Epileptic Seizure Detection from Eeg Signals by Adaptive Wavelets and Support Vector Machine

  • Authors

    • T. Venkateshkanna
    • Punithavathy K
    • Vallikannu R
    2018-12-09
    https://doi.org/10.14419/ijet.v7i4.36.23780
  • Brain disorder, EEG signal classification, epileptic seizure, adaptive wavelets, EWT, SVM

  • Abstract

    Recent advances in computer technologies help to diagnose various disorders of the brain using Electroencephalogram (EEG) signals. The importance of a diagnostic application is to reduce the False Positive (FP) cases. To achieve this, an efficient approach for epileptic seizure classification is proposed using adaptive wavelets called Empirical Wavelet Transform (EWT).  The different modes of EEG signals are extracted using EWT and then features from the different modes are extracted. Then, classification is done by a typical machine learning technique, Support Vector Machine (SVM). The performance of EWT-SVM system is evaluated using confusion matrix. From the confusion matrix, sensitivity and specificity are computed. In this paper, an efficient approach for the diagnosis of epileptic seizure using EEG signals is designed. At first, the given EEG signal is decomposed using EWT to extract the information of all components. The EWT energy features are extracted from the EEG signals which are used for training the SVM classifier. Results show that EWT-SVM system reduces the FP cases with 100% of accuracy, sensitivity and specificity which indicates that no misclassification occurs. 

     

     

  • References

    1. [1] Guo, Y., Zhang, Y., Mursalin, M., Xu, W., & Lo, B. (2018), Automated Epileptic Seizure Detection by Analyzing Wearable EEG Signals Using Extended Correlation-Based Feature Selection, IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, 66-69.

      [2] Wang, Y., Li, Z., Feng, L., Bai, H., & Wang, C. (2017), Hardware design of multiclass SVM classification for epilepsy and epileptic seizure detection, IET Circuits, Devices & Systems, 12(1), 108-115.

      [3] Gupta, A., Singh, P., & Karlekar, M. (2018), A Novel Signal Modeling Approach for Classification of Seizure and Seizure-Free EEG Signals, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(5), 925-935.

      [4] Jiang, Y., Wu, D., Deng, Z., Qian, P., Wang, J., Wang, G., ... & Wang, S. (2017), Seizure Classification From EEG Signals Using Transfer Learning, Semi-Supervised Learning and TSK Fuzzy System, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(12), 2270-2284.

      [5] Gnana Rajesh, D. (2016), Analysis of MFCC Features for EEG Signal Classification, Int. J. Adv. Sig. Img. Sci, 2 (1), 14-20.

      [6] Zhang, T., & Chen, W. (2017), LMD based features for the automatic seizure detection of EEG signals using SVM, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(8), 1100-1108.

      [7] Supriya, S., Siuly, S., Wang, H., Cao, J., & Zhang, Y. (2016), Weighted visibility graph with complex network features in the detection of epilepsy, IEEE Access, 4, 6554-6566.

      [8] Tjandrasa, H., Djanali, S., & Arunanto, F. X. (2016), Feature extraction using combination of intrinsic mode functions and power spectrum for EEG signal classification, IEEE International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, pp. 1498-1502.

      [9] Riaz, F., Hassan, A., Rehman, S., Niazi, I. K., & Dremstrup, K. (2016), EMD-based temporal and spectral features for the classification of EEG signals using supervised learning, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 24(1), 28-35.

      [10] Lasefr, Z., Reddy, R. R., & Elleithy, K. (2017), Smart phone application development for monitoring epilepsy seizure detection based on EEG signal classification, IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, pp. 83-87.

      [11] Samiee, K., Kovacs, P., & Gabbouj, M. (2015), Epileptic seizure classification of EEG time-series using rational discrete short-time Fourier transform, IEEE transactions on Biomedical Engineering, 62(2), 541-552.

      [12] Jaiswal, P., & Koushal, R. (2015), EEG signal classification using Modified Fuzzy Clustering algorithm, International Journal of Computer Science And Information Technologies, 6(3), 2031-2034.

      [13] Gilles, J. (2013). Empirical wavelet transform. IEEE transactions on signal processing, 61(16), 3999-4010.

      Daubechies, Ten Lectures on Wavelets, ser. CBMS-NSF Regional Conf. Series in Appl. Math.. Philadelphia, PA, USA: SIAM, 1992

      [14] EEG database: http://epileptologie-onn.de/cms/front_content.php?idcat=193&lang=3

      [15] Andrzejak, R.G., Lehnertz, K., Mormann, F., Rieke, C., David, P. and Elger, C.E., 2001. Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state. Physical Review E, 64(6), p.061907.

  • Downloads

  • How to Cite

    Venkateshkanna, T., K, P., & R, V. (2018). Epileptic Seizure Detection from Eeg Signals by Adaptive Wavelets and Support Vector Machine. International Journal of Engineering & Technology, 7(4.36), 247-253. https://doi.org/10.14419/ijet.v7i4.36.23780

    Received date: 2018-12-12

    Accepted date: 2018-12-12

    Published date: 2018-12-09