Abstract—An algorithm for the real time detection of human fatigue has been developed by using multiple fatigue parameters. In addition to existing metrics such as Blink rate and the PERCLOS, a third metric, the variation of head position and the tilt has been used in generating a cumulative measure of fatigue with non intrusive techniques of monitoring. The initial results obtained out of the simulation studies have been discussed in this paper with a stress on fatigue monitoring using variation in head position. The system was found to be sufficiently accurate and highly robust in prediction of fatigue under test situations for fatigue monitoring.
—Fatigue monitoring, PERCLOS, algorithm.
Muhammad Jafar Ali is with the Department of Mechanical Engineering, National University of Singapore, Lower Kent Ridge Road, Singapore 119260 (e-mail: firstname.lastname@example.org, Tel: 85067178).
Suvra Sarkar, GNVA Pavan Kumar, and John-John Cabibihan are with the Department of Electrical and Computer Engineering, National University of Singapore, Lower Kent Ridge Road, Singapore 119260.
Cite: Muhammad Jafar Ali, Suvra Sarkar, GNVA Pavan Kumar, and John-John Cabibihan, "A Non Intrusive Human Fatigue Monitoring System," International Journal of Future Computer and Communication
vol. 1, no. 3, pp. 284-288, 2012.