• DocumentCode
    113928
  • Title

    Electrooculogram based cognitive context recognition

  • Author

    Datta, Soupayan ; Banerjee, Adrish ; Konar, Amit ; Tibarewala, D.N.

  • Author_Institution
    Dept. of Electron. & Telecommun. Eng., Jadavpur Univ., Kolkata, India
  • fYear
    2014
  • fDate
    16-17 Jan. 2014
  • Firstpage
    1
  • Lastpage
    4
  • Abstract
    Recognition of cognitive context is an important aspect of context aware pervasive computing systems. The present work is aimed at identification of cognitive contexts of human beings from the analysis of their eye movements by acquiring Electrooculogram signals. These signals are represented through Adaptive Autoregressive Parameters, Hjorth Parameters and Wavelet Coefficients as signal features. Classification of the obtained feature spaces is carried out using Support Vector Machine with Radial Basis Function Kernel to distinctly identify a particular class of activity defining a person´s cognitive context, achieving an average recognition accuracy of 91.825% for eight types of cognitive activities.
  • Keywords
    autoregressive processes; biomechanics; cognition; electro-oculography; feature extraction; medical signal detection; medical signal processing; radial basis function networks; signal classification; support vector machines; ubiquitous computing; Hjorth parameters; adaptive autoregressive parameters; average recognition accuracy; context aware pervasive computing systems; electrooculogram based cognitive context recognition; electrooculogram signal acquisition; eye movements; feature space classification; human beings; person cognitive context; radial basis function kernel; signal features; support vector machine; wavelet coefficients; Adaptation models; Analytical models; Computational modeling; Context; Games; Optical sensors; Writing; Adaptive Autoregressive Parameters; Cognitive Context Recognition; Electrooculogram; Hjorth Parameters; Support Vector Machine; Wavelet Transform;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Electronics, Communication and Instrumentation (ICECI), 2014 International Conference on
  • Conference_Location
    Kolkata
  • Print_ISBN
    978-1-4799-3982-4
  • Type

    conf

  • DOI
    10.1109/ICECI.2014.6767362
  • Filename
    6767362