Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 15, 2026

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

MSESTA: Multi-scale evolving spatial-temporal attention for long-term traffic prediction.

Huaijin Ran¹, Haoyi Zhang²

¹Department of Intelligent Supply Chain, Xi'an Jiaotong-Liverpool University, Suzhou, 215123, China.

Neural Networks : the Official Journal of the International Neural Network Society

|July 13, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Myeloid-derived suppressor cells in colorectal cancer: mechanisms of immunosuppression, therapy resistance and therapeutic targeting.

Frontiers in cell and developmental biology·2026

Same author

Contrast Echocardiography in the Multimodal Diagnosis of a Giant Primary Cardiac Angiosarcoma: A Case Report.

Journal of clinical ultrasound : JCU·2026

Same author

PM2.5 Exacerbates Viral Myocarditis by Disrupting Lysophosphatidylcholine Metabolism and Inhibiting the GPR4/ERK/PPARγ Pathway.

Journal of applied toxicology : JAT·2026

Same author

Benchmark-Driven Clinical Decision Framework for Multi-Class Middle Ear Disease Diagnosis: Superiority of Swin Transformer in Accuracy and Stability.

Diagnostics (Basel, Switzerland)·2026

Same author

Urolithin A Attenuates Sleep Deprivation-Induced Neutrophilic Inflammation by Suppression of the ROS-H3K18la Feedback Loop.

Journal of agricultural and food chemistry·2026

Same author

Staphylococcus aureus escapes endosomes and autophagosomes via α-hemolysin.

International immunopharmacology·2025

Accurate long-term traffic prediction is now more achievable with the novel Multi-Scale Evolving Spatial Temporal Attention (MSESTA) network. This model enhances prediction accuracy and efficiency for intelligent transportation systems.

Area of Science:

Intelligent Transportation Systems
Traffic Prediction
Deep Learning

Background:

Accurate long-term traffic prediction is vital for Intelligent Transportation Systems (ITS).
Existing methods excel at short-term prediction but struggle with long-term horizons due to computational and modeling challenges.
Long-term spatial-temporal dynamics in traffic data remain difficult to capture effectively.

Purpose of the Study:

To propose a novel network, the Multi-Scale Evolving Spatial Temporal Attention (MSESTA) network.
To enhance the capacity for learning long-term spatial-temporal dependencies in traffic data.
To improve computational efficiency for long-term traffic forecasting.

Main Methods:

Partitioning traffic data into multi-scale sequences to capture latent representations.

Keywords:

Evolving spatial-temporal attention Intelligent transportation systems Long-term prediction Multi-scale modeling Traffic prediction

More Related Videos

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Published on: April 4, 2025

Related Experiment Videos

Last Updated: Jul 15, 2026

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

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Published on: April 4, 2025

Designing an evolving spatial-temporal attention mechanism with linear complexity (summarization, aggregation, broadcasting).

Implementing a global spatial information aggregation strategy to integrate prior spatial knowledge.

Main Results:

MSESTA demonstrates significant improvements in prediction accuracy on four real-world traffic datasets.
The proposed network achieves enhanced computational efficiency for long-term forecasting.
The cross-scale evolution mechanism effectively models global spatial-temporal patterns.

Conclusions:

MSESTA effectively addresses the challenges of long-term traffic prediction.
The network offers a promising solution for improving the planning and scheduling of Intelligent Transportation Systems.
Future work will involve releasing the code for broader application and research.