Electrooculogram based cognitive context recognition

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.