Towards Obviating Human Errors in Real-time through Eye Tracking

To minimize human errors (principal reasons for accidents in process industries) it is imperative to understand their cognitive workload, the excess of which is often a preliminary state leading to human errors. In this work, we have devised a methodology based on an eye tracking parameter—gaze entropy—to gauge the variation of cognitive work load on a control room operator. The study highlights the potential of gaze entropy in observing the variation of cognitive workload with learning. The patterns observed have a potential to minimize human errors and improve safety in process industries.