Federated Learning for Drowsiness Detection in Connected Vehicles

TL;DR

This paper introduces a federated learning framework for driver drowsiness detection in connected vehicles, achieving high accuracy while preserving privacy and demonstrating scalability across multiple vehicles.

Contribution

The paper presents a novel federated learning approach for driver drowsiness detection that maintains high accuracy and addresses privacy concerns in vehicular networks.

Findings

Achieved 99.2% accuracy in drowsiness detection

Demonstrated scalability with multiple federated clients

Preserved data privacy by avoiding central data collection

Abstract

Ensuring driver readiness poses challenges, yet driver monitoring systems can assist in determining the driver's state. By observing visual cues, such systems recognize various behaviors and associate them with specific conditions. For instance, yawning or eye blinking can indicate driver drowsiness. Consequently, an abundance of distributed data is generated for driver monitoring. Employing machine learning techniques, such as driver drowsiness detection, presents a potential solution. However, transmitting the data to a central machine for model training is impractical due to the large data size and privacy concerns. Conversely, training on a single vehicle would limit the available data and likely result in inferior performance. To address these issues, we propose a federated learning framework for drowsiness detection within a vehicular network, leveraging the YawDD dataset. Our approach achieves an accuracy of 99.2%, demonstrating its promise and comparability to conventional deep learning techniques. Lastly, we show how our model scales using various number of federated clients