Advertisement

Data selection in EEG signals classification

  • Shuaifang WangEmail author
  • Yan Li
  • Peng Wen
  • David Lai
Scientific Paper

Abstract

The alcoholism can be detected by analyzing electroencephalogram (EEG) signals. However, analyzing multi-channel EEG signals is a challenging task, which often requires complicated calculations and long execution time. This paper proposes three data selection methods to extract representative data from the EEG signals of alcoholics. The methods are the principal component analysis based on graph entropy (PCA-GE), the channel selection based on graph entropy (GE) difference, and the mathematic combinations channel selection, respectively. For comparison purposes, the selected data from the three methods are then classified by three classifiers: the J48 decision tree, the K-nearest neighbor and the Kstar, separately. The experimental results show that the proposed methods are successful in selecting data without compromising the classification accuracy in discriminating the EEG signals from alcoholics and non-alcoholics. Among them, the proposed PCA-GE method uses only 29.69 % of the whole data and 29.5 % of the computation time but achieves a 94.5 % classification accuracy. The channel selection method based on the GE difference also gains a 91.67 % classification accuracy by using only 29.69 % of the full size of the original data. Using as little data as possible without sacrificing the final classification accuracy is useful for online EEG analysis and classification application design.

Keywords

EEG Data selection Horizontal visibility graph (HVG) Principal component analysis (PCA) 

References

  1. 1.
    Haas LF (2003) Hans Berger (1873–1941), Richard Caton (1842–1926), and electroencephalography. J Neurol Neurosurg Psychiatr 74(1):9–9CrossRefPubMedPubMedCentralGoogle Scholar
  2. 2.
    Lehnertz K, Elger CE (1998) Can Epileptic seizures be predicted? Evidence from nonlinear time series analysis of brain electrical activity. Phys Rev Lett 80(22):5019–5022CrossRefGoogle Scholar
  3. 3.
    Martinerie J, Adam C, Quyen MLV, Baulac M, Clemenceau S, Renault B, Varela FJ (1998) Epileptic seizures can be anticipated by non-linear analysis. Nat Med 4(10):1173–1176CrossRefPubMedGoogle Scholar
  4. 4.
    Siuly S, Kabir E, Wang H, Zhang Y (2015) Exploring sampling in the detection of multicategory EEG signals. Computat Math Methods Med 2015:576437. doi: 10.1155/2015/576437 Google Scholar
  5. 5.
    Siuly LY, Wen P (2011) EEG signal classification based on simple random sampling technique with least square support vector machine. Int J Biomed Eng Technol 7(4):390–409. doi: 10.1504/IJBET.2011.044417 CrossRefGoogle Scholar
  6. 6.
    Zhu G, Li Y, Wen P (2011) Evaluating functional connectivity in alcoholics based on maximal weight matching. J Adv Comput Intell Intell Inform 15(9):1221–1227Google Scholar
  7. 7.
    Wackermann J (1995) Beyond mapping: estimating complexity of multichannel EEG recordings. Acta Neurobiol Exp 56(1):197–208Google Scholar
  8. 8.
    Zhu G, Li Y, Wen PP (2012) An efficient visibility graph similarity algorithm and its application on sleep stages classification. Brain Informatics. Springer, New York, pp 185–195CrossRefGoogle Scholar
  9. 9.
    Stam C, Lelj EHVD, Keunen R, Tavy D (1999) Nonlinear EEG changes in postanoxic encephalopathy. Theory in Biosciences-Theorie in den Biowissenschaften 118(3–4):209–218Google Scholar
  10. 10.
    Stam CJ, Van Woerkom T, Keunen R (1997) Non-linear analysis of the electroencephalogram in Creutzfeldt-Jakob disease. Biol Cybern 77(4):247–256CrossRefPubMedGoogle Scholar
  11. 11.
    Nguyen-Ky T, Wen P, Li Y, Malan M (2012) Measuring the hypnotic depth of anaesthesia based on the EEG signal using combined wavelet transform, eigenvector and normalisation techniques. Comput Biol Med 42(6):680–691CrossRefPubMedGoogle Scholar
  12. 12.
    Li T, Wen P, Jayamaha S (2014) Anaesthetic EEG signal denoise using improved nonlocal mean methods. Australas Phys Eng Sci Med 37(2):431–437CrossRefPubMedGoogle Scholar
  13. 13.
    Misulis KE, Spehlmann R (1994) Spehlmann’s evoked potential primer: visual, auditory, and somatosensory evoked potentials in clinical diagnosis. Butterworth-Heinemann Medical, BostonGoogle Scholar
  14. 14.
    Oscar-Berman M, Marinković K (2007) Alcohol: effects on neurobehavioral functions and the brain. Neuropsychol Rev 17(3):239–257CrossRefPubMedPubMedCentralGoogle Scholar
  15. 15.
    Richman JS, Moorman JR (2000) Physiological time-series analysis using approximate entropy and sample entropy. Am J Physiology-Heart Circ Physiol 278(6):H2039–H2049Google Scholar
  16. 16.
    Di W, Zhihua C, Ruifang F, Guangyu L, Tian L Notice of Retraction Study on human brain after consuming alcohol based on EEG signal. In: Computer science and information technology (ICCSIT), 2010 3rd IEEE international conference on 2010. IEEE, pp 406–409Google Scholar
  17. 17.
    Sun Y, Ye N, Xu X EEG analysis of alcoholics and controls based on feature extraction. In: Signal processing, 2006 8th international conference on 2006 IEEEGoogle Scholar
  18. 18.
    Subasi A (2007) EEG signal classification using wavelet feature extraction and a mixture of expert model. Expert Syst Appl 32(4):1084–1093CrossRefGoogle Scholar
  19. 19.
    Güler I, Übeyli ED (2005) Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients. J Neurosci Methods 148(2):113–121CrossRefPubMedGoogle Scholar
  20. 20.
    Tsuji T, Bu N, Fukuda O, Kaneko M (2003) A recurrent log-linearized Gaussian mixture network. Neural Netw IEEE Trans 14(2):304–316CrossRefGoogle Scholar
  21. 21.
    Vasicek O (1976) A test for normality based on sample entropy. J R Stat Soc Ser B (Methodol) 38:54–59Google Scholar
  22. 22.
    Polat K, Güneş S (2007) Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform. Appl Math Comput 187(2):1017–1026Google Scholar
  23. 23.
    Chandaka S, Chatterjee A, Munshi S (2009) Cross-correlation aided support vector machine classifier for classification of EEG signals. Expert Syst Appl 36(2):1329–1336CrossRefGoogle Scholar
  24. 24.
    Zhu G, Li Y, Wen PP, Wang S (2014) Analysis of alcoholic EEG signals based on horizontal visibility graph entropy. Brain Inform 1:1–7CrossRefGoogle Scholar
  25. 25.
    Tomida, Naoki et al. Active Data selection for motor imagery EEG classification. Biomed Eng, IEEE Trans 62.2 (2015): 458–467Google Scholar
  26. 26.
    Bache K, Lichman M (2013) UCI machine learning repository. URL http://archive.ics.uci.edu/ml, vol 901
  27. 27.
    Gutin G, Mansour T, Severini S (2011) A characterization of horizontal visibility graphs and combinatorics on words. Phys A 390(12):2421–2428CrossRefGoogle Scholar
  28. 28.
    Luque B, Lacasa L, Ballesteros F, Luque J (2009) Horizontal visibility graphs: exact results for random time series. Phys RevE 80(4):046103Google Scholar
  29. 29.
    Diestel R (2005) Graph theory, 3rd edn. Springer, Berlin, New YorkGoogle Scholar
  30. 30.
    Körner J (1973) Coding of an information source having ambiguous alphabet and the entropy of graphs. In: 6th Prague conference on information theory, pp 411–425Google Scholar
  31. 31.
    Shannon CE (2001) A mathematical theory of communication. ACM SIGMOBILE Mobile Comput Commun Rev 5(1):3–55CrossRefGoogle Scholar
  32. 32.
    Person K (1901) On lines and planes of closest fit to systems of points in space. Philos Mag 2(6):559–572CrossRefGoogle Scholar
  33. 33.
    Hotelling H (1933) Analysis of a complex of statistical variables into principal components. J Educ Psychol 24(6):417CrossRefGoogle Scholar
  34. 34.
    Salzberg SL (1994) C4. 5: programs for machine learning by j. ross quinlan. morgan kaufmann publishers, inc., 1993. Mach Learn 16(3):235–240Google Scholar
  35. 35.
    Sehgal L, Mohan N, Sandhu PS (2012) Quality prediction of function based software using decision tree approach. In: International conference on computer engineering and multimedia technologies (ICCEMT), pp 43–47Google Scholar
  36. 36.
    Duda RO, Hart PE (1973) Pattern classification and scene analysis, vol 3. Wiley, New YorkGoogle Scholar

Copyright information

© Australasian College of Physical Scientists and Engineers in Medicine 2015

Authors and Affiliations

  1. 1.Faculty of Health, Engineering and SciencesUniversity of Southern QueenslandToowoombaAustralia

Personalised recommendations