Nonlinear eye movement detection method for drowsiness studies.

Automatic long-term vigilance analysis systems require information about the occurrence and type of eye movements, in addition to information about other physiological signals. This paper presents a method to detect different types of eye movements in ambulatory recordings. The method is based on the application of a weighted FIR-median-hybrid filter in the preprocessing of the signal and on the novel use of linear correlation between two EOG signals which are obtained using a new, improved electrode montage. The evaluation of the method showed that it performed well in detecting isolated unambiguous eye movements, but differences were observed in comparison to visual scoring in borderline cases. The method was found to be suitable for use as part of a signal analysis system for drowsiness studies.