Multichannel EEG based inter-ictal seizures detection using Teager energy with backpropagation neural network classifier

  • N. Sriraam
  • Kadeeja Tamanna
  • Leena Narayan
  • Mehraj Khanum
  • S. Raghu
  • A. S. Hegde
  • Anjani Bhushan Kumar
Technical Paper


A long-term multichannel electroencephalogram recording plays a crucial role in recognizing the epileptic seizure activities from the brain lobes. This research study investigates the automated detection of epileptic seizures from multichannel electroencephalogram recordings using Teager energy feature. A supervised back-propagation neural network model was implemented to classify the inter-ictal seizures. The study was conducted on multichannel electroencephalogram data that was obtained from Institute of Neuroscience, Ramaiah Memorial Hospital, Bengaluru, India, after ethical clearance from the from the Institutional Ethics Board. Initially, notch filter was applied to remove the 50 Hz power line noise from raw electroencephalogram followed by independent component analysis to remove eye blinks and muscular activities. A time domain feature called Teager energy was estimated which detects the rapid changes in the given electroencephalogram time series. A 1 s windowing was introduced to ensure stationarity for estimation of Teager energy. The descriptive and box plot analysis ensures the suitability of the Teager energy for the seizure detection. The performance of the multilayer perceptron neural network classifier was evaluated using sensitivity, specificity, and false detection rate. Simulation results showed the highest sensitivity, specificity and false detection rate of 96.66%, 99.15%, and 0.30 per hour respectively. It can be concluded that procedure can be applied for real-time seizure detection.


Electroencephalogram Epileptic seizures Epilepsy Independent component analysis Multilayer perceptron neural network 



The authors would like to thank the doctors, Institute of Neuroscience, Ramaiah Memorial Hospital, Bengaluru, India, for granting permission to use the EEG data. We would also like to acknowledge them for their constant support in data annotation and effective discussions on epilepsy.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

The proposed study makes use EEG from Ramaiah Memorial College and Hospitals, Bengaluru, India, after appropriate ethical clearance was taken.


  1. 1.
    New to seizures and Epilepsy, Epilepsy Foundation (2017) Accessed 5 Jan 2018
  2. 2.
    EEG (2017) Accessed 5 Jan 2018
  3. 3.
    Dabye AS, Issaka MA, Gueye L (2015) Localization of epileptic seizure with an approach based on the PSD with an autoregressive model. arXiv preprint arXiv:1506.00947Google Scholar
  4. 4.
    Kamath C (2013) A new approach to detect epileptic seizures in electroencephalograms using Teager energy. ISRN Biomed Eng. CrossRefGoogle Scholar
  5. 5.
    Herta J et al (2015) Prospective assessment and validation of rhythmic and periodic pattern detection in NeuroTrend: a new approach for screening continuous EEG in the intensive care unit. Epilepsy Behav 49:273–279CrossRefGoogle Scholar
  6. 6.
    Abbassi R, Esmaielpour E (2017) Selecting statistical characteristics of brain signals to detect epileptic seizures using discrete wavelet transform and perceptron neural network. Int J Interact Multimed Artif Intell 4:33–38Google Scholar
  7. 7.
    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 60:3375–3381CrossRefGoogle Scholar
  8. 8.
    Xia YS, Leung H (2006) Nonlinear spatial-temporal prediction based on optimal fusion. IEEE Trans Neural Netw 17:975–988CrossRefGoogle Scholar
  9. 9.
    Guruva Reddy A, Narava S (2013) Artifact removal from EEG signals. Int J Comput Appl 77(13):1–3Google Scholar
  10. 10.
    Kamath C (2013) Teager energy based filter-bank Cepstra in EEG classification for seizure detection using radial basis function neural network. ISRN Biomedical Engineering, Hindawi. CrossRefGoogle Scholar
  11. 11.
    Samiee K, Kovacs P, Gabbouj M (2015) Epileptic seizure classification of EEG time-series using rational discrete short-time Fourier transform. IEEE Trans Biomed Eng 62:541–552CrossRefGoogle Scholar
  12. 12.
    Zeng K, Jiaqing Y, Yinghua W (2016) Automatic detection of absence seizures with compressive sensing EEG. Neurocomputing 171:497–502. CrossRefGoogle Scholar
  13. 13.
    Venkataraman V (2014) Brain dynamics based automated epileptic seizure detection. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, pp 946–949. CrossRefGoogle Scholar
  14. 14.
    Ratham H et al (2016) Classification of epileptic EEG signals based on simple random sampling and sequential feature selection. Brain Inform 3:85–91CrossRefGoogle Scholar
  15. 15.
    Koren J et al (2005) Prediction of rhythmic and periodic EEG patterns and seizures on continuous EEG with early epileptiform discharges. Epilepsy Behav 49:286–289. CrossRefGoogle Scholar
  16. 16.
    Agustina GC, Lorena O, Pablo D, Eric L (2015) Automatic detection of epileptic seizures in long-term EEG records, Universidad Nacional de San Juan (UNSJ), San Juan, Argentina. Comput Biol Med 57:66–73CrossRefGoogle Scholar
  17. 17.
    Helal AEM, Seddi AF, Eldosoky M, Hussein AAF (2014) An efficient method for epileptic seizure detection in long-term EEG recordings. J Biomed Sci Eng 7:963–972CrossRefGoogle Scholar
  18. 18.
    Li M, Cui Y, Yang J (2013) Automatic removal of ocular artifact from EEG with DWT and ICA method. Appl Math Inform Sci 7:809–816CrossRefGoogle Scholar
  19. 19.
    Besio WG et al (2014) High-frequency oscillations recorded on the scalp of patients with epilepsy using tripolar concentric ring electrodes. IEEE J Trans Eng Health Med 2:1–11CrossRefGoogle Scholar
  20. 20.
    Zandi AS, Javidan M, Dumont GA, Tafreshi R (2010) Automated real-time epileptic seizure detection in scalp EEG recordings using an algorithm based on wavelet packet transform. IEEE Trans Biomed Eng 57:1639–1651CrossRefGoogle Scholar
  21. 21.
    Shoeb A et al (2004) Patient-specific seizure onset detection. Epilepsy Behav 5:483–498CrossRefGoogle Scholar
  22. 22.
    Bhattacharyya S et al (2011) Feature selection for automatic burst detection in the neonatal electroencephalogram. IEEE J Emerg Select Top Circuits Syst 1:469–479CrossRefGoogle Scholar
  23. 23.
    Shen CP (2013) A physiology-based seizure detection system for multichannel EEG. PLoS ONE 8:1–9CrossRefGoogle Scholar
  24. 24.
    Ji Z et al (2015) An automatic spike detection system based on elimination of false positives using the large-area context in the scalp EEG. IEEE Trans Biomed Eng 58:2478–2488Google Scholar
  25. 25.
    Raghu S, Sriraam N, Pradeep Kumar G, Hegde AS (2018) A novel approach for real time recognition of epileptic seizures using minimum variance modified fuzzy entropy. IEEE Trans Biomed Eng. CrossRefPubMedGoogle Scholar
  26. 26.
    Raghu S, Sriraam N (2017) Optimal configuration of multilayer perceptron neural network classifier for recognition of intracranial epileptic seizures. Expert Syst Appl 89:205–222CrossRefGoogle Scholar
  27. 27.
    Raghu S, Sriraam N, Pradeep Kumar G (2016) Classification of epileptic seizures using wavelet packet log energy and norm entropies with recurrent Elman neural network classifier. Cognit Neurodyn 11:51–66CrossRefGoogle Scholar
  28. 28.
    Probability and Statistics (2014) Accessed 5 Jan 2018

Copyright information

© Australasian College of Physical Scientists and Engineers in Medicine 2018

Authors and Affiliations

  1. 1.Centre for Medical Electronics and ComputingRamaiah Institute of Technology (Affiliated to VTU Belgaum)BengaluruIndia
  2. 2.Institute of NeuroscienceRamaiah Medical College and HospitalsBengaluruIndia

Personalised recommendations