Skip to main content
SpringerLink
Log in

EEG classification using recurrent adaptive neuro-fuzzy network based on time-series prediction

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Brain–computer interface (BCI) is a system that provides a way for brain and computer to communicate with each other directly. Electroencephalogram (EEG) is an important process in a BCI that can be used to determine whether the subject is doing action and/or imagination. This paper presents a motor imagery (MI) classification for BCI systems using recurrent adaptive neuro-fuzzy interface system (ANFIS). The classification system is based on time-series prediction where features are exploited from the EEG signals recorded from subjects imagining of the right hand, left hand, tongue, and foot movement. The classification system contains some recurrent ANFISes. Each recurrent ANFIS is trained on MI signals of one class and specializes in recognizing the signals of the same class from the signals of other categories. Recurrent ANFISes are employed to predict one step ahead for the EEG time-series data, and then, the classification is performed by mean square error (MSE) of the predicted signals. This approach is carried out on twelve subjects MI signals of four classes in online mode. Average prediction MSE of 0.0302 and average classification accuracy of 85.52% are obtained as results.

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

Similar content being viewed by others

References

  1. Buccino AP, Keles HO, Omurtag A (2016) Hybrid EEG-fNIRS asynchronous brain–computer interface for multiple motor tasks. PLoS ONE 11(1):e0146610

    Article  Google Scholar 

  2. Wasserman D, Aas S (2016) BCIs and disability: enhancement, environmental modification, and embodiment. Brain Comput Interfaces 3(3):126–132

    Article  Google Scholar 

  3. Cano-Izquierdo JM, Ibarrola J, Almonacid M (2012) Improving motor imagery classification with a new BCI design using neuro-fuzzy S-dFasArt. IEEE Trans Neural Syst Rehabil Eng 20(1):2–7

    Article  Google Scholar 

  4. Li M, Chen W, Zhang T (2017) Classification of epilepsy EEG signals using DWT-based envelope analysis and neural network ensemble. Biomed Signal Process Control 31:357–365

    Article  Google Scholar 

  5. Lotte F, Lécuyer A, Arnaldi B (2009) FuRIA: an inverse solution based feature extraction algorithm using fuzzy set theory for brain–computer interfaces. IEEE Trans Signal Process 57(8):3253–3263

    Article  MathSciNet  MATH  Google Scholar 

  6. Choubisa M, Trivedi P (2015) Analysing EEG signals for detection of mind awake stage and sleep deprivation stage. In: 2015 International conference on green computing and internet of things (ICGCIoT), IEEE, pp 1209–1211

  7. Komijani H, Nabaei A, Zarrabi H (2016) Classification of normal and epileptic EEG signals using adaptive neuro-fuzzy network based on time series prediction. Neurosci Biomed Eng J 4(4):273–277

    Article  Google Scholar 

  8. Abu-Alqumsan M, Ebert F, Peer A (2017) Goal-recognition-based adaptive brain–computer interface for navigating immersive robotic systems. J Neural Eng 14:036024

    Article  Google Scholar 

  9. Jang JS (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23(3):665–685

    Article  Google Scholar 

  10. Luu TP, He Y, Brown S, Nakagame S, Contreras-Vidal JL (2016) Gait adaptation to visual kinematic perturbations using a real-time closed-loop brain–computer interface to a virtual reality avatar. J Neural Eng 13(3):036006

    Article  Google Scholar 

  11. Saa JFD, Çetin M (2013) Discriminative methods for classification of asynchronous imaginary motor tasks from EEG data. IEEE Trans Neural Syst Rehabil Eng 21(5):716–724

    Article  Google Scholar 

  12. Coyle D, Prasad G, McGinnity TM (2009) Faster self-organizing fuzzy neural network training and a hyperparameter analysis for a brain–computer interface. IEEE Trans Syst Man Cybern B Cybern 39(6):1458–1471

    Article  Google Scholar 

  13. Mohammadi MR, Khaleghi A, Nasrabadi AM, Rafieivand S, Begol M, Zarafshan H (2016) EEG classification of ADHD and normal children using non-linear features and neural network. Biomed Eng Lett 6(2):66–73

    Article  Google Scholar 

  14. Chai R, Naik GR, Nguyen TN, Ling SH, Tran Y, Nguyen HT (2016) Selecting optimal EEG channels for mental tasks classification: an approach using ICA. In: 2016 IEEE congress on evolutionary computation (CEC), Vancouver, BC, pp 1331–1335

  15. Chai R, Naik GR, Nguyen TN, Ling SH, Tran Y, Craig A, Nguyen HT (2017) Driver fatigue classification with independent component by entropy rate bound minimization analysis in an EEG-based system. IEEE J Biomed Health Inform 21(3):715–724

    Article  Google Scholar 

  16. Chai R et al (2016) Classification of EEG based-mental fatigue using principal component analysis and Bayesian neural network. In: 2016 IEEE 38th annual international conference of the engineering in medicine and biology society (EMBC), IEEE

  17. Chai R et al (2015) Classification of driver fatigue in an electroencephalography-based countermeasure system with source separation module. In: 2015 37th annual international conference of the IEEE engineering in medicine and biology society (EMBC), Milan, pp 514–517

  18. La Rocca D, Campisi P, Scarano G (2012) EEG biometrics for individual recognition in resting state with closed eyes. In: 2012 BIOSIG-Proceedings of the international conference of the biometrics special interest group (BIOSIG), IEEE

  19. Kumari P, Kumar S, Vaish A (2014) Feature extraction using empirical mode decomposition for biometric system. In: 2014 international conference on signal propagation and computer technology (ICSPCT), IEEE

  20. Das R, et al (2015) EEG biometrics for user recognition using visually evoked potentials. In: 2015 International conference of the biometrics special interest group (BIOSIG), IEEE

  21. Vatankhah M, Yaghubi M (2009). Adaptive neuro-fuzzy inference system for classification of eeg signals using fractal dimension. In: 2009. EMS’09. Third UKSim European symposium on computer modeling and simulation, IEEE pp 214–218

  22. Yu W, Feng H, Feng Y, Madani K, Sabourin C (2015) Nonholonomic mobile system control by combining EEG-based BCI with ANFIS. Bio Med Mater Eng 26(s1):S1125–S1133

    Article  Google Scholar 

  23. Begum D, Ravikumar KM, Mathew J, Kubakaddi S, Yadav R (2015) EEG based patient monitoring system for mental alertness using adaptive neuro-fuzzy approach. J Med Bioeng 4(1):59–66

    Google Scholar 

  24. Homri I, Yacoub S, Ellouze N (2015) Combined approaches of features selection for EEG classification. Int Rev Comput Softw IRECOS 10(3):256–264

    Article  Google Scholar 

  25. Hekim M (2016) The classification of EEG signals using discretization-based entropy and the adaptive neuro-fuzzy inference system. Turk J Electr Eng Comput Sci 24(1):285–297

    Article  Google Scholar 

  26. Adedayo OO, Oladipo F, Ijeh-Ogboi C (2015) Softcomputing techniques for improved electroencephalogram signal analysis. Int J Curr Eng Technol 5(3):2181–2186

    Google Scholar 

  27. Blankertz B, Muller KR, Krusienski DJ, Schalk G, Wolpaw JR, Schlogl A, Birbaumer N (2006) The BCI competition III: validating alternative approaches to actual BCI problems. IEEE Trans Neural Syst Rehabil Eng 14(2):153–159

    Article  Google Scholar 

  28. Blankertz B et al (2005) BCI competition III and IV [Online]. http://www.bbci.de/competition/

  29. Schlogl A et al (2005 and 2008) BCI-competitions III (Dataset IIIa) and IV (Dataset 2A) [Online]. http://www.bbci.de/competition/iii/#data_set_iiia and http://www.Bbci.de/competition/iv/desc_2a.pdf

  30. Schlögl A, Lee F, Bischof H, Pfurtscheller G (2005) Characterization of four-class motor imagery EEG data for the BCI-competition 2005. J Neural Eng 2(4):L14

    Article  Google Scholar 

  31. Pfurtscheller G, Neuper C (2001) Motor imagery and direct brain–computer communication. Proc IEEE 89(7):1123–1134

    Article  Google Scholar 

  32. Bhardwaj S et al (2015) Online and automated reliable system design to remove blink and muscle artefact in EEG. In: 2015 37th annual international conference of the IEEE engineering in medicine and biology society (EMBC), Milan, pp 6784–6787

  33. Kwon Y et al (2015) Efficient learning of image super-resolution and compression artifact removal with semi-local Gaussian processes. IEEE Trans Pattern Anal Mach Intell 37(9):1792–1805

    Article  Google Scholar 

  34. Jadhav PN et al (2014) Automated detection and correction of eye blink and muscular artefacts in EEG signal for analysis of Autism Spectrum Disorder. In: 2014 36th annual international conference of the IEEE engineering in medicine and biology society, Chicago, IL, pp 1881–1884

  35. Jahani Fariman H, Ahmad SA, Hamiruce Marhaban M, Ali Jan Ghasab M, Chappell PH (2015) Simple and computationally efficient movement classification approach for EMG-controlled prosthetic hand: ANFIS vs. artificial neural network. Intell Autom Soft Comput 21(4):559–573

    Article  Google Scholar 

  36. Dash R, Dash P (2016) Efficient stock price prediction using a self evolving recurrent neuro-fuzzy inference system optimized through a modified technique. Expert Syst Appl 52:75–90

    Article  Google Scholar 

  37. Lin YY, Chang JY, Lin CT (2013) Identification and prediction of dynamic systems using an interactively recurrent self-evolving fuzzy neural network. IEEE Trans Neural Netw Learn Syst 24(2):310–321

    Article  Google Scholar 

  38. Frolov AA, Husek D, Polyakov PY (2009) Recurrent-neural-network-based Boolean factor analysis and its application to word clustering. IEEE Trans Neural Netw 20(7):1073–1086

    Article  Google Scholar 

  39. Coyle D, Prasad G, McGinnity TM (2005) A time-series prediction approach for feature extraction in a brain–computer interface. IEEE Trans Neural Syst Rehabil Eng 13(4):461–467

    Article  MATH  Google Scholar 

  40. Coyle D (2009) Neural network based auto association and time-series prediction for biosignal processing in brain–computer interfaces. IEEE Comput Intell Mag 4:47–59

    Article  Google Scholar 

  41. Shiman F, Safavi SH, Vaneghi FM, Oladazimi M, Safari MJ, Ibrahim F (2012) EEG feature extraction using parametric and non-parametric models. In: Proceedings of 2012 IEEE-EMBS international conference on biomedical and health informatics

  42. Zhao Y, Billings SA, Wei HL, Sarrigiannis PG (2013) A parametric method to measure time-varying linear and nonlinear causality with applications to EEG data. IEEE Trans Biomed Eng 60(11):3141–3148

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to acknowledge the Laboratory of Brain–Computer Interfaces, Institute of Biomedical Engineering, Graz University of Technology, Austria, for preparing the EEG data.

Author information

Authors and Affiliations

  1. Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran

    Hossein Komijani

  2. Department of Engineering and IT, Shiraz University of Technology, Shiraz, Iran

    Mohammad Reza Parsaei

  3. Faculty of Computing, Universiti Teknologi Malaysia, Skudai, Johor, Malaysia

    Ebrahim Khajeh

  4. Department of Electrical and Computer Engineering, Zahedan Branch, Islamic Azad University, Zahedan, Iran

    Mohammad Javad Golkar

  5. ICT Research Institute, Tehran, Iran

    Houman Zarrabi

Authors
  1. Hossein Komijani
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohammad Reza Parsaei
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ebrahim Khajeh
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mohammad Javad Golkar
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Houman Zarrabi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hossein Komijani.

Ethics declarations

Conflict of interest

All authors have no potential conflict of interest.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Komijani, H., Parsaei, M.R., Khajeh, E. et al. EEG classification using recurrent adaptive neuro-fuzzy network based on time-series prediction. Neural Comput & Applic 31, 2551–2562 (2019). https://doi.org/10.1007/s00521-017-3213-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-017-3213-3

Keywords

Search

Navigation