Efficient feature for the classification of eye movements using electrooculography signals

Abstract

Electrooculography (EOG) signal is widely and successfully used to detect activi-ties of human eye. The advantages of the EOG-based interface over other con-ventional interfaces have been presented in the last two decades; however, due to a lot of information in EOG signals, the extraction of useful features should be done before the classification task. In this study, an efficient feature extracted from two directional EOG signals, vertical and horizontal signals, has been pre-sented and evaluated. There are the maximum peak and valley amplitude values, the maximum peak and valley position values, and slope, which are derived from both vertical and horizontal signals. In the experiments, EOG signals obtained from five healthy subjects with ten directional eye movements were employed: up, down, right, left, up-right, up-left, down-right down-left clockwise and counter clockwise. The mean feature values and their standard deviations have been re-ported. The difference between the mean values of the proposed feature from dif-ferent eye movements can be clearly seen. Using the scatter plot, the differences in features can also be clearly observed. Results show that classification accu-racy can approach 100% with a simple distinction feature rule. The proposed features can be useful for various advanced human-computer interface applica-tions in future researches.