Real-time Drowsiness Detection and Emergency Parking using EEG

Asim Javed, Muhammad Umair Arshad, Ehtesham Saeed, Noman Naseer

Abstract

This paper presents a comprehensive method to prepare a highly accurate and efficient classification model to detect drivers drowsiness and a parking system for parking the car along the emergency lane. Vehicle accidents are rapidly increasing in many countries. One of the most demanding technologies for the active prevention of such fatal road accidents are drowsiness monitoring systems since drowsiness is the leading cause of severe road accidents on motorways and highways. EEG is direct and effective, it directly measures the change in the brain’s electrical activity compared to techniques of image processing, which are indirect in approach. The EEG signals, recorded from ten healthy subjects under the state of drowsiness playing a car simulator and were given the feel like they were driving a car. As a proof of concept, a scaled car based on computer vision would shift to autonomous mode on detection of the drowsy state of the driver. The EEG system detects drowsiness with an accuracy of 96.8%. The autonomous system is also able to process 50-60 frames per second and gives decision accordingly. The turning angle for the scaled autonomous car ranges between 0 to 30 degrees.

Download


Paper Citation


in Harvard Style

Javed A., Arshad M., Saeed E. and Naseer N. (2020). Real-time Drowsiness Detection and Emergency Parking using EEG.In Proceedings of the International Conference on Health Informatics, Medical, Biological Engineering, and Pharmaceutical - Volume 1: HIMBEP, ISBN 978-989-758-500-5, pages 308-316. DOI: 10.5220/0010370703080316


in Bibtex Style

@conference{himbep20,
author={Asim Javed and Muhammad Umair Arshad and Ehtesham Saeed and Noman Naseer},
title={Real-time Drowsiness Detection and Emergency Parking using EEG},
booktitle={Proceedings of the International Conference on Health Informatics, Medical, Biological Engineering, and Pharmaceutical - Volume 1: HIMBEP,},
year={2020},
pages={308-316},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010370703080316},
isbn={978-989-758-500-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the International Conference on Health Informatics, Medical, Biological Engineering, and Pharmaceutical - Volume 1: HIMBEP,
TI - Real-time Drowsiness Detection and Emergency Parking using EEG
SN - 978-989-758-500-5
AU - Javed A.
AU - Arshad M.
AU - Saeed E.
AU - Naseer N.
PY - 2020
SP - 308
EP - 316
DO - 10.5220/0010370703080316