Affiliation:
1. SASTRA University (Deemed), India
Abstract
According to the reports from the World Health Organization (WHO), one of the primary causes that led to death in the world was road accidents. Every year, numerous road accidents are caused by drivers due to their drowsiness. It can be minimized by alerting the driver, and it has been done by identifying and recognizing the initial stages of drowsiness. Several models have been proposed to detect drivers' drowsiness and alert them before a road accident occurs. However, the most prominent one is VGG16 with a transfer learning mechanism that is utilized to view the status of the respective regions of interest. By utilizing these models, the drivers are monitored, and alarms are generated to alert the drivers as well as the passengers. This experimental analysis was carried out on the Kaggle Yawn-Eye-Dataset (KYED), and the results showed the low computational intricacy and high precision of the eye closure estimation and the ability of the proposed system for drowsiness detection.
Reference25 articles.
1. Papaya maturity Classification Using Deep Convolutional.;M. M.Al-Masawabe;Neural Networks,2022
2. Al-sudani, A. R. (2020). Yawn based driver fatigue level prediction. Proceedings of 35th International Confer, 69, 372-382.
3. A customized deep learning algorithm for drowsiness detection using single-channel EEG signal;J. P.Allam;Artificial Intelligence-Based Brain-Computer Interface,2022
4. Automatic driver sleepiness detection using EEG, EOG and contextual information
5. Convolutional Neural Network for Drowsiness Detection Using EEG Signals
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献