Classification of Distraction Levels Using Hybrid Deep Neural Networks From EEG Signals

TL;DR

This study demonstrates the feasibility of classifying pilot distraction levels using hybrid deep neural networks applied to EEG signals, achieving high accuracy in a simulated flight environment, which is crucial for safety in aviation and autonomous systems.

Contribution

First to classify distraction levels in pilots during flight simulation using deep learning on EEG data, advancing safety monitoring in aviation.

Findings

Achieved 84.37% accuracy in classifying distraction levels.

First application of deep learning for pilot distraction detection in flight simulation.

Potential for integration into autonomous flight safety systems.

Abstract

Non-invasive brain-computer interface technology has been developed for detecting human mental states with high performances. Detection of the pilots' mental states is particularly critical because their abnormal mental states could cause catastrophic accidents. In this study, we presented the feasibility of classifying distraction levels (namely, normal state, low distraction, and high distraction) by applying the deep learning method. To the best of our knowledge, this study is the first attempt to classify distraction levels under a flight environment. We proposed a model for classifying distraction levels. A total of ten pilots conducted the experiment in a simulated flight environment. The grand-average accuracy was 0.8437 for classifying distraction levels across all subjects. Hence, we believe that it will contribute significantly to autonomous driving or flight based on artificial intelligence technology in the future.