Analysis of behavioural curves to classify iris images under the influence of alcohol, drugs, and sleepiness conditions

Causa, Leonardo; Tapia, Juan E.; Valenzuela, Andres; Benalcazar, Daniel; Droguett, Enrique Lopez; Busch, Christoph

Abstract

This paper proposes a new method to estimate behavioural curves from Near-Infra-Red (NIR) iris images for classifying Fitness for Duty using a biometric capture device. Fitness for Duty (FFD) techniques detect whether a subject is Fit to safely perform a given task, which means no reduced alertness condition and security, or the subject is unfit, that could impact a reduced alertness condition by sleepiness or consumption of alcohol and drugs. The analysis showed essential differences in pupil and iris behaviour to classify the workers in "Fit"or "Unfit"conditions. The best results can distinguish subjects robustly under alcohol, drug consumption, and sleep conditions. The Multi-Layer-Perceptron and Gradient Boosted Machine reached the best results in all groups with an overall accuracy for Fit and Unfit classes of 74.0% and 75.5%, respectively. These results open a new application for iris capture devices.

Más información

Título según WOS: Analysis of behavioural curves to classify iris images under the influence of alcohol, drugs, and sleepiness conditions
Título de la Revista: EXPERT SYSTEMS WITH APPLICATIONS
Volumen: 242
Editorial: PERGAMON-ELSEVIER SCIENCE LTD
Fecha de publicación: 2024
DOI:

10.1016/j.eswa.2023.122808

Notas: ISI