Fatigue Science launched Readi, a fatigue management information system that gives validated, personalized fatigue predictions for operators. The system, which does not use wearables, enables dispatchers and fleet safety managers to predict risks before putting drivers behind the wheel, the company said.

Readi uses data on each driver’s shift schedule, or from electronic logging device systems. Work hours are then paired with each driver’s metadata profile, which includes basic demographic data, such as height, weight, sex, age. The profile may include sleep habit data taken from an optional operator intake survey.

Readi’s machine learning algorithm compares these data to patterns in its growing database of over 4 million sleeps, recorded by workers using wearables. The algorithm estimates each driver’s sleep quantity, quality, and timing over the preceding 10 days. Sleep estimates are then processed by the SAFTE Biomathematical Fatigue Model, which constructs a prediction of each operator’s risk for each hour in the shift ahead.

The risk information is then sent to dispatchers, supervisors, and safety managers.

Readi uses incoming data from a global network of wearable devices deployed at sites around the world. Although wearables are not required, customers can seamlessly integrate them if desired. In trials, customers chose to give wearables to their highest-risk operators, who then get personal fatigue alerts sent to the wearables in advance of critical periods of fatigue.