Advertisement

Detection of Alcoholism: An EEG Hybrid Features and Ensemble Subspace K-NN Based Approach

  • Sandeep Bavkar
  • Brijesh IyerEmail author
  • Shankar Deosarkar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11319)

Abstract

The excessive consumption of alcohol affects the brain neuronal system. Electroencephalogram signals convey information regarding alcoholic or normal status of a subject. The paper reports a novel method of detection of alcoholism using EEG hybrid features. Narrow band pass Butterworth filters are designed to separate the EEG rhythms. Linear, nonlinear and statistical feature are extracted to measure the complexity and nonlinearity in EEG signal. Alpha and Gamma rhythm gives very low p-value, indicating that gamma and alpha rhythms are capable to differentiate alcoholic EEG signal from nonalcoholic EEG signal. These rhythm features were applied to ensemble subspace K NN classifier with 10-fold cross validation. The proposed method with ensemble subspace KNN classifier delivers best classification accuracy (98.25%) as compared with other existing techniques.

Keywords

Alcoholic Nonlinear features EEG rhythm 

References

  1. 1.
    World Health Organization: Global Status Report on Alcohol and Health. World Health Organization, Geneva (2014)Google Scholar
  2. 2.
  3. 3.
    Mukherjee, S.: Alcoholism and its effects on the central nervous system. Curr. Neurovascular Res. 10(3), 256–262 (2013)CrossRefGoogle Scholar
  4. 4.
    Acharya, U.R., Sree, S.V., Chattopadhyay, S., Suri, J.S.: Automated diagnosis of normal and alcoholic EEG signals. Int. J. Neural Syst. 22(3) (2012).  https://doi.org/10.1142/s0129065712500116
  5. 5.
    Palaniappan, R.: Discrimination of alcoholic subjects using second order autoregressive modelling of brain signals evoked during visual stimulus perception. World Acad. Sci. Eng. Technol. 12, 640–645 (2005)Google Scholar
  6. 6.
    Zhu, G., Li, Y., Wen, P.P., Wang, S.: Analysis of alcoholic EEG signals based on horizontal visibility graph entropy. Brain Inform. 1(1–4), 19–25 (2014)CrossRefGoogle Scholar
  7. 7.
    Shri, T.K.P., et.al.: Characterization of EEG signals for identification of alcoholics using ANOVA ranked approximate entropy and classifiers. In: International Conference on Circuits, Communication, Control and Computing, Bangalore, pp. 109–112 (2014)Google Scholar
  8. 8.
    Kumar, A., Ghosh, S., Tetarway, S., Sinha, R.: Support vector machine and fuzzy C-mean clustering-based comparative evaluation of changes in motor cortex electroencephalogram under chronic alcoholism. Med. Biol. Eng. Comput. 53(7), 609–622 (2015)CrossRefGoogle Scholar
  9. 9.
    Taran, S., Bajaj, V.: Rhythm-based identification of alcohol EEG signals. IET Sci. Measur. Technol. 12(3), 343–349 (2018)CrossRefGoogle Scholar
  10. 10.
  11. 11.
    Gul, A., Perperoglou, A., Khan, Z., et al.: Adv. Data Anal. Classif. 12, 827 (2018).  https://doi.org/10.1007/s11634-015-0227-5MathSciNetCrossRefGoogle Scholar
  12. 12.
    Ahmadi, N., Pei, Y., Pechenizkiy, M.: Detection of alcoholism based on EEG signals and functional brain network features extraction. In: 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS), Thessaloniki, pp. 179–184 (2017)Google Scholar
  13. 13.
    Gopan, G.K., Sinha, N., Babu, D.J.: Hybrid features based classification of alcoholic and non-alcoholic EEG. In: IEEE International Conference on Electronics, Computing and Communication Technologies, Bangalore, pp. 1–6 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Sandeep Bavkar
    • 1
  • Brijesh Iyer
    • 1
    Email author
  • Shankar Deosarkar
    • 1
  1. 1.Department of E & TC EngineeringDr. Babasaheb Ambedkar Technological UniversityLonere, District RaigadIndia

Personalised recommendations