Volume 9, Issue 3 (volume9, Issue 3 2021)                   CPJ 2021, 9(3): 54-69 | Back to browse issues page

XML Persian Abstract Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Daneshmand-Bahman F, Goshvarpour A. Classification of EEG Signals in Two Levels of Normal and Anxious Using Nonlinear Features. CPJ 2021; 9 (3) :54-69
URL: http://jcp.khu.ac.ir/article-1-3437-en.html
Department of Biomedical Engineering, Imam Reza International University, Mashhad, Razavi Khorasan, Iran. , ateke.goshvarpour@gmail.com
Abstract:   (4357 Views)
Anxiety is a natural reaction of humans to stress that occurs in the face of various factors. Anxiety is considered as a mental illness if it is excessive and uncontrollable in the form of fear and anxiety. Today, clinicians use certain criteria to diagnose anxiety disorders. This analytical-observational study was aimed at automatically classifying the two levels of anxious and normal by analyzing electroencephalogram signals. In this paper, the DASPS database was used, which contains a 14-channel electroencephalogram of 23 people (13 females and 10 males, mean age 30 years) during anxiety. Anxiety was presented in the form of flooding as actual exposure to the feared stimulus. Based on the results of the Self-Assessment Manikin, data were divided into two groups: (1) normal and low anxiety and (2) moderate and high anxiety. Approximate entropy, fractal dimension, and Lyapunov exponents were extracted from all channels as nonlinear properties. Maximum relevance and minimum redundancy were used to select the best feature to apply to the multilayer perceptron network. To evaluate the performance of the algorithm, different network structures were examined in terms of the number of features and neurons as well as different feature dimensions. Maximum accuracy, precision, f1-score, and sensitivity in 20 repetitions in all cases is equal to 100, and with an increasing number of neurons, the average accuracy increases. The best results were obtained for 5 features and 15 neurons, where the mean accuracy, precision, f1-score, and sensitivity for it were 80%, 92.75%, 84.15%, and 80.58%, respectively. The results of this paper indicated the capability of the proposed algorithm to distinguish anxious people from normal ones.
Full-Text [PDF 1505 kb]   (915 Downloads)    
Type of Study: Research | Subject: Medical Engineering - Bioelectric
Received: 2021/06/3 | Accepted: 2021/09/29 | Published: 2021/10/2

1. Abiodun, O. I., Jantan, A., Omolara, A. E., Dada, K. V., Mohamed, N. A., & Arshad, H. (2018). State-of-the-art in artificial neural network applications: A survey. Heliyon, 4(11), e00938. doi:10.1016/j.heliyon.2018.e00938 [DOI:10.1016/j.heliyon.2018.e00938]
2. Awrejcewicz, J., Krysko, A. V., Erofeev, N. P., Dobriyan, V., Barulina, M. A., & Krysko, V. A. (2018). Quantifying chaos by various computational methods. Part 1: simple [DOI:10.20944/preprints201801.0154.v1]
3. systems. Entropy, 20(3), 175. doi:10.3390/e20030175 [DOI:10.3390/e20030175]
4. Baghdadi, A., Aribi, Y., Fourati, R., Halouani, N., Siarry, P., & Alimi, A. M. (2019). DASPS: A Database for Anxious States based on a Psychological Stimulation. arXiv preprint arXiv:1901.02942.
5. Cervantes-De la Torre, F., González-Trejo, J. I., Real-Ramirez, C. A., & Hoyos-Reyes, L. F. (2013). Fractal dimension algorithms and their application to time series associated with natural phenomena. In Journal of Physics: Conference Series (Vol. 475, No. 1, p. 012002). IOP Publishing. doi:10.1088/1742-6596/475/1/012002 [DOI:10.1088/1742-6596/475/1/012002]
6. Chicco, D., & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC genomics, 21(1), 1-13. doi:10.1186/s12864-019-6413-7 [DOI:10.1186/s12864-019-6413-7]
7. Darzi, M., Ulfatbakhsh, A., Gorgin, S., Oveisi, F., Hashemi, E. A., … & Alavi, N. A. (2016). Classification of unbalanced data in the initial diagnosis of breast diseases by methods of adabost, probabilistic neural network and K to the nearest neighbor. Iranian Journal of Breast Diseases, 9 (2), 7-18.
8. Delgado-Bonal, A., & Marshak, A. (2019). Approximate entropy and sample entropy: A comprehensive tutorial. Entropy, 21(6), 541. doi:10.3390/e21060541 [DOI:10.3390/e21060541]
9. De Pascalis, V., Vecchio, A., & Cirillo, G. (2020). Resting anxiety increases EEG delta-beta correlation: Relationships with the Reinforcement Sensitivity Theory Personality traits. Personality and Individual Differences, 156, 109796. doi:10.1016/j.paid.2019.109796 [DOI:10.1016/j.paid.2019.109796]
10. Giannakakis, G., Grigoriadis, D., & Tsiknakis, M. (2015). Detection of stress/anxiety state
11. from EEG features during video watching. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 6034-6037).IEEE. doi:10.1109/EMBC.2015.7319767 [DOI:10.1109/EMBC.2015.7319767]
12. Jiao, Y., & Du, P. (2016). Performance measures in evaluating machine learning based bioinformatics predictors for classifications. Quantitative Biology, 4(4), 320-330. doi :10.1007/s40484-016-0081-2 [DOI:10.1007/s40484-016-0081-2]
13. Katz, M. J. (1988). Fractals and the analysis of waveforms. Computers in biology and medicine, 18(3), 145-156. doi: 10.1016/0010-4825(88)90041-8 [DOI:10.1016/0010-4825(88)90041-8]
14. Klados, M. A., Pandria, N., Athanasiou, A., & Bamidis, P. D. (2017). An automatic EEG based system for the recognition of math anxiety. In 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS) (pp. 409-412). IEEE. doi:10.1109/CBMS.2017.107 [DOI:10.1109/CBMS.2017.107]
15. Li, J., Ran, H., & Zhao, J. (2019). Relationship Between Multiple Temporal Features of Resting EEG and the Anxiety State of Normal Subjects. In 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) (pp. 1-6). IEEE. doi:10.1109/CISP-BMEI48845.2019.8965982 [DOI:10.1109/CISP-BMEI48845.2019.8965982]
16. Liu, J., Li, J., Peng, W., Feng, M., & Luo, Y. (2019). EEG correlates of math anxiety during arithmetic problem solving: Implication for attention deficits. Neuroscience letters, 703, 191-197. doi:10.1016/j.neulet.2019.03.047 [DOI:10.1016/j.neulet.2019.03.047]
17. Mohammadi, M. R., Khaleghi, A., Nasrabadi, A. M., Rafieivand, S., Begol, M., & Zarafshan, H. (2016). EEG classification of ADHD and normal children using non
18. linear features and neural network. Biomedical Engineering Letters, 6(2), 66-73. doi:10.1007/s13534-016-0218-2 [DOI:10.1007/s13534-016-0218-2]
19. Paramanathan, P., & Uthayakumar, R. (2008). An algorithm for computing the fractal dimension of waveforms. Applied Mathematics and Computation, 195(2), 598-603. doi:10.1016/j.amc.2007.05.011 [DOI:10.1016/j.amc.2007.05.011]
20. Pincus, S. M. (1991). Approximate entropy as a measure of system complexity. Proceedings of the National Academy of Sciences, 88(6), 2297-2301. doi:10.1073/pnas.88.6.2297 [DOI:10.1073/pnas.88.6.2297]
21. Shi, C. T. (2018). Signal pattern recognition based on fractal features and machine learning. Applied Sciences, 8(8), 1327. doi:10.3390/app8081327 [DOI:10.3390/app8081327]
22. Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006). Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. In Australasian joint conference on artificial intelligence (pp. 1015-1021). Springer, Berlin, Heidelberg. doi:10.1007/11941439_114 [DOI:10.1007/11941439_114]
23. So, P., Barreto, E., & Hunt, B. R. (1999). Box-counting dimension without boxes: Computing D 0 from average expansion rates. Physical Review E, 60(1), 378. doi: 10.1103/PhysRevE.60.378 [DOI:10.1103/PhysRevE.60.378]
24. Taheri, H., Taheri, A., & Amiri, M. (2017). Evaluation of the effectiveness of group behavioral activation therapy on social anxiety, avoidance and negative evaluations of people with social anxiety symptoms. Journal of Mental Health Principles, 19 (5), 361-365.‎ doi:10.22038/JFMH.2017.9057 [Persian]
25. Taravat, A., Proud, S., Peronaci, S., Del Frate, F., & Oppelt, N. (2015). Multilayer perceptron neural networks model for meteosat second generation SEVIRI daytime cloud masking. Remote Sensing, 7(2), 1529-1539. doi:10.3390/rs70201529 [DOI:10.3390/rs70201529]
26. Trambaiolli, L. R., & Biazoli, C. E. (2020). Resting-state global EEG connectivity predicts depression and anxiety severity. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 3707-3710).IEEE. doi: 10.1109/EMBC44109.2020.9176161 [DOI:10.1109/EMBC44109.2020.9176161]
27. Wang, S., Tang, J., & Liu, H. (2017). Feature Selection. doi:10.1007/978-1-4899-7502-7_101-1 [DOI:10.1007/978-1-4899-7502-7_101-1]
28. Xie, Y., Yang, B., Lu, X., Zheng, M., Fan, C., Bi, X., & Li, Y. (2020). Anxiety and depression diagnosis method based on brain networks and convolutional neural networks. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 1503-1506). IEEE. doi:10.1109/EMBC44109.2020.9176471 [DOI:10.1109/EMBC44109.2020.9176471]
29. Zhao, Z., Anand, R., & Wang, M. (2019). Maximum relevance and minimum redundancy feature selection methods for a marketing machine learning platform. In 2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA) (pp. 442-452). IEEE. doi:10.1109/DSAA.2019.00059 [DOI:10.1109/DSAA.2019.00059]

Add your comments about this article : Your username or Email:

Send email to the article author

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

© 2024 CC BY-NC 4.0 | فصلنامه روانشناسی شناختی

Designed & Developed by : Yektaweb