Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

High mobility group box 1 (HMGB1) levels in the placenta and in serum in preeclampsia.

American journal of reproductive immunology (New York, N.Y. : 1989)·2011

Same author

Destabilization of coxsackievirus b3 genome integrated with enhanced green fluorescent protein gene.

Intervirology·2011

Same author

[Clinicopathological features of primary splenic histiocytic sarcoma: a case report and literature review].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2011

Same author

[Comparison of treatment with micro endoscopic discectomy and posterior lumbar interbody fusion using single and double B-Twin expandable spinal spacer].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2011

Same author

Virtual transplantation in designing a facial prosthesis for extensive maxillofacial defects that cross the facial midline using computer-assisted technology.

The International journal of prosthodontics·2011

Same author

Total synthesis of phorboxazole A via de novo oxazole formation: convergent total synthesis.

Journal of the American Chemical Society·2010

Search research articles

Related Experiment Video

Updated: Jul 31, 2025

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

Driver identification and fatigue detection algorithm based on deep learning.

Yuhua Ma¹, Ye Tao¹, Yuandan Gong¹

¹School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan, China.

Mathematical Biosciences and Engineering : MBE

|May 10, 2023

Summary

This study introduces an improved deep learning algorithm for driver fatigue detection, enhancing accuracy and efficiency in identifying drowsiness, yawning, and phone use. The new model significantly reduces parameters while boosting performance for safer driving.

Keywords:

SSD algorithm driving behavior driving state facial identification fatigue detection

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Related Experiment Videos

Last Updated: Jul 31, 2025

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Area of Science:

Computer Science
Artificial Intelligence
Transportation Safety

Background:

Traffic accidents are often caused by driver fatigue, smoking, and phone use.
Existing driver fatigue detection algorithms have limitations in accuracy and efficiency.
A robust system is needed to identify and mitigate risky driver behaviors.

Purpose of the Study:

To design an effective deep learning-based driver fatigue detection algorithm.
To improve upon the Single Shot MultiBox Detector (SSD) for enhanced driver monitoring.
To integrate detection of smoking and phone use alongside fatigue indicators.

Main Methods:

Utilized a face recognition module with Facenet for driver identification and feature extraction.
Developed a novel deep learning algorithm based on the SSD framework, incorporating reverse residual ideas.
Redesigned the SSD's network structure, including FPN and SE networks, and adjusted prior boxes.

Main Results:

Reduced model parameters from 96.62 MB to 18.24 MB.
Increased average accuracy from 89.88% to 95.69%.
Improved recall rates for closed eyes (46.69% to 65.87%), yawning (59.72% to 82.72%), and smoking (65.87% to 83.09%).
Enhanced frames per second from 51.69 to 71.86, indicating increased processing speed.

Conclusions:

The improved deep learning model demonstrates superior feature extraction capabilities, especially for small targets.
The algorithm effectively identifies driver fatigue, smoking, and phone use, contributing to enhanced road safety.
The optimized model offers a practical and efficient solution for real-time driver monitoring systems.