Can Foundation Models Predict Fitness for Duty?

TL;DR

This paper explores using deep learning and foundational models to predict fitness for duty by analyzing biometric iris images, addressing data scarcity challenges and leveraging self-supervised model generalization.

Contribution

It investigates the application of foundational models for fitness for duty prediction, highlighting their potential to overcome data limitations in biometric alertness assessment.

Findings

Deep learning models can predict alertness from iris images.

Self-supervised foundational models improve generalization.

Potential for real-world alertness monitoring systems.

Abstract

Biometric capture devices have been utilised to estimate a person's alertness through near-infrared iris images, expanding their use beyond just biometric recognition. However, capturing a substantial number of corresponding images related to alcohol consumption, drug use, and sleep deprivation to create a dataset for training an AI model presents a significant challenge. Typically, a large quantity of images is required to effectively implement a deep learning approach. Currently, training downstream models with a huge number of images based on foundational models provides a real opportunity to enhance this area, thanks to the generalisation capabilities of self-supervised models. This work examines the application of deep learning and foundational models in predicting fitness for duty, which is defined as the subject condition related to determining the alertness for work.