Alertness prediction system and method
An alertness prediction bio-mathematical model for use in devices such as a wearable device that improves upon previous models of predicting fatigue and alertness by gathering data from the individual being monitored to create a more accurate estimation of alertness levels. The bio-mathematical model may be a two-process algorithm which incorporates a sleep-wake homeostasis aspect and a circadian rhythm aspect. The sleep-wake homeostasis aspect of the model is improved by using actigraphy measures in conjunction with distal skin, ambient light and heart rate measures to improve the accuracy of the sleep and wake estimations. The circadian rhythm model aspect improves fatigue prediction and estimation by using distal skin, heart rate and actigraphy data. The sleep-wake homeostasis and circadian rhythm aspects may also be combined with additional objective and subjective measures as well as information from a user to improve the accuracy of the alertness estimation even further.
1. A device for monitoring and predicting alertness of an individual, the device comprising:
one or more sensors configured to obtain information signals about the individual, the sensors comprising at least one of:
a motion sensor configured to produce movement data or body position data of the individual,
a temperature sensor configured to produce distal skin temperature data of the individual, and
a heart rate monitor configured to produce heart rate data of the individual;
a memory configured to store:
a default circadian rhythm configured to be refined with data derived from the information signals about the individual to generate an estimated circadian rhythm for the individual, and
a bio-mathematical model configured to generate a fatigue score for the individual;
a processor coupled to the one or more sensors and to the memory, configured to:
receive the information signals about the individual,
estimate a circadian rhythm of the individual by incorporating the information signals about the individual to refine the default circadian rhythm,
extract features from the information signals about the individual and the estimated circadian rhythm,
extract at least one coefficient from the extracted features using at least one pattern recognition algorithm or machine learning algorithm,
apply the bio-mathematical model to the at least one extracted coefficient, and
generate the fatigue score for the individual from the at least one extracted coefficient using the bio-mathematical model.