Abstract: A Fit-For-Duty network system and method that integrates several drowsiness detection devices with software analytics engine to more accurately predict, monitor and/or detect an actual unfit-for-duty condition or “positive event” in real time. The system monitors behavior based on changing operational conditions (such as speed of vehicle and pre-defined conditions, such as time of day and geographic conditions) to dynamically estimate both seriousness and probability of a positive event. Moreover, based on estimated seriousness and probability of a positive event the system self-initiates different levels of alerts ranging from light and sound, to connection to a third party intervener (an operations center), to stopping the vehicle.

Abstract: A Fit-For-Duty network system and method that integrates several drowsiness detection devices with software analytics engine to more accurately predict, monitor and/or detect an actual unfit-for-duty condition or “positive event” in real time. The system monitors behavior based on changing operational conditions (such as speed of vehicle and pre-defined conditions, such as time of day and geographic conditions) to dynamically estimate both seriousness and probability of a positive event. Moreover, based on estimated seriousness and probability of a positive event the system self-initiates different levels of alerts ranging from light and sound, to connection to a third party intervener (such as an operations center), to stopping the vehicle.