Effects of Sampling Length and Overlap Ratio on EEG Mental Arithmetic Task Performance: A Comparative Study

Abstract

Cognitive tasks have become quite popular in recent years. Understanding this sort of neurological research, its real-world applications, and how it may be improved in future studies are crucial. For this purpose, our study compares the classification accuracies for various segment lengths and overlap ratios for EEG recordings collected from 36 healthy volunteers during mental arithmetic tasks. EEG features are extracted from brain signals using the wavelet spectrum and the sample length and the overlap ratio of the sliding Windows are used as parameters. Feature selection was conducted using Correlation-Based and ReliefF feature selections. Subsequently, for classification results, Support Vector Machine, Random Forest, C4.5 Algorithm and k-Nearest Neighbor algorithms were employed, with the outcomes supported by the F1-score and Matthew's correlation coefficient. Therefore, the reliability of the obtained results has been ensured. In the comparisons obtained, the best average results for Accuracy, F1-score, and Matthew's correlation coefficient were found to be 0.990, 0.987, and 0.975 respectively, when applying the ReliefF feature selection method with the Support Vector Machine classifier.

Keywords

• Classification algorithms
• Cognitive science
• Electroencephalography
• Feature extraction
• Wavelet Transform

References

1. [1] Sörnmo, L., and Laguna, P., “Bioelectrical Signal Processing In Cardiac And Neurological Applications”, Elsevier Academic Press, 8: 25-53, (2005).
2. [2] Baillet, S., Mosher, J. C., and Leahy, R. M., “Electromagnetic brain mapping”, IEEE, 18(6): 14–30, (2001).
3. [3] Fukushima, K., Fukushima, J., Warabi, T., and Barnes, G. R., “Cognitive processes involved in smooth pursuit eye movements: behavioral evidence, neural substrate and clinical correlation”, Frontiers in Systems Neuroscience, 7(4), (2013).
4. [4] McFarland D. J., and Wolpaw, J. R., “EEG-based brain–computer interfaces”, current opinion in Biomedical Engineering, 4: 194-200, (2017).
5. [5] Chaudhary, U., Birbaumer, N., and Ramos-Murguialday, A., “Brain–computer interfaces for communication and rehabilitation”, Nature Reviews Neurology, 12(9): 513-525, (2016).
6. [6] Sharma, L. D., Chhabra, H., Chauhan, U., Saraswat R. K., and Sunkaria, R. K., “Mental Arithmetic Task Load Recognition Using EEG Signal and Bayesian Optimized K-Nearest Neighbor”, International Journal of Information Technology, 13(6): 2363–2369, (2021).
7. [7] Yavuz, E., and Aydemir, O., “Classification of Mental Arithmetic Based Hybrid EEG+Nirs Signals”, 28th Signal Processing and Communications Applications Conference (SIU). IEEE, Gaziantep, Turkey 1–4, (2020).
8. [8] Ergün, E., and Aydemir, O., “A New Evolutionary Preprocessing Approach for Classification of Mental Arithmetic Based EEG Signals”, Cognitive Neurodynamics, 14(5): 609–617, (2020).

9. [9] Edla, D. R., Mangalorekar, K., Dhavalikar, G., and Dodia, S., “Classification of EEG Data for Human Mental State Analysis Using Random Forest Classifier”, Procedia Computer Science, 132: 1523–1532, (2018).
10. [10] Lim, W., Sourina, O., Liu, Y., and Wang, L., “EEG-Based Mental Workload Recognition Related to Multitasking”, 10th International Conference on Information, Communications and Signal Processing (ICICS). IEEE, Singapore, 1–4, (2015).
11. [11] Fatimah, B., Javali, A., Ansar, H., Harshitha, B., and Kumar, H., “Mental Arithmetic Task Classification Using Fourier Decomposition Method”, International Conference on Communication and Signal Processing (ICCSP). IEEE, Chennai, India, 46–50, July (2020).
12. [12] Ahammed, K., and Ahmed, M. U., “Quantification of mental stress using complexity analysis of EEG signals”, Biomedical Engineering: Applications, Basis and Communications, 32(2): 2050011, (2020).
13. [13] Rahman, S. M. Z., Tawana, I., Mostafiz, H. R., Chowdhury T. T., and Shahnaz, C., “Arithmetic Mental Task of EEG Signal Classification Using Statistical Modeling of The Dwt Coefficient”, International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2). IEEE, Rajshahi, Bangladesh, 1–4, (2021).
14. [14] O’Reilly J. A., and Chanmittakul, W., “L1 Regularization-Based Selection of EEG Spectral Power and Ecg Features for Classification of Cognitive State”, 9th International Electrical Engineering Congress (iEECON). IEEE, Pattaya, Thailand, 365–368, (2021).
15. [15] Mridha, K., Kumar, D., Shukla, M., and Jani, M., “Temporal Features and Machine Learning Approaches to Study Brain Activity with EEG And Ecg”, International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE). IEEE, Greater Noida, India, 409–414, (2021).
16. [16] Babu, T. A., Gadde, S., Ravi, S., Rao, K. V., Mamillu, Y., and Krishna, D., “Analysis of Mental Task Ability in Students based on Electroencephalography Signals”, In 2022 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES), 1: 274-278, IEEE, (2022).
17. [17] Malviya, L., and Mal, S., “A novel technique for stress detection from EEG signal using hybrid deep learning model”, Neural Computing and Applications, 34(22): 19819-19830, (2022).
18. [18] Saini, M., Satija U., and Upadhayay, M. D., “Discriminatory Features Based on Wavelet Energy for Effective Analysis of Electroencephalogram During Mental Tasks”, Circuits, Systems, and Signal Processing, 1–29, (2022)
19. [19] Bergil, E., Oral C., and Ergül, E. U., “Classification of arithmetic mental task performances using EEG and ECG signals”, The Journal of Supercomputing, 1-13, (2023).
20. [20] Baygin, N., Aydemir, E., Barua, P. D., Baygin, M., Dogan, S., Tuncer, T., Tan R. S., and Acharya, U. R., “Automated mental arithmetic performance detection using quantum pattern-and triangle pooling techniques with EEG signals”, Expert Systems with Applications, 227, 120306, (2023).
21. [21] Zyma, I., Tukaev, S., Seleznov, I., Kiyono, K., Popov, A., Chernykh, M., and Shpenkov, O., “Electroencephalograms During Mental Arithmetic Task Performance”, Data, 4(1): 14, (2019).
22. [22] Vargha, A., and Delaney, H. D., “The Kruskal-Wallis Test and Stochastic Homogeneity”, Journal of Educational and Behavioral Statistics, 23(2): 170–192, (1998).
23. [23] Homan, R. W., Herman J., and Purdy, P., “Cerebral Location of International 10–20 System Electrode Placement”, Electroencephalography and Clinical Neurophysiology, 66(4): 376–382, (1987).
24. [24] Adeli, H., Zhou, Z., and Dadmehr, N., “Analysis of EEG Records in An Epileptic Patient Using Wavelet Transform”, Journal of Neuroscience Methods, 123(1): 69–87, (2003).
25. [25] Hazarika, N., Chen, J. Z., Tsoi, A. C., and Sergejew, A., “Classification of EEG Signals Using the Wavelet Transform”, Signal Processing, 59: 1, 61–72, (1997).
26. [26] Pathak, R. S., “The Wavelet Transform”, Springer Science & Business Media, 4: 109-128, 2009.
27. [27] Tzimourta, K. D., Astrakas, L. G., Gianni, A. M., Tzallas, A. T., Giannakeas, N., Paliokas, I., Tsalikakis, D. G., and Tsipouras, M. G., “Evaluation of window size in classification of epileptic short-term EEG signals using a Brain Computer Interface software”, Engineering, Technology & Applied Science Research, 8(4): 3093-3097, (2018).
28. [28] Gaur, P., Gupta, H., Chowdhury, A., McCreadie, K., Pachori, R. B., and Wang, H., “A sliding window common spatial pattern for enhancing motor imagery classification in EEG-bci”, IEEE Transactions on Instrumentation and Measurement, 70: 1–9, (2021).
29. [29] Li, Y., Wei, H. L., Billings, S. A., and Sarrigiannis, P. G., “Identification of Nonlinear Time-Varying Systems Using An Online Sliding-Window and Common Model Structure Selection (Cmss) Approach with Applications to EEG”, International Journal of Systems Science, 47: 11, 2671–2681, (2016).
30. [30] Hall, M. A., “Correlation-based feature selection for machine learning”, Ph.D. dissertation, The University of Waikato, (1999).
31. [31] Jin, J., Miao, Y., Daly, I., Zuo, C., Hu, D., and Cichocki, A., “Correlation-based channel selection and regularized feature optimization for MI-based BCI”, Neural Networks, 118: 262-270, (2019).
32. [32] Şen, B., Peker, M., Çavuşoğlu, A., and Çelebi, F. V., “A comparative study on classification of sleep stage based on EEG signals using feature selection and classification algorithms”, Journal of Medical Systems, 38: 1-21, (2014).
33. [33] Kira, K., and Rendell, A. L., “The feature selection problem: Traditional methods and a new algorithm”, In Proceedings of The Tenth National Conference On Artificial Intelligence, 129-134, (1992).
34. [34] Zhang, S., Cheng, D., Deng, Z., Zong, M., and Deng, X., “A Novel Knn Algorithm with Data-Driven K Parameter Computation”, Pattern Recognition Letters, 109: 44–54, (2018).
35. [35] Edla, D. R., Mangalorekar, K., Dhavalikar, G., and Dodia, S., “Classification of EEG Data for Human Mental State Analysis Using Random Forest Classifier”, Procedia Computer Science, 132: 1523-1532, (2018).
36. [36] Wang, S., Li, Y., Wen, P., and Zhu, G., “Analyzing EEG signals using graph entropy-based principle component analysis and J48 decision tree”, In Proceedings of the 6th International Conference on Signal Processing Systems (ICSPS 2014), University of Southern Queensland, (2014).
37. [37] Du, K. L., and Swamy, M., “Support vector machines”, in Neural Networks and Statistical Learning, Springer, 469–524, (2014).
38. [38] Sidaoui, B., and Sadouni, K., “Epilepsy Seizure Prediction from EEG Signal Using Machine Learning Techniques”, Advances in Electrical & Computer Engineering, 23: 2, (2023).
39. [39] Stancic, I., Veic, L., Music, J., and Grujic, T., “Classification of Low-Resolution Flying Objects in Videos Using the Machine Learning Approach”, Advances in Electrical & Computer Engineering, 22: 2, (2022).
40. [40] Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E., Louppe, G., “Scikit-learn: Machine Learning in Python”, JMLR 12: 2825-2830, (2011).
41. [41] Chicco, D., and Jurman, G., “The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation”, BMC Genomics, 21: 1, 1-13, (2020).
42. [42] Berrar, D., “Cross-Validation”, 542-545, (2019).