Scholarlink

<p>Driver drowsiness is a major cause of road accidents worldwide. In this paper, we propose a deep learning-based system for detecting driver drowsiness from facial images using a hybrid ensemble framework. The model incorporates multiple pre-trained convolutional neural networks (CNNs) for robust feature extraction. These features are selected using the Select-KBest method and further processed by multiple machine learning classifiers. The outputs are combined through ensemble learning to enhance prediction accuracy. The final classification categorizes drowsiness likelihood into different risk levels. Experimental results demonstrate the effectiveness of the proposed method in improving detection reliability and reducing false alarms.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Deep Ensemble Learning-Based Driver Drowsiness Detection System Using Real Time Facial Image Features

  • 期刊论文

  • 发表日期：

    2026年3月30日

查看全文
  • Sahadev Roy,
  • Arindam Mandal,
  • Md Faysal Kabir

摘要

Driver drowsiness is a major cause of road accidents worldwide. In this paper, we propose a deep learning-based system for detecting driver drowsiness from facial images using a hybrid ensemble framework. The model incorporates multiple pre-trained convolutional neural networks (CNNs) for robust feature extraction. These features are selected using the Select-KBest method and further processed by multiple machine learning classifiers. The outputs are combined through ensemble learning to enhance prediction accuracy. The final classification categorizes drowsiness likelihood into different risk levels. Experimental results demonstrate the effectiveness of the proposed method in improving detection reliability and reducing false alarms.