Medical & Biological Engineering & Computing

, Volume 48, Issue 4, pp 321–330 | Cite as

New feature extraction approach for epileptic EEG signal detection using time-frequency distributions

  • Carlos Guerrero-Mosquera
  • Armando Malanda Trigueros
  • Jorge Iriarte Franco
  • Ángel Navia-Vázquez
Original Article


This paper describes a new method to identify seizures in electroencephalogram (EEG) signals using feature extraction in time–frequency distributions (TFDs). Particularly, the method extracts features from the Smoothed Pseudo Wigner-Ville distribution using tracks estimated from the McAulay-Quatieri sinusoidal model. The proposed features are the length, frequency, and energy of the principal track. We evaluate the proposed scheme using several datasets and we compute sensitivity, specificity, F-score, receiver operating characteristics (ROC) curve, and percentile bootstrap confidence to conclude that the proposed scheme generalizes well and is a suitable approach for automatic seizure detection at a moderate cost, also opening the possibility of formulating new criteria to detect, classify or analyze abnormal EEGs.


Time–frequency distributions Epilepsy Detection Sinwave analysis McAulay-Quatieri sinusoidal analysis Feature extraction 


  1. 1.
    Abásolo D, Escudero J, Hornero R, Gómez C, Espino P (2008) Approximate entropy and auto mutual information analysis of the electroencephalogram in Alzheimer’s disease patients. Med Biol Eng Comput 46:1019–1028CrossRefGoogle Scholar
  2. 2.
    Acir N, Oztura I, Kuntalp M, Baklan B, Guzelis C (2005) Automatic detection of epileptiform events in EEG by three-stage procedure based on artificial neural networks. IEEE Trans Biomed Eng 52:30–40CrossRefGoogle Scholar
  3. 3.
    Afonso VX, Tompkins WJ (1995) Detecting ventricular fibrillation. IEEE Eng Med Biol 14:152–159CrossRefGoogle Scholar
  4. 4.
    Akay M (1996) Detection and estimation methods for biomedical signals. Academic Press, New JerseyGoogle Scholar
  5. 5.
    Auger F, Aldrin P, Goncalves P, Lemoine O (1996) Time–frequency toolbox for Matlab, user’s guide and reference guide. CNRS (France) and Rice University (USA), ParisGoogle Scholar
  6. 6.
    Barlow JS (1985) Methods of analysis of nonstationary EEGs, with emphasis on segmentation techniques: a comparative review. J Clin Neurophysiol 2:267–304CrossRefGoogle Scholar
  7. 7.
    Blume WT, Young GB, Lemieux JF (1984) EEG morphology of partial epileptic seizures. Electroencephalogr Clin Neurophysiol 4:295–302Google Scholar
  8. 8.
    Boashash B (2003) Time frequency signal analysis and processing. A comprehensive reference. Elsevier, OxfordGoogle Scholar
  9. 9.
    Boashash B, Mesbah M (2001) A time–frequency approach for newborn seizure detection. IEEE Eng Med Biol Mag 20(5):54–64CrossRefGoogle Scholar
  10. 10.
    Boashash B, Mesbah M (2002) Time–frequency methodology for newborn electroencephalographic seizure detection. In: Papandreou-Suppappola A (ed) Applications in time–frequency signal processing. CRC Press, Boca Raton, FloridaGoogle Scholar
  11. 11.
    Boashash B, Carson H, Mesbah M (2000) Detection of seizures in newborns using time–frequency of EEG signals. Proceedings of Tenth IEEE workshop on statistical signal and array processing, pp 564–568Google Scholar
  12. 12.
    Cardoso JF (1998) Blind signal separation: statistical principles. Proc IEEE 86:2009–2025CrossRefGoogle Scholar
  13. 13.
    Carmona RA, Hwang WL, Torrésani B (1999) Multiridge detection and time–frequency reconstruction. IEEE Trans Signal Process 47:480–492CrossRefGoogle Scholar
  14. 15.
    Cohen L (1989) Time–frequency distributions—a review. Proc IEE 77:941–981CrossRefGoogle Scholar
  15. 14.
    Cohen L (1995) Time–frequency analysis. Prentice Hall, Upper Saddle River, NJGoogle Scholar
  16. 16.
    Colder BW, Frysinger RC, Wilson CL, Harper RM, et al (1996) Decreased neuronal burst discharge near site of seizure onset in epileptic human temporal lobes. Epilepsia 37:113–121CrossRefGoogle Scholar
  17. 17.
    Durka PJ (1996) Time–frequency analysis of EEG. Thesis Institute of Experimental Physics, Warsaw UniversityGoogle Scholar
  18. 18.
    Freeman WJ (1963) The electrical activity of a primary sensory cortex: analysis of EEG waves. Int Rev Neurobiol 5:53–119CrossRefGoogle Scholar
  19. 19.
    Gonzalez B, Sanei S, Chambers JA (2003) Support vector machines for seizure detection. Proceedings of the IEEE ISSPIT, pp 126–129Google Scholar
  20. 21.
    Gotman J (1982) Automatic recognition of epileptic seizures in the EEG. Electroencephalogr Clin Neurophysiol 54:530–540CrossRefGoogle Scholar
  21. 20.
    Gotman J (1983) Measurement of small time differences between EEG channels: methods and application to epileptic seizure propagation. Electroencephalogr Clin Neurophysiol 56:501–514CrossRefGoogle Scholar
  22. 22.
    Grewal S, Gotman J (2005) An automatic warning system for epileptic seizures recorded on intracerebral EEGs. Clin Neurophysiol 116:2460–2472CrossRefGoogle Scholar
  23. 23.
    Guerrero C, Malanda A, Iriarte J (2005) Time–frequency EEG analysis in epilepsy: what is more suitable? Proceedings of the IEEE ISSPIT, pp 202–207Google Scholar
  24. 24.
    Guerrero-Mosquera C, Navia Vazquez A (2009) Automatic removal of ocular artifacts from EEG data using adaptive filtering and independent component analysis. Proceedings of the 17th European signal processing conference (EUSIPCO), pp 2317–2321Google Scholar
  25. 25.
    Harrell FE (2001) Regression modeling strategies. Springer, New YorkMATHGoogle Scholar
  26. 26.
    Hassanpour H, Mesbah M, Boashash B (2004) Time–frequency feature extraction of newborn EEG seizure using SVD-based techniques. Proceedings of EURASIP. J Appl Signal Process 16:2544–2554CrossRefGoogle Scholar
  27. 27.
    He P, Wilson G, Russel C (2004) Removal of ocular artifacts from electro-encephalogram by adaptive filtering. Med Biol Eng Comput 42:407–412CrossRefGoogle Scholar
  28. 28.
    Hinrikus H, Suhhova A, Bachmann M, et al (2009) Electroencephalographic spectral asymmetry index for detection of depression. Med Biol Eng Comput 47:1291–1299CrossRefGoogle Scholar
  29. 29.
    Hlawatsch F, Boudreaux-Bartels GF (1992) Linear and quadratic time–frequency signal representation. IEEE SP Mag 9:21–67CrossRefGoogle Scholar
  30. 30.
    Hoeve M, Zwaag BJ, Slump K, Jones R (2003) Detecting epileptic seizure activity in the EEG by independent component analysis. Proceedings of the ProRISC workshop on circuits systems and signal processing, pp 373–378Google Scholar
  31. 31.
    Iriarte J, Urrestarazu E, Valencia M, Alegre M, Malanda A, Viteri C, Artieda J (2003) Independent component analysis as a tool to eliminate artifacts in EEG: a quantitative study. J Clin Neurophysiol 20:249–257CrossRefGoogle Scholar
  32. 32.
    Joyce CA, Gorodnitsky IF, Kutas M (2004) Automatic removal of eye movement and blink artifacts from EEG data using blind component separation. Psychophysiology 41:1–13CrossRefGoogle Scholar
  33. 33.
    Kay SM, Marple SL (1981) Spectrum analysis: a modern perspective. Proc IEEE 69:1380–1419CrossRefGoogle Scholar
  34. 34.
    Lehnertz K, Elger CE (1995) Spatio-temporal dynamics of the primary epileptogenic area in temporal lobe epilepsy characterized by neuronal complexity loss. Electroencephalogr Clin Neurophysiol 95:108–117CrossRefGoogle Scholar
  35. 35.
    Le Van P, Urrestarazu E, Gotman J (2006) A system for automatic removal in ictal scalp EEG based on independent component analysis and Bayesian classification. Clin Neurophysiol 117:912–927CrossRefGoogle Scholar
  36. 36.
    Li H, Sun Y (2005) The study and test of ICA algorithms. Proc IEEE Wirel Commun Netw Mob Comput 1:602–605CrossRefMathSciNetGoogle Scholar
  37. 37.
    Lin Z-Y, Chen JDZ (1996) Advances in time–frequency analysis of biomedical signals. Crit Rev Biomed Eng 24:1–70MATHGoogle Scholar
  38. 38.
    Makeig S, Bell AJ, Jung TP, Sejnowski T (1996) Independent component analysis of electroencephalogram data. Adv Neural Inf Process Syst 145–151Google Scholar
  39. 39.
    McAulay RJ, Quatieri TF (1986) Speech analysis/synthesis based on a sinusoidal representation. IEEE Trans Acoust Speech Signal Process 34:744–754CrossRefGoogle Scholar
  40. 40.
    Mohseni HR, Maghsoudi A, Shamsollahi MB (2006) Seizure detection in EEG signals: a comparision of different approaches. Proceedings of the 28th IEEE annual EMBS international conference, pp 6724–6727Google Scholar
  41. 41.
    Muthuswamy J, Thakor NV (1998) Spectral analysis methods for neurological signals. J Clin Neurophysiol 83:1–14Google Scholar
  42. 42.
    Osorio I, Frei MG, Wilkinson SB (1998) Real-time automated detection and quantitative analysis of seizures and short-term prediction of clinical onset. Epilepsy 39:615–627CrossRefGoogle Scholar
  43. 43.
    Rankine R, Mesbah M, Boashash B (2007) IF estimation for multicomponent signals using image processing techniques in the time–frequency domain. Signal Process 87:1234–1250CrossRefMATHGoogle Scholar
  44. 44.
    Sclabassi RJ, Sun M, Krieger DN, Scher MS (1990) Time–frequency analysis of the EEG signal. Proceedings of the international conference on signal processing, pp 935–938Google Scholar
  45. 45.
    Senhadji L, Wendling F (2002) Epileptic transient detection: wavelets and time–frequency approaches. Neurophysiol Clin 32:175–192CrossRefGoogle Scholar
  46. 46.
    Swarnkar V, Abeyratne UR, Hukins C, Duce B (2009) A state transition-based method for quantifying EEG sleep fragmentation. Med Biol Eng Comput 47:1053–1061CrossRefGoogle Scholar
  47. 47.
    Tognola G, Ravazzani P, Minicucci F, Locatelli T, et al (1996) Analysis of temporal non-stationarities in EEG signals by means of parametric modelling. Technol Health Care 4:169–185Google Scholar
  48. 48.
    Tseng SY, Chen RC, Chong FC, Kuo TS (1995) Evaluation of parametric methods in EEG signal analysis. Med Eng Phys 17:71–78CrossRefGoogle Scholar
  49. 49.
    Tzallas AT, Tsipouras MG, Fotiadis DI (2007) The use of time–frequency distributions for epileptic seizure detection in EEG recordings. Proceedings of the IEEE EMBS, pp 3–6Google Scholar
  50. 50.
    Williams WJ, Zavery HP, Sackellares JC (1995) Time–frequency analysis in electrophysiology signals in epilepsy. IEEE Eng Med Biol 14:133–143CrossRefGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2010

Authors and Affiliations

  • Carlos Guerrero-Mosquera
    • 1
  • Armando Malanda Trigueros
    • 1
  • Jorge Iriarte Franco
    • 1
  • Ángel Navia-Vázquez
    • 1
  1. 1.Signal Processing and Communications DepartmentUniversity Carlos III of MadridMadridSpain

Personalised recommendations