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

相关实验视频

Updated: Sep 16, 2025

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street
14:55

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street

Published on: January 20, 2023

3.5K

基于CNNBLSTM算法的短期流量预测方法的应用效应.

Guozhu Sui1, Meixia Song1, Ke Bian1

  • 1School of Traffic and Electrical Engineering, Dalian University of Science and Technology, Dalian, China.

PloS one
|July 7, 2025
PubMed
概括
此摘要是机器生成的。

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

Antioxidant Nanozymes: From Rational Design to Biomedical Applications.

Research (Washington, D.C.)·2026
Same author

The feasibility of ovarian tissue cryopreservation in selected females after hematopoietic stem cell transplantation.

Bone marrow transplantation·2026
Same author

Nanoporous-based biomaterials in biomedical applications: from fundamentals and biosensing to drug delivery, wound healing, and tissue engineering.

Nanoscale advances·2026
Same author

Molecular mechanism of hidden matrix-bound deoxynivalenol binding to proteins in wheat.

Food chemistry·2026
Same author

Long-term assessment of nutrient-induced eutrophication in Xiamen Bay: Implications for integrated watershed-coast management.

Marine environmental research·2026
Same author

Helicase A determines the transcription program of T<sub>H</sub>17 lineage differentiation and autoimmunity.

Science advances·2026

这项研究引入了一种改进的深度学习模型,用于准确的短期流量预测. 改进的算法显著提高了预测精度和融合速度,为交通管理提供了强大的解决方案.

科学领域:

  • 人工智能的人工智能
  • 运输工程 运输工程
  • 数据科学数据科学数据科学

背景情况:

  • 传统的流量预测算法与时空动态作斗争,导致精度降低.
  • 准确的短期交通流量预测对于有效的交通管理和规划至关重要.

研究的目的:

  • 开发一种先进的短期交通流量预测方法.
  • 通过使用深度学习技术,提高预测准确性和模型融合速度.

主要方法:

  • 数据预处理涉及识别,修复和分解异常流量数据,使用平滑估计值和自适应噪声集成实证模式分解.
  • 提出了一个混合深度学习模型,结合了改进的卷积神经网络 (CNN) 和双向长短期记忆 (BiLSTM) 算法.
  • 集成了增强的Adam和Lookahead优化算法,以提高模型性能.

主要成果:

  • 拟议的方法显示了更快的收率和显著降低的培训和验证损失值.
  • 培训损失从0.0250下降到0.0021,验证损失从0.0010下降到0.0008.
  • 与传统的CNN-BiLSTM模型相比,该模型实现了更高的预测准确度,平均绝对百分比误差为0.233,根平均平方误差为23.87.

结论:

更多相关视频

Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

13.7K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K

相关实验视频

Last Updated: Sep 16, 2025

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street
14:55

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street

Published on: January 20, 2023

3.5K
Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

13.7K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K
  • 开发的算法有效且准确地预测短期的流量.
  • 增强的深度学习方法为智能运输系统和交通管理决策提供了可靠的基础.
  • 该研究强调了将CNN,BiLSTM和高级优化技术集成到复杂的时间序列预测任务中的潜力.