Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

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

Effect of various interventions on relieving non-coring needle puncture-related pain in patients with totally implantable venous access port: a network meta-analysis of randomized control trials.

Frontiers in surgery·2026
Same author

MM-TransUNet: Multi-modal and multi-graph feature learning for neurodevelopmental disorder diagnosis.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Rethinking Skeleton-Based Action Recognition From Action-Class Prediction Distribution Perspective.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Association between dietary fat intake and fatty acid profiles and hyperuricemia among Chinese adults: Results from the China Health and Nutrition Survey.

Asia Pacific journal of clinical nutrition·2026
Same author

Integrated bioinformatics and mendelian randomization reveal a six-gene diagnostic signature and key role of CYP26B1 in sarcopenia.

Frontiers in molecular biosciences·2026
Same author

Targeting mitochondrial quality control: Ginsenoside Rg1 as a therapeutic candidate for neuromuscular diseases.

Journal of ginseng research·2026

相关实验视频

Updated: Jul 19, 2025

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

840

使用多尺度一维卷积神经网络检测缓慢的眼动,以检测驾驶员的嗜睡.

Yingying Jiao1, Xiujin He1, Zhuqing Jiao1

  • 1Center for Brain-like Computing and Machine Intelligence, Department of Computer Science and Engineering, Shanghai Jiao Tong University, 800 Dong Chuan Road, Shanghai 200240, China.

Journal of neuroscience methods
|August 14, 2023
PubMed
概括

一个新的多尺度一维卷积神经网络 (MS-1D-CNN) 准确地检测缓慢的眼动 (SEM),表明驾驶员入睡. 这种人工智能模型显著提高了分类准确性,为增强的驾驶员安全系统铺平了道路.

关键词:
司机疲劳导致的疲劳司机昏昏欲睡,可能导致司机昏昏欲睡.电光眼图 (EOG) 是指电光眼图 (EOG) 的一个形式.一维卷积神经网络 (1D-CNN)睡眠开始的时间 睡眠开始的时间缓慢的眼睛运动 缓慢的眼睛运动

更多相关视频

Eye-Tracking Control to Assess Cognitive Functions in Patients with Amyotrophic Lateral Sclerosis
07:00

Eye-Tracking Control to Assess Cognitive Functions in Patients with Amyotrophic Lateral Sclerosis

Published on: October 13, 2016

8.2K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

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

Published on: December 15, 2023

3.8K

相关实验视频

Last Updated: Jul 19, 2025

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

840
Eye-Tracking Control to Assess Cognitive Functions in Patients with Amyotrophic Lateral Sclerosis
07:00

Eye-Tracking Control to Assess Cognitive Functions in Patients with Amyotrophic Lateral Sclerosis

Published on: October 13, 2016

8.2K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

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

Published on: December 15, 2023

3.8K

科学领域:

  • 人工智能的人工智能
  • 机器学习 机器学习
  • 生物医学信号处理

背景情况:

  • 缓慢的眼动 (SEM) 是驾驶员在模拟驾驶过程中入睡的关键指标.
  • 精确检测SEM对于开发先进的驾驶员嗜睡检测系统至关重要.

研究的目的:

  • 提出一种新的多尺度一维卷积神经网络 (MS-1D-CNN) 用于对SEM波形进行分类.
  • 评估MS-1D-CNN模型在检测司机入睡时的有效性.

主要方法:

  • 开发了一个MS-1D-CNN模型,该模型利用多个下方采样分支和本地卷积层从SEM信号中提取多个尺度的特征.
  • 在标准列车测试和连续数据集上使用主体对主体和离开一个主体的交叉验证来评估模型的性能.
  • 将MS-1D-CNN的性能与使用手工设计特征的基线方法进行了比较.

主要成果:

  • 在标准数据集上达到高分类准确率,约为99.1%和98.6%,在连续数据集上分别为99.3%和99.2%.
  • 与基线方法相比,表现出优异的性能,平均精度提高了3.5%.
  • 该MS-1D-CNN模型表现出强的性能,即使在离开一个主体的交叉验证场景中.

结论:

  • 在MS-1D-CNN模型中的多尺度特征提取显著提高了SEM检测的分类准确性.
  • 拟议的MS-1D-CNN模型为检测驾驶员昏昏欲睡提供了一个高度有效和可靠的解决方案.
  • 这项技术在驾驶员安全监控系统中具有强大的实际应用潜力.