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

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

Patient preferences for the integration of exercise for depression into mental health care.

Translational behavioral medicine·2026

Same author

Young Adults' Perspectives on an Ecological Momentary Intervention for Drinking to Cope: Qualitative Study.

JMIR formative research·2026

Same author

HIV-related Stigma and Alcohol Involvement Among People with HIV Who Engage in Unhealthy Drinking.

AIDS and behavior·2026

Same author

PARP Inhibitors as Radiosensitizers: Current Evidence and Future Directions.

Current oncology reports·2026

Same author

Sweet artificial intelligence as digital catalysts in infectious diseases: Glycomics and glycoanalysis.

Biosensors & bioelectronics·2026

Same author

Associations between daily pain severity and concurrent alcohol craving among women in early recovery following alcohol treatment.

Drug and alcohol dependence·2026

Search research articles

相关实验视频

Updated: Jul 6, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

用双线CNN进行细粒度中毒步态分类.

Ruojun Li^1,2, Emmanuel Agu³, Atifa Sarwar⁴

¹Department of Optical Information, Huazhong University of Science and Technology, Wuhan, China.

IEEE sensors journal

|January 8, 2024

概括

这项研究使用智能手机运动数据和双线卷积神经网络 (BiCNN) 来检测走路中的酒精中毒. 这种新的方法达到83.5%的准确性,提供一种被动的方式来减少醉酒驾驶事故.

关键词:

血液中的酒精含量 (BAC)卷积神经网络 (CNN) 是一种神经网络.步态分析步态分析神经网络的神经网络的神经网络

更多相关视频

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Published on: August 12, 2019

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

相关实验视频

Last Updated: Jul 6, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits

Published on: August 12, 2019

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

科学领域:

* 计算神经科学和机器学习应用.
* 生物医学工程和可穿戴传感器技术.
* 公共卫生和道路安全倡议.

背景情况:

* 过度饮酒会导致行动能力,判断力受损,以及每天因驾驶事故造成的重大伤害和死亡.
*对醉酒司机的被动检测方法可以实现及时警报,并减少驾驶醉酒 (DUI) 事件.
*智能手机拥有运动传感器和处理能力,适用于步态分析和机器学习模型部署.

研究的目的:

* 通过智能手机的步态数据提出一种用于检测酒精中毒的新方法.
*利用双线卷积神经网络 (BiCNN) 来分析加速度计和陀螺仪数据.
* 根据智能手机用户的步行模式来确定智能手机用户是否超过合法驾驶限制 (0.08 BAC).

主要方法:

*步行数据分为步骤,并转换为格拉米安角场 (GAF) 图像.
*利用BiCNN对GAF编码的步态数据进行细粒度图像分类.
* 实施全面的管道,包括步骤检测,数据规范化,融合,GAF生成和BiCNN分类.

主要成果:

* 拟议的BiCNN模型在分类醉酒者与清醒的用户方面实现了83.5%的准确性.
*该方法成功地区分了步行模式中的微妙差异,这表明了中毒.
*性能超越了以前通过步态分析检测中毒的先进方法.

结论:

* 这种新的方法有效地利用智能手机的运动传感器和BiCNN用于被动酒精中毒检测.
* 这种方法证明了使用日常道路安全设备的步态分析的可行性.
*这些发现为准时发出警报铺平了道路,以防止醉酒驾驶事故.