Advertisement

Neural Computing and Applications

, Volume 31, Issue 4, pp 1117–1126 | Cite as

LU triangularization extreme learning machine in EEG cognitive task classification

  • Yakup KutluEmail author
  • Apdullah Yayık
  • Esen Yildirim
  • Serdar Yildirim
Original Article

Abstract

Electroencephalography (EEG) has been used as a promising tool for investigation of brain activity during cognitive processes. The aim of this study is to reveal whether EEG signals can be used for classifying cognitive processes: arithmetic tasks and text reading. A recently introduced EEG database, which is constructed from 18 healthy subjects during a slide show including 60 slides of simple arithmetic tasks and easily readable texts, is used for this purpose. Multi-order difference plot-based time-domain attributes, number of values in specified regions after scattering the sequential difference values with several degrees, are extracted. For classification, improved extreme learning machine (ELM) scheme, namely luELM, by the use of lower–upper triangularization method instead of singular value decomposition which has disadvantages when used with huge data is proposed. As a result, higher accuracy results are achieved with reduced training time for proposed luELM classifier than traditional ELM classifier for both subject-dependent and subject-independent analysis.

Keywords

Cognitive processes Lower–upper triangularization Extreme learning machine MoDP method Optimized nodes 

Notes

Acknowledgements

The authors are very grateful to Mr. Server Göksel Eraldemir for his efforts to construct the EEG-MaTeP database.

Compliance with ethical standards

Conflicts of interest

The authors declare that there is no conflict of interest.

References

  1. 1.
    Baretta L, Tomitch LMB, MacNair N, Lim VK, Waldie KE (2009) Inference making while reading narrative and expository texts: An ERP study. Psychol Neurosci 2(2):137CrossRefGoogle Scholar
  2. 2.
    Bunch JR, Hopcroft JE (1974) Triangular factorization and inversion by fast matrix multiplication. Math Comput 28(125):231–236MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Duda RO, Hart PE, Stork DG (2001) Pattern classification. 2nd edition. A Wiley-Interscience publicationGoogle Scholar
  4. 4.
    Eberhard-Moscicka AK, Jost LB, Raith M, Maurer U (2015) Neurocognitive mechanisms of learning to read: print tuning in beginning readers related to word-reading fluency and semantics but not phonology. Dev Sci 18(1):106–118CrossRefGoogle Scholar
  5. 5.
    Eraldemir SG (2014) Analysis of EEG signals during text reading and mathematical processingGoogle Scholar
  6. 6.
    Eraldemir SG, Yildirim E (2014) Classification of simple text reading and mathematical tasks from EEG. In: Signal processing and communications applications conference (SIU). IEEE, pp 180–183Google Scholar
  7. 7.
    Eraldemir SG, Yıldırım E, Kutlu Y (2014) Classification of mathematical tasks from EEG signals using k-NN algorithm. In: Elektrik Elektronik Bilgisayar ve Biyomedikal Mhendislii Sempozyumu (Eleco 2014), Bursa, Turkey. pp 551–554Google Scholar
  8. 8.
    Eraldemir SG Yıldırım E, Yıldırım S, Kutlu Y (2014) Kognitif EEG isaretleri icin oznitelik secimi tabanli kanal secimi ve siniflandirma. In: Akilli Sistemlerde Yenilikler ve Uygulamalari Sempozyumu (ASYU). Izmir, TurkeyGoogle Scholar
  9. 9.
    Galán FC, Beal CR (2012) EEG estimates of engagement and cognitive workload predict math problem solving outcomes. In: User modeling, adaptation, and personalization. Springer, pp 51–62Google Scholar
  10. 10.
    Golub GH, Reinsch C (1970) Singular value decomposition and least squares solutions. Numer Math 14(5):403–420MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Golub GH, Van Loan CF (2012) Matrix computations. 4th edition. JHU Press, BaltimorezbMATHGoogle Scholar
  12. 12.
    Gundel A, Wilson GF (1992) Topographical changes in the ongoing EEG related to the difficulty of mental tasks. Brain Topogr 5(1):17–25CrossRefGoogle Scholar
  13. 13.
    Hall MA (1999) Correlation-based feature selection for machine learning. Ph.D. thesis, The University of WaikatoGoogle Scholar
  14. 14.
    Horata P, Chiewchanwattana S, Sunat K (2013) Robust extreme learning machine. Neurocomputing 102:31–44CrossRefGoogle Scholar
  15. 15.
    Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501. doi: 10.1016/j.neucom.2005.12.126 CrossRefGoogle Scholar
  16. 16.
    Krogh A, Vedelsby J et al (1995) Neural network ensembles, cross validation, and active learning. Adv Neural Inf Process Syst 7:231–238Google Scholar
  17. 17.
    Kutlu Y, Yayik A, Yildirim E, Yildirim S (2015) Orthogonal extreme learning machine based P300 visual event-related BCI. In: Neural information processing. Springer, pp 284–291Google Scholar
  18. 18.
    Liang NY, Huang GB, Saratchandran P, Sundararajan N (2006) A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Trans Neural Netw 17(6):1411–1423CrossRefGoogle Scholar
  19. 19.
    Lin CL, Jung M, Wu YC, Lin CT, She HC (2012) Brain dynamics of mathematical problem solving. In: Engineering in Medicine and Biology Society (EMBC), 2012 annual international conference of the IEEE. IEEE, pp 4768–4771Google Scholar
  20. 20.
    Meyer CD (2000) Matrix analysis and applied linear algebra. Siam publicationGoogle Scholar
  21. 21.
    Osaka M (1984) Peak alpha frequency of EEG during a mental task: task difficulty and hemispheric differences. Psychophysiology 21(1):101–105CrossRefGoogle Scholar
  22. 22.
    Pachori RB, Hewson D, Snoussi H, Duchêne J (2009) Postural time-series analysis using empirical mode decomposition and second-order difference plots. In: IEEE international conference on acoustics, speech and signal processing, 2009. ICASSP 2009. IEEE, pp 537–540Google Scholar
  23. 23.
    Pachori RB, Patidar S (2014) Epileptic seizure classification in EEG signals using second-order difference plot of intrinsic mode functions. Comput Methods Programs Biomed 113(2):494–502. doi: 10.1016/j.cmpb.2013.11.014 CrossRefGoogle Scholar
  24. 24.
    Ramsden S, Richardson FM, Josse G, Shakeshaft C, Seghier ML, Price CJ (2013) The influence of reading ability on subsequent changes in verbal IQ in the teenage years. Dev Cogn Neurosci 6:30–39CrossRefGoogle Scholar
  25. 25.
    Regression AA (1972) The Moore–Penrose pseudoinverse. Academic, New-YorkGoogle Scholar
  26. 26.
    Rosazza C, Cai Q, Minati L, Paulignan Y, Nazir TA (2009) Early involvement of dorsal and ventral pathways in visual word recognition: an ERP study. Brain Res 1272:32–44CrossRefGoogle Scholar
  27. 27.
    Thuraisingham R (2010) A classification system to detect congestive heart failure using second-order difference plot of RR intervals. Cardiol Res Pract. doi: 10.4061/2009/807379 Google Scholar
  28. 28.
    Thuraisingham RA (2009) A classification system to detect congestive heart failure using second-order difference plot of RR intervals. Cardiol Res Pract 2009:1–8CrossRefGoogle Scholar
  29. 29.
    Tzeng J (2013) Split-and-combine singular value decomposition for large-scale matrix. J Appl Math. doi: 10.1155/2013/683053 MathSciNetzbMATHGoogle Scholar
  30. 30.
    Yayık A, Kutlu Y (2011) Diagnosis of congestive heart failure using poincare map plot. In: Signal process and communication conferenceGoogle Scholar
  31. 31.
    Yayık A, Kutlu Y, Yıldırım E (2014) Epileptic state detection: pre-ictal, inter-ictal, post-ictal. In: International conference on advanced technology and sciencesGoogle Scholar
  32. 32.
    Zhu QY, Qin AK, Suganthan PN, Huang GB (2005) Evolutionary extreme learning machine. Pattern Recogn 38(10):1759–1763CrossRefzbMATHGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2017

Authors and Affiliations

  • Yakup Kutlu
    • 1
    Email author
  • Apdullah Yayık
    • 2
  • Esen Yildirim
    • 3
  • Serdar Yildirim
    • 4
  1. 1.Department of Computer Engineeringİskenderun Technical UniversityHatayTurkey
  2. 2.Alparslan Defence SciencesNational Defense UniversityAnkaraTurkey
  3. 3.Department of Electrical and Electronics EngineeringAdana Science and Technology UniversityAdanaTurkey
  4. 4.Department of Computer EngineeringAdana Science and Technology UniversityAdanaTurkey

Personalised recommendations