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

Core-shell CuFeMnHCF@CuHCF: a high-rate and durable Prussian blue cathode for sodium-ion batteries.

Chemical communications (Cambridge, England)·2026

Same author

Injectable thermosensitive hydrogel embedding lignin-modified PLGA microspheres enables sustained lidocaine release and prolonged neuromodulation.

International journal of biological macromolecules·2026

Same author

Pharmacological Strategies for Preventing Postoperative Recurrence in Crohn's Disease: A Systematic Review and Network Meta-Analysis of Randomized Controlled Trials.

Medicina (Kaunas, Lithuania)·2026

Same author

Lactylation and targeted therapy resistance in hepatocellular carcinoma.

Clinical epigenetics·2026

Same author

Nano-geo interfaces in urinary stone formation: linking drinking water geochemistry to calcium oxalate crystallization dynamics.

Environmental geochemistry and health·2026

Same author

Clustering ensemble method integrating Gaussian mixture model and three-way decision (GMM-3WD-CE).

Scientific reports·2026

Search research articles

相关实验视频

Updated: May 13, 2025

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

用成本敏感的多图表注意力网络进行时空崩严重性分析.

Jianwu Wan¹, Siying Zhu², Yunpeng Ma¹

¹School of Information Science and Engineering, Hohai University, PR China.

Accident; analysis and prevention

|April 17, 2025

概括

本研究引入了一个成本敏感的多图表注意网络 (CSmGAT) 用于事故严重性分析. 新型模型通过优先考虑严重的碰撞因素和捕捉时空模式,显著减少了错误分类损失.

科学领域:

运输工程运输工程
数据科学数据科学数据科学
机器学习机器学习

背景情况:

传统的撞车严重性模型假设所有错误的损失均等,忽视了识别严重撞车因素的更大重要性.
现有的模型与时空异质性作斗争,经常使用更简单的统计或机器学习方法.

研究的目的:

将崩严重性分析重新定义为成本敏感的学习问题,将差异性成本分配给错误分类的错误.
开发一个先进的深度学习模型,准确地捕获时空撞击严重性结构.
提出一个新的成本敏感的多图表注意网络 (CSmGAT),以改进事故分析.

主要方法:

开发了一个成本矩阵来定义不平等的错误分类损失在事故严重性分析.
引入了基于图形卷积网络的多图的注意力机制,以建模时空异质性.
提出了CSmGAT模型,将成本敏感性和图表注意力集成在一起,以学习最佳的时空和空间崩关联.

主要成果:

与23个最先进的模型相比,CSmGAT模型至少减少了11.31%的总体错误分类损失.
在预定义的时空图中使用多图注意力卷曲有效过错误的归属.
使用伪弹性值识别和解释了重大事故导致的因素.

关键词:

注意力机制注意力机制具有成本敏感性的学习.崩严重程度分析分析.空间时间异质性空间时间异质性不平等的错误分类损失

更多相关视频

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

相关实验视频

Last Updated: May 13, 2025

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

结论:

通过解决成本敏感性和时空复杂性,CSmGAT模型为事故严重性分析提供了一种优越的方法.
对成本敏感的框架和图表注意力机制提高了事故导致因素识别的准确性和可解释性.
这项研究促进了深度学习在运输安全中的应用,通过提供对碰撞严重性的更细致的理解.