Context aware ubiquitous computing systems are capable of assisting people by sensing human cognitive context. In this work, visual memory recall of human beings is identified by analysing their eye movements. Electrooculogram signals, potential difference produced in the surrounding region of eye socket for eye ball movement, are recorded to collect eye movement data. Electrooculogram signals while viewing ‘repeated’ and ‘non-repeated’ visual stimuli were classified for ‘with’ and ‘without’ audio cue sections. Adaptive autoregressive parameters, power spectral density, Hjorth parameters and wavelet coefficients are extracted from these signals as features. A combined feature space is formed comprising all four signal features. A maximum accuracy of 88.70% is obtained on an average over five participating subjects using SVM-RBF classifier for ‘without audio’ visual memory recall. From this study, it is evident that this auditory effect leaves an impact on EOG signal patterns so that to make reduction in the recognition performance.
CITATION STYLE
Banerjee, A., Dey, A., Datta, S., & Tibarewala, D. N. (2015). Effect of audio cue on electrooculogram-based eye movement analysis of visual memory recall. In Lecture Notes in Electrical Engineering (Vol. 335, pp. 471–477). Springer Verlag. https://doi.org/10.1007/978-81-322-2274-3_52
Mendeley helps you to discover research relevant for your work.