6), 617–627 (2005)
Hardeveld, F., et al.: Recurrence of major depressive disorder across different treatment settings: results from the NESDA study. J. Affect. Disord. 147(1–3), 225–231 (2013)
Kreezer, G.: The electro-encephalogram and its use in psychology. Am. J. Psychol. 51(4), 737–759 (1938)
Hosseinifard, B., Moradi, M.H., Rostami, R.: Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal. Comput. Methods Program. Biomed. 109(3), 339–345 (2013)
Acharya, U.R., et al.: A novel depression diagnosis index using nonlinear features in EEG signals. Eur. Neurol. 74(1–2), 79–83 (2015)
Hinrikus, H., et al.: Electroencephalographic spectral asymmetry index for detection of depression. Med. Biol. Eng. Comput. 47(12), 1291–1299 (2009)
Shen, J., Zhang, X., Hu, B., Wang, G., Ding, Z.: An improved empirical mode decomposition of electroencephalogram signals for depression detection. IEEE Trans. Affect. Comput. (2019)
Zhang, X., Shen, J., ud Din, Z., Liu, J., Wang, G., Hu, B.: Multimodal depression detection: fusion of electroencephalography and paralinguistic behaviors using a novel strategy for classifier ensemble. IEEE J. Biomed. Health Inf. 23(6), 2265–2275 (2019)
Ay, B., et al.: Automated depression detection using deep representation and sequence learning with EEG signals. J. Med. Syst. 43(7), 1–12 (2019)
Tian, C., Xu, Y., Zuo, W.: Image denoising using deep CNN with batch renormalization. Neural Netw. 121, 461–473 (2020)
Zhang, X., Li, J., Hou, K., Hu, B., Shen, J., Pan, J.: Eeg-based depression detection using convolutional neural network with demographic attention mechanism. In: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 128–133. IEEE (2020)
Jorm, A.F., et al.: MRI hyperintensities and depressive symptoms in a community sample of individuals 60–64 years old. Am. J. Psychiatry 162(4), 699–705 (2005)
Siegel, M.J., Bradley, E.H., Gallo, W.T., Kasl, S.V.: The effect of spousal mental and physical health on husbands’ and wives’ depressive symptoms, among older adults: longitudinal evidence from the health and retirement survey. J. Aging Health 16(3), 398–425 (2004)
Van Putten, M.J., Olbrich, S., Arns, M.: Predicting sex from brain rhythms with deep learning. Sci. Rep. 8(1), 1–7 (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Paris, A., Atia, G.K., Vosoughi, A., Berman, S.A.: A new statistical model of electroencephalogram noise spectra for real-time brain-computer interfaces. IEEE Trans. Biomed. Eng. 64(8), 1688–1700 (2016)
Lotte, F.: Generating artificial eeg signals to reduce BCI calibration time. In: 5th International Brain-Computer Interface Workshop, pp. 176–179 (2011)
Le Guennec, A., Malinowski, S., Tavenard, R.: Data augmentation for time series classification using convolutional neural networks. In: ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data (2016)
Dinarès-Ferran, J., Ortner, R., Guger, C., Solé-Casals, J.: A new method to generate artificial frames using the empirical mode decomposition for an EEG-based motor imagery BCI. Front. Neurosci. 12, 308 (2018)
Zhang, Z., et al.: A novel deep learning approach with data augmentation to classify motor imagery signals. IEEE Access 7, 15945–15954 (2019)
Sheehan, D.V., et al.: The mini-international neuropsychiatric interview (mini): the development and validation of a structured diagnostic psychiatric interview for dsm-iv and icd-10. J. Clin. Psychiatry 59(20), 22–33 (1998)
Kroenke, K., Spitzer, R.L., Williams, J.B.: The PHQ-9: validity of a brief depression severity measure. J. Gen. Intern. Med. 16(9), 606–613 (2001)
Molla, M.K., Tanaka, T., Rutkowski, T.M., Cichocki, A.: Separation of EOG artifacts from EEG signals using bivariate EMD. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 562–565. IEEE (2010)
Liu, P., Wang, X., Xiang, C., Meng, W.: A survey of text data augmentation. In: 2020 International Conference on Computer Communication and Network Security (CCNS), pp. 191–195. IEEE (2020)
Li, K., Shapiai, M.I., Adam, A., Ibrahim, Z.: Feature scaling for EEG human concentration using particle swarm optimization. In: 2016 8th International Conference on Information Technology and Electrical Engineering (ICITEE), pp. 1–6. IEEE (2016)
Yamauchi, T., Xiao, K., Bowman, C., Mueen, A.: Dynamic time warping: a single dry electrode EEG study in a self-paced learning task. In: 2015 International Conference on Affective Computing and Intelligent Interaction (ACII), pp. 56–62. IEEE (2015)
Flandrin, P., Rilling, G., Goncalves, P.: Empirical mode decomposition as a filter bank. IEEE Sig. Process. Lett. 11(2), 112–114 (2004)
Bajaj, V., Pachori, R.B.: Classification of seizure and nonseizure EEG signals using empirical mode decomposition. IEEE Trans. Inf. Technol. Biomed. 16(6), 1135–1142 (2011)
Acknowledgement
This work was supported in part by National Key R&D Program of China (Grant No. 2019YFA0706200), in part by the National Natural Science Foundation of China (Grant No. 62072219, 61632014), in part by the National Basic Research Program of China (973 Program, Grant No.2014CB744600).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wei, X., Chen, M., Wu, M., Zhang, X., Hu, B. (2021). EEG-Based Depression Detection with a Synthesis-Based Data Augmentation Strategy. In: Wei, Y., Li, M., Skums, P., Cai, Z. (eds) Bioinformatics Research and Applications. ISBRA 2021. Lecture Notes in Computer Science(), vol 13064. Springer, Cham. https://doi.org/10.1007/978-3-030-91415-8_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-91415-8_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91414-1
Online ISBN: 978-3-030-91415-8
eBook Packages: Computer ScienceComputer Science (R0)