Accurate and efficient operatorfunctional state classification
and assessment based on physiological data have
many important applications ranging from operator
monitoring to interaction and control ofhuman/machine
systems, Eyeblink characteristics are frequently used as
physiological indicators for this purpose. In this paper,
we describe an efficient and robust eyeblink detection algorithm
based on nonlinear analysis ofthe electrooculogram
(EOG) signal. Theperformance ofthe algorithm was
evaluated via data analysis results ofseveral benchmark
test sets in comparison with another eyeblink detection
algorithm.