Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A hybrid transformer-BiLSTM model optimized with Firefly Algorithm for network traffic anomaly detection.

Debiao Luo1, Weijie Wang1, Xinyue Liu1

  • 1Information Network Center, Chengdu University, Chengdu, China.

Plos One
|June 17, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Transformers with Off-Nominal Turns Ratios01:25

Transformers with Off-Nominal Turns Ratios

In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the rated...

You might also read

Related Articles

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

Sort by
Same author

Data Resource Profile: The China National Health Survey (CNHS).

International journal of epidemiology·2018
Same author

New Pathway for Hot Electron Relaxation in Two-Dimensional Heterostructures.

Nano letters·2018
Same author

A Dual-Band Multilayer InSe Self-Powered Photodetector with High Performance Induced by Surface Plasmon Resonance and Asymmetric Schottky Junction.

ACS nano·2018
Same author

Two-minute walk test: Reference equations for healthy adults in China.

PloS one·2018
Same author

The Dysregulation of the <i>DLK1</i>-<i>MEG3</i> Locus in Islets From Patients With Type 2 Diabetes Is Mimicked by Targeted Epimutation of Its Promoter With TALE-DNMT Constructs.

Diabetes·2018
Same author

Co-regulatory networks of human serum proteins link genetics to disease.

Science (New York, N.Y.)·2018

This study introduces a novel framework for network traffic anomaly detection (NTAD) using signal decomposition and a hybrid deep learning model. The EMD-FA-Transformer-BiLSTM approach significantly improves timely anomaly prediction for enhanced cyber defense.

Area of Science:

  • Cybersecurity
  • Artificial Intelligence
  • Data Science

Background:

  • Network Traffic Anomaly Detection (NTAD) is critical for cybersecurity.
  • Sophisticated cyber threats necessitate advanced detection methods.
  • Existing methods face challenges with non-stationary and noisy network data.

Purpose of the Study:

  • To develop a data-driven framework for timely network traffic anomaly prediction.
  • To integrate adaptive signal decomposition, attention-recurrent architecture, and metaheuristic optimization.
  • To enhance proactive cyber defense capabilities.

Main Methods:

  • Empirical Mode Decomposition (EMD) for preprocessing raw traffic sequences, mitigating non-stationarity and noise.
  • A hybrid deep network combining multi-head self-attention for global dependencies and Bidirectional Long Short-Term Memory (BiLSTM) for temporal dynamics.

Related Experiment Videos

  • Firefly Algorithm (FA) for automated, population-based hyperparameter optimization of the deep learning model.

    • Main Results:

    • The proposed EMD-FA-Transformer-BiLSTM model achieved state-of-the-art performance on benchmark datasets.
    • Demonstrated statistically significant improvements in both regression error and classification F1-score compared to baseline and existing models.
    • The framework effectively captures global dependencies and bidirectional temporal dynamics for accurate anomaly prediction.

    Conclusions:

    • The integrated EMD-FA-Transformer-BiLSTM framework offers a robust solution for network traffic anomaly detection.
    • This approach enhances proactive cyber defense by providing timely and accurate anomaly predictions.
    • The methodology shows significant potential for real-world application in network security.