Abstract

Epilepsy is a type of neurological disorder which impacts the brain’s central nervous system. While the effects vary from person to person, they com- monly include mental instability, moments of loss of awareness, and seizures.There are several classi- cal approaches for analysing EEG signals for seizures identification, all of which are time-consuming. Many seizure detection strategies based on machine learning techniques have recently been developed to replace traditional methods. A hybrid model for seizure prediction of 54-DWT mother wavelets analysis of EEG signals using GA (genetic algorithm) in combination with other five machine learning (ML) classifiers: Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Artificial Neural Net- work (ANN) Naive Bayes (NB) and Random Forest is used in this paper.Using these 5 ML classifiers, the efficacy of 14 possible combinations for two-class epileptic seizure detection is evaluated. Nonetheless, the ANN classifier beat the other classifiers in most dataset combinations and attained the highest accuracy.

References

• Acharya, U. R., Oh, S. L., Hagiwara, Y., Tan, J. H., Adeli, H., & Subha, D. P. (2018). Automated eeg-based screening of depression using deep convolutional neural network. Computer meth- ods and programs in biomedicine, 161 , 103– 113.
• Ahmedt-Aristizabal, D., Fernando, T., Denman, S., Robinson, J. E., Sridharan, S., Johnston, P. J., Fookes, C. (2020). Identification of children at risk of schizophrenia via deep learning and eeg responses. IEEE Journal of biomedical and health informatics, 25 (1), 69–76.
• Akut, R. (2019). Wavelet based deep learning ap- proach for epilepsy detection. Health informa- tion science and systems, 7 (1), 8.
• Andrzejak, R. G., Lehnertz, K., Mormann, F., Rieke, C., David, P., & Elger, C. E. (2001). Indi- cations of nonlinear deterministic and finite- dimensional structures in time series of brain electrical activity: Dependence on recording re- gion and brain state. Physical Review E , 64 (6), 061907.
• Anuragi, A., & Sisodia, D. S. (2019). Alcohol use disorder detection using eeg signal features and flexible analytical wavelet transform. Biomed- ical Signal Processing and Control , 52 , 384– 393.
• Azevedo, F. A., Carvalho, L. R., Grinberg, L. T., Farfel, J. M., Ferretti, R. E., Leite, R. E., Herculano-Houzel, S. (2009). Equal numbers of neuronal and nonneuronal cells make the human brain an isometrically scaled-up pri- mate brain. Journal of Comparative Neurology, 513 (5), 532–541.
• Berger, H. (1929). Uber das electrenkephalogramm des menschen. Arch Psychiat Nervenkrankh, 87 , 527–570.
• Boersma, M., Smit, D. J., de Bie, H. M., Van Baal, G. C. M., Boomsma, D. I., de Geus, E. J., Stam, C. J. (2011). Network analysis of resting state eeg in the developing young brain: structure comes with maturation. Human brain mapping , 32 (3), 413–425.
• Brovelli, A., Battaglini, P. P., Naranjo, J. R., & Bu- dai, R. (2002). Medium-range oscillatory net- work and the 20-hz sensorimotor induced po- tential. Neuroimage, 16 (1), 130–141.
• Chen, D., Wan, S., Xiang, J., & Bao, F. S. (2017). A high-performance seizure detection algorithm based on discrete wavelet transform (dwt) and eeg. PloS one, 12 (3), e0173138.
• Chen, X., Ji, J., Ji, T., & Li, P. (2018). Cost-sensitive deep active learning for epileptic seizure detec- tion. In Proceedings of the 2018 acm interna- tional conference on bioinformatics, computational biology, and health informatics (pp. 226–235).
• Correa, A. G., Orosco, L., & Laciar, E. (2014). Automatic detection of drowsiness in eeg records based on multimodal analysis. Medical engi- neering & physics, 36 (2), 244–249.
• Davis, L. (1991). Handbook of genetic algorithms. Dedeo, M., & Garg, M. (2021). Early detection of pediatric seizures in the high gamma band. IEEE Access, 9 , 85209–85216.
• Ferrara, M., & De Gennaro, L. (2011). Going lo- cal: insights from eeg and stereo-eeg studies of the human sleep-wake cycle. Current topics in medicinal chemistry, 11 (19), 2423–2437.
• Genuth, I. (2015). All in the mind. Engineering & Technology , 10 (5), 37–39.
• Golberg, D. E. (1989). Genetic algorithms in search, optimization, and machine learning. Addion wesley, 1989 (102), 36.
• Hamad, A., Houssein, E. H., Hassanien, A. E., & Fahmy, A. A. (2018a). A hybrid eeg signals classification approach based on grey wolf op- timizer enhanced svms for epileptic detection. In Proceedings of the international conference on advanced intelligent systems and informat- ics 2017 (pp. 108–117).
• Hamad, A., Houssein, E. H., Hassanien, A. E., & Fahmy, A. A. (2018b). Hybrid grasshopper optimization algorithm and support vector ma- chines for automatic seizure detection in eeg signals. In The international conference on advanced machine learning technologies and ap- plications (amlta2018) (pp. 82–91).
• Hassan, A. R., & Subasi, A. (2016). Automatic iden- tification of epileptic seizures from eeg signals using linear programming boosting. computer methods and programs in biomedicine, 136 , 65– 77.
• Joachims, T. (2005). Text categorization with sup- port vector machines: Learning with many rel- evant features. In Machine learning: Ecml-98: 10th european conference on machine learning chemnitz, germany, april 21–23, 1998 proceedings (pp. 137–142).
• Kaleem, M., Guergachi, A., & Krishnan, S. (2018). Patient-specific seizure detection in long-term eeg using wavelet decomposition. Biomedical Signal Processing and Control , 46 , 157–165.
• Kitano, L. A. S., Sousa, M. A. A., Santos, S. D., Pires, R., Thome-Souza, S., & Campo, A. B. (2018). Epileptic seizure prediction from eeg signals using unsupervised learning and a polling-based decision process. In Artificial neural networks and machine learning icann 2018: 27th international conference on artifi- cial neural networks, rhodes, greece, october 4- 7, 2018, proceedings, part ii 27 (pp. 117–126).
• Kołodziej, M., Majkowski, A., & Rak, R. J. (2011). A new method of eeg classification for bci with feature extraction based on higher order statis- tics of wavelet components and selection with genetic algorithms. In Adaptive and natural computing algorithms: 10th international con- ference, icannga 2011, ljubljana, slovenia, april 14-16, 2011, proceedings, part i 10 (pp. 280–289).
• Kumar, M., Pachori, R. B., & Acharya, U. R. (2017). Use of accumulated entropies for automated de- tection of congestive heart failure in flexible an- alytic wavelet transform framework based on short-term hrv signals. Entropy, 19 (3), 92.
• Lekshmy, H., Panickar, D., & Harikumar, S. (2022). Comparative analysis of multiple ma- chine learning algorithms for epileptic seizure prediction. In Journal of physics: Conference series (Vol. 2161, p. 012055).
• Lestari, F. P., Haekal, M., Edison, R. E., Fauzy, F. R., Khotimah, S. N., & Haryanto, F. (2020). Epileptic seizure detection in eegs by using ran- dom tree forest, naïve bayes and knn classifica- tion. In Journal of physics: Conference series (Vol. 1505, p. 012055).
• Li, M., Chen, W., & Zhang, T. (2017). Automatic epileptic eeg detection using dt-cwt-based non- linear features. Biomedical Signal Processing and Control , 34 , 114–125.
• Lima, C. A., Coelho, A. L., Madeo, R. C., & Peres, S. M. (2016). Classification of electromyog- raphy signals using relevance vector machines and fractal dimension. Neural Computing and Applications, 27 , 791–804.
• Lin, C.-T., Chang, C.-J., Lin, B.-S., Hung, S.-H., Chao, C.-F., & Wang, I.-J. (2010). A real-time wireless brain–computer interface system for drowsiness detection. IEEE transactions on biomedical circuits and systems, 4 (4), 214–222. Mardini, W., Yassein, M. M. B., Al-Rawashdeh, R., Aljawarneh, S., Khamayseh, Y., & Meqdadi, O. (2020). Enhanced detection of epileptic seizure using eeg signals in combination with machine learning classifiers. IEEE Access, 8 , 24046–24055.
• Michalewicz, Z. (1999). Genetic algorithms+ data structures= evolution programs. springer- verlag, 1999. Google Scholar Google Scholar Digital Library Digital Library.
• Moshrefi, R., Mahjani, M. G., & Jafarian, M. (2014). Application of wavelet entropy in analysis of electrochemical noise for corrosion type identifi- cation. Electrochemistry Communications, 48 , 49–51.
• Mumtaz, W., Vuong, P. L., Xia, L., Malik, A. S., & Abd Rashid, R. B. (2016). Automatic diag- nosis of alcohol use disorder using eeg features. Knowledge-Based Systems, 105 , 48–59.
• Nasiri, J. A., Sabzekar, M., Yazdi, H. S., Naghibzadeh, M., & Naghibzadeh, B. (2009). Intelligent arrhythmia detection using genetic algorithm and emphatic svm (esvm). In 2009 third uksim european symposium on computer modeling and simulation (pp. 112–117).
• Park, C., Choi, G., Kim, J., Kim, S., Kim, T.-J., Min, K., . . . Chong, J. (2018). Epileptic seizure detection for multi-channel eeg with deep con- volutional neural network. In 2018 international conference on electronics, information, and communication (iceic) (pp. 1–5).
• Pontil, M., & Verri, A. (1998). Support vector ma- chines for 3d object recognition. IEEE trans- actions on pattern analysis and machine intel- ligence, 20 (6), 637–646.
• Raghu, S., & Sriraam, N. (2018). Classification of focal and non-focal eeg signals using neighbor- hood component analysis and machine learning algorithms. Expert Systems with Applications,113 , 18–32.
• Satapathy, S. K., Jagadev, A. K., & Dehuri, S. (2017a). Weighted majority voting based en- semble of classifiers using different machine learning techniques for classification of eeg sig- nal to detect epileptic seizure. Informatica (03505596), 41 (1).
• Satapathy, S. K., Jagadev, A. K., & Dehuri, S. (2017b). Weighted majority voting based en- semble of classifiers using different machine learning techniques for classification of eeg signal to detect epileptic seizure. Informatica (03505596), 41 (1).
• Schölkopf, B., Burges, C. J., Smola, A. J., et al. (1999). Advances in kernel methods: support vector learning. MIT press.
• Schölkopf, B., Smola, A. J., Bach, F., et al. (2002). Learning with kernels: support vector ma- chines, regularization, optimization, and be- yond. MIT press.
• Stam, C. J., Montez, T., Jones, B., Rombouts, S., Van Der Made, Y., Pijnenburg, Y. A., & Schel- tens, P. (2005). Disturbed fluctuations of rest- ing state eeg synchronization in alzheimer’s dis- ease. Clinical neurophysiology , 116 (3), 708–715.
• Subasi, A. (2007a). Eeg signal classification using wavelet feature extraction and a mixture of ex- pert model. Expert Systems with Applications, 32 (4), 1084–1093.
• Subasi, A. (2007b). Eeg signal classification using wavelet feature extraction and a mixture of ex- pert model. Expert Systems with Applications, 32 (4), 1084–1093.
• Subasi, A., Kevric, J., & Abdullah Canbaz, M. (2019). Epileptic seizure detection using hybrid machine learning methods. Neural Computing and Applications, 31 , 317–325.
• Türk, Ö., & Özerdem, M. S. (2019). Epilepsy de- tection by using scalogram based convolutional neural network from eeg signals. Brain sci- ences, 9 (5), 115.
• Yao, X., Cheng, Q., & Zhang, G.-Q. (2019a). Au- tomated classification of seizures against non- seizures: A deep learning approach. arXiv preprint arXiv:1906.02745 .
• Yao, X., Cheng, Q., & Zhang, G.-Q. (2019b). A novel independent rnn approach to classification of seizures against non-seizures. arXiv preprint arXiv:1903.09326 .
• Yu, G.-X., Ostrouchov, G., Geist, A., & Samatova, N. F. (2003). An svm-based algorithm for iden- tification of photosynthesis-specific genome fea- tures. In Computational systems bioinformat- ics. csb2003. proceedings of the 2003 ieee bioin- formatics conference. csb2003 (pp. 235–243).
• Yu, H., Lei, X., Song, Z., Liu, C., & Wang, J. (2019). Supervised network-based fuzzy learn- ing of eeg signals for alzheimer’s disease identification. IEEE Transactions on Fuzzy Systems, 28 (1), 60–71.
• Yuvaraj, R., Rajendra Acharya, U., & Hagiwara, Y. (2018). A novel parkinson’s disease diagnosis index using higher-order spectra features in eeg signals. Neural Computing and Applications, 30 , 1225–1235.
• Zakeri, Z., Assecondi, S., Bagshaw, A., & Arvanitis, T. (2014). Influence of signal preprocessing on ica-based eeg decomposition. In Xiii mediter- ranean conference on medical and biological en- gineering and computing 2013: Medicon 2013, 25-28 september 2013, seville, spain (pp. 734– 737).