Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Narcolepsy

Narcolepsy

Narcolepsy is a chronic sleep disorder characterized by pervasive, uncontrolled sleepiness and other sleep disturbances. One of its hallmark symptoms is an abrupt transition to REM sleep upon falling asleep, which causes symptoms typically associated with this phase to occur unexpectedly during wakefulness. These include the following symptoms, which typically last from a minute or two to half an hour.

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

AURKA regulates LGR5 in response to Helicobacter Pylori infection by modulating its deubiquitination.

Cell death and differentiation·2026

Same author

Dynamic driver drowsiness detection with attention enhanced convolutional neural networks for real time monitoring and road safety applications.

Scientific reports·2026

Same author

A novel hybrid deep learning framework for customer churn prediction using RFM and embedding clustering.

Scientific reports·2026

Same author

Bipolar resection versus enucleation of the prostate in management of benign prostatic hyperplasia patients with large-sized prostates: a prospective randomized controlled clinical trial.

BMC urology·2026

Same author

Correction: Benchmarking GPT-5 in radiation oncology: measurable gains, but persistent need for expert oversight.

Frontiers in oncology·2026

Same author

Benchmarking GPT-5 in radiation oncology: measurable gains, but persistent need for expert oversight.

Frontiers in oncology·2025

Search research articles

相关实验视频

Updated: May 23, 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

使用变压器架构实时检测驾驶员的昏昏欲睡:一种新的深度学习方法.

Osama F Hassan¹, Ahmed F Ibrahim^2,3, Ahmed Gomaa^4,5

¹Information Systems Department, Faculty of Computers and Informatics, Suez Canal University, Ismailia, 41522, Egypt.

Scientific reports

|May 20, 2025

概括

这项研究引入了一个深度学习框架,用于使用变压器模型实时检测驾驶员的昏昏欲睡,达到99%以上的准确性. 该系统通过可靠地识别昏昏欲睡并及时触发警报来提高道路安全.

更多相关视频

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

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

相关实验视频

Last Updated: May 23, 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

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

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

科学领域:

计算机科学计算机科学
人工智能的人工智能
机器学习机器学习

背景情况:

司机昏昏欲睡是道路交通事故的主要原因之一,导致严重的社会和经济损失.
现有的嗜睡检测方法在现实条件下往往缺乏准确性和稳定性.

研究的目的:

开发一种新的,强大的深度学习框架,用于实时检测司机的昏昏欲睡.
利用最先进的变压器架构并转移学习以提高准确性和可靠性.

主要方法:

利用先进的数据预处理:图像规范化,增强和Haar Cascade来选择感兴趣的区域.
评估了视觉变压器 (ViT),Swin变压器以及各种转移学习模型 (VGG19,DenseNet169,ResNet50V2等). 在MRL眼睛数据集上.
集成的类激活映射 (CAM) 用于模型解释性和实时的昏昏欲睡得分与警报.

主要成果:

视觉变压器 (ViT) 和Swin变压器实现了高准确率,分别为99.15%和99.03%.
变压器模型在精度,回忆和F1分数方面表现优于其他评估模型.
该系统在各种数据集 (NTHU-DDD,CEW) 和具有挑战性的条件 (照明,眼镜) 中表现出强度.

结论:

基于变压器的深度学习架构为驾驶员昏昏欲睡的检测提供了重大进步.
拟议的无接触系统为提高道路安全提供了可靠和高效的解决方案.
该框架显示了在先进的驾驶辅助系统中广泛采用的潜力.