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: Jan 10, 2026

Spatial Temporal Analysis of Fieldwise Flow in Microvasculature

Spatial Temporal Analysis of Fieldwise Flow in Microvasculature

Published on: November 18, 2019

Multi-scale Wavelet-Mamba framework for spatiotemporal traffic forecasting.

Wenhao Li¹, Jiale Song², Pengying Ouyang³

¹School of Transportation, Southeast University, Nanjing, 210096, China.

Scientific Reports

|November 29, 2025

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

Breaking the trade-off with ordered nanochannels for highly effective osmotic energy conversion.

Nanoscale·2026

Same author

Revealing Electronic Effect in Mesoporous Medium-Entropy Alloy for Promoting Electrocatalytic Upcycling of Polyethylene Terephthalate Plastic.

ACS nano·2026

Same author

Research progress on high-altitude hypoxia pulmonary injury: pathogenesis and Chinese herbal medicine for prevention and treatment.

Frontiers in pharmacology·2026

Same author

Effect of Transcutaneous Auricular Vagus Nerve Stimulation on Postoperative Cognitive Dysfunction in Older Patients: A Randomized Controlled Clinical Trial.

Neuromodulation : journal of the International Neuromodulation Society·2026

Same author

Identification and validation of KLRB1-related biomarkers in rheumatoid arthritis.

Scientific reports·2026

Same author

[Folic acid supplementation alleviates high-salt diet-induced renal fibrosis in mice].

Nan fang yi ke da xue xue bao = Journal of Southern Medical University·2026

This summary is machine-generated.

This study introduces WMF-Traffic, a novel framework for accurate network traffic prediction. It effectively captures multi-scale patterns and long-range dependencies, improving intelligent transportation resource management.

Area of Science:

Artificial Intelligence
Data Science
Transportation Engineering

Background:

Intelligent resource management in transportation relies on accurate network traffic prediction.
Existing methods face challenges in capturing multi-scale temporal patterns, long-range dependencies, and periodic behaviors efficiently.

Purpose of the Study:

To present WMF-Traffic, a novel framework for traffic forecasting.
To address limitations of current methods in handling complex temporal dynamics and computational efficiency.

Main Methods:

WMF-Traffic integrates Wavelet Decomposition, selective state space modeling (Mamba), and frequency domain processing (Fourier).
Key components include Multi-scale Wavelet Decomposition, Wavelet Traffic Convolution, Traffic-aware Mamba, and Fourier Pattern Adjustment.

Keywords:

Distributed network systems Fourier analysis Frequency domain processing Intelligent resource management Long-range dependency modeling Mamba architecture Multi-scale temporal modeling Network traffic prediction State space models Traffic-aware selective mechanisms Wavelet decomposition

More Related Videos

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

Related Experiment Videos

Last Updated: Jan 10, 2026

Spatial Temporal Analysis of Fieldwise Flow in Microvasculature

Spatial Temporal Analysis of Fieldwise Flow in Microvasculature

Published on: November 18, 2019

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

A comprehensive training objective balances reconstruction accuracy, temporal consistency, and spectral coherence.

Main Results:

WMF-Traffic demonstrated consistent improvements over state-of-the-art methods on four real-world datasets.
Achieved gains of 1.0-1.3% in MAE, 0.6-1.1% in RMSE, and 0.2-1.0% in MAPE.
Traffic-aware Mamba showed the largest individual contribution (10.2% MAE reduction), with the full framework improving performance by up to 27.1%.

Conclusions:

WMF-Traffic offers a robust and efficient solution for network traffic prediction.
The synergistic integration of wavelet, Mamba, and Fourier components effectively models complex traffic patterns.
The framework significantly enhances intelligent transportation systems through improved forecasting accuracy and robustness.