Skip to main content
SpringerLink
Log in

Noninvasive method of epileptic detection using DWT and generalized regression neural network

  • Focus
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

Epilepsy is a continual disorder, the characteristic of which is recurrent, motiveless seizures. Many people with epilepsy have more than one type of seizure and may have other symptoms of neurological problems as well. In this paper, a noninvasive method using discrete wavelet transform (DWT) and neural network is projected for automatic detection of epilepsy from EEG signals. DWT of the EEG signals is carried out using Haar Wavelets. Statistical features of approximate and detailed coefficients are extracted from the transformed signal. The entropy, as well as approximate entropy of the transformed signals, is determined. The features extracted from the transformed signal are used as the training set for the artificial neural network (ANN). Two types of ANNs viz. feedforward neural network (FFNN) and generalized regression neural network (GRNN) are trained. Three types of subjects viz. healthy, seizure-free period of an epileptic patient and epileptic patients are considered. The signals are classified accordingly as normal, seizure-free epileptic and abnormal. The results are compared on the basis of the confusion matrix, error histogram, and error plot. The quality measures used for comparison are sensitivity, specificity, precision, and accuracy. On all the evaluation parameters, GRNN is found to be best suited for anomaly detection in EEG signals.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Abbreviations

EEG:

Electroencephalogram

SVM:

Support vector machine

FFNN:

Feedforward neural networks

ANN:

Artificial neural network

WT:

Wavelet transform

DWT:

Discrete wavelet transform

GRNN:

Generalized regression neural network

ApEn:

Approximate entropy

KNN:

K-Nearest neighbor

References

  • Acharya UR, Molinari F, Sree SV, Chattopadhyay S, Ng K-H, Suri JS (2012) Automated diagnosis of epileptic EEG using entropies. Biomed Signal Process Control 7(4):401–408

    Article  Google Scholar 

  • Andrzejak RG, Lehnertz K, Mormann F, Rieke C, David P, Elger CE (2001) Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. Phys Rev E 64(6):061907

    Article  Google Scholar 

  • Bhattacharyya A, Sharma M, Pachori RB (2016) A novel approach for automated detection of focal EEG signals using empirical wavelet transform. Neural Comput Appl 29:1–11

    Google Scholar 

  • Bronzino JD (2000) Biomedical engineering handbook, vol 1. CRC Press, New York

    Google Scholar 

  • Chaovalitwongse W, Iasemidis LD, Pardalos PM, Carney PR, Shiau D-S, Sackellares JC (2005) Performance of a seizure warning algorithm based on the dynamics of intracranial EEG. Epilepsy Res 64:93–113

    Article  Google Scholar 

  • Gabor AJ, Seyal M (1992) Automated interictal EEG spike detection victimization artificial neural networks. Electroencephalogr Clin Neurosci 83:271–280

    Article  Google Scholar 

  • Gotman J (1999) Automatic detection of seizures and spikes. J Clin Neurophysiol 16(2):130–140. https://doi.org/10.1097/00004691-199903000-00005

    Article  Google Scholar 

  • Guo L, Riveero D, Pazaos A (2010) Convulsion detection victimization multiwavelet rework based mostly approximate entropy and artificial neural networks. J Neurosci Ways 193:156–163

    Google Scholar 

  • Janjarasjitt S (2010) Classification of the epileptic EEGs using the wavelet-based scale variance feature. Int J Appl Biomed Eng 3(1):19–25

    Google Scholar 

  • Kumar Y, Dewal ML, Anand RS (2014) Epileptic seizures detection in EEG using DWT-based ApEn and artificial neural network. Signal Image Video Process 8(7):1323–1334

    Article  Google Scholar 

  • Liu Y, Zhou W, Yuan Q, Chen S (2012) Automatic seizure detection using wavelet transform and SVM in long-term intracranial EEG. IEEE Trans Neural Syst Rehabil Eng 20(6):749–755

    Article  Google Scholar 

  • Micheli-Tzanakou E (2000) Supervised and unattended pattern recognition: feature extraction and procedure intelligence. CRC Press, Boca Raton

    Google Scholar 

  • Mihandoost S, Amirani M, Mazlaghani M, Mihandoost A (2012) Automatic feature extraction using generalised autoregressive conditional heteroscedasticity model: an application to lectroencephalogram classification. IET Signal Process 6:829–838

    Article  Google Scholar 

  • Mu Z, Xiao D, Hu J (2009) Classification of motor representational process EEG signals supported time–frequency analysis. Int J Digit Content Technol Appl 3(4):116–119

    Google Scholar 

  • Orhan U, Gurbuz E (2012) Classifying discrete interval densities of EEG signals by using DWT and SVM. In: 2012 international symposium on innovations in intelligent systems and applications, 2–4 July 2012

  • Parvez MZ, Paul M (2016) Epileptic seizure prediction by exploiting spatiotemporal relationship of EEG signals using phase correlation. IEEE Trans Neural Syst Rehabil Eng 24(1):158–168

    Article  Google Scholar 

  • Satapathya SK (2017) EEG signal classification using PSO trained RBF neural network for epilepsy identification. Inform Med Unlocked 6:1–11

    Article  Google Scholar 

  • Sivasankari N, Thanushkodi K (2009) Automated convulsion detection in EEG signals victimization quick ICA and neural network. Int J Adv Soft Comput Appl 1(2):91–104

    Google Scholar 

  • Supriya S, Siuly S, Wang H, Zhang Y (2016) Analyzing EEG signal data for detection of epileptic seizure: introducing weight on visibility graph with complex network feature. In: Proceedings of Australasian database conference (ADC), Sydney, NSW, Australia, pp 56–66

  • Tzallas AT, Tsipouras MG, Fotiadis DI (2007) Automatic seizure detection based on time–frequency analysis and artificial neural networks. Comput Intell Neurosci 2007:80510. https://doi.org/10.1155/2007/80510

    Article  Google Scholar 

  • Vavadi H, Ayatollahi A, Mirzaei A (2010) A wavelet-approximate entropy method for epileptic activity detection from EEG and its sub-bands. J Biomed Sci Eng 3:1182–1189. https://doi.org/10.4236/jbise.2010.312154

    Article  Google Scholar 

  • Wang C, Zhang C, Zou J, Zhang J (2012) Performance evaluation for epileptic electroencephalogram (EEG) detection by using Neyman-Pearson criteria and a support vector machine. Phys A 391(4):1602–1609

    Article  Google Scholar 

  • Zhou W, Liu Y, Yuan Q, Li X (2013) Epileptic seizure detection using lacunarity and Bayesian linear discriminant analysis in intracranial EEG. IEEE Trans Biomed Eng 60(12):3375–3381. https://doi.org/10.1109/tbme.2013.2254486 (Epub 2013 Apr 25)

    Article  Google Scholar 

Download references

Acknowledgements

We would also like to show our gratitude to the (S. Arivazhagan, Principal, and Dr. K. Muneeswaran, Professor and Head Department of CSE Mepco Schlenk Engineering College) for sharing their pearls of wisdom with us during the course of this research.

Author information

Authors and Affiliations

  1. Dhanalakshmi College of Engineering, Chennai, Tamil Nadu, 601301, India

    S. Vijay Anand

  2. Mepco Schlenk Engineering College, Sivakasi, Tamil Nadu, 626005, India

    R. Shantha Selvakumari

Authors
  1. S. Vijay Anand
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. R. Shantha Selvakumari
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Each author is expected to have made substantial contributions to the conception or design of the work; or the acquisition, analysis, or interpretation of data; or the creation of code used in the work. We agree to be personally accountable for the author’s own contributions and for ensuring that questions related to the accuracy or integrity of any part of the work, even ones in which the author was not personally involved, are appropriately investigated, resolved, and documented in the literature.

Corresponding author

Correspondence to S. Vijay Anand.

Ethics declarations

Conflict of interest

No conflict of interest.

Availability of data materials

The data available on Department of Epileptology, University of Bonn EEG time series download page. The link for the data set is http://epileptologie-bonn.de/cms/upload/workgroup/lehnertz/eegdata.html. The data analyzed in our study are available on this page. The sampling rate of the data was 173.61 Hz. For a more detailed description of the data, please refer to the manuscript. Please note, however, that the time series has the spectral bandwidth of the acquisition system, which is 0.5–85 Hz. The application of a low-pass filter of 40 Hz, as described in the manuscript, is regarded as the first step of analysis and therefore not carried out for the downloadable time series.

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Additional information

Communicated by P. Pandian.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Vijay Anand, S., Shantha Selvakumari, R. Noninvasive method of epileptic detection using DWT and generalized regression neural network. Soft Comput 23, 2645–2653 (2019). https://doi.org/10.1007/s00500-018-3630-y

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-018-3630-y

Keywords

Search

Navigation