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 Concept Videos

Laminar and Turbulent Flow01:07

Laminar and Turbulent Flow

9.7K
Fluid dynamics is the study of fluids in motion. Velocity vectors are often used to illustrate fluid motion in applications like meteorology. For example, wind—the fluid motion of air in the atmosphere—can be represented by vectors indicating the speed and direction of the wind at any given point on a map. Another method for representing fluid motion is a streamline. A streamline represents the path of a small volume of fluid as it flows. When the flow pattern changes with time, the...
9.7K
Laminar Flow01:27

Laminar Flow

2.1K
Laminar flow represents a smooth, orderly fluid motion where particles move along parallel paths, resulting in minimal mixing between layers. Streamlined particle paths characterize this flow regime and occur under conditions where viscous forces dominate over inertial forces. The distinction between laminar, transitional, and turbulent flow is primarily determined by the Reynolds number, a dimensionless quantity calculated as:
2.1K

You might also read

Related Articles

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

Sort by
Same author

Large Language Models for Synthetic Dataset Generation of Cybersecurity Indicators of Compromise.

Sensors (Basel, Switzerland)·2025
Same author

Reinforcement Learning-Based Time-Slotted Protocol: A Reinforcement Learning Approach for Optimizing Long-Range Network Scalability.

Sensors (Basel, Switzerland)·2025
Same author

Predicting triage of pediatric patients in the emergency department using machine learning approach.

International journal of emergency medicine·2025
Same author

The implementation of the cognitive theory of multimedia learning in the design and evaluation of an AI educational video assistant utilizing large language models.

Heliyon·2024
Same author

A semi supervised approach to Arabic aspect category detection using Bert and teacher-student model.

PeerJ. Computer science·2023
Same author

IoT Traffic Analyzer Tool with Automated and Holistic Feature Extraction Capability.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Apr 30, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

983

Network Traffic Data Augmentation Using WGAN Model Guided by LLM.

Jumanah Hmoud Alyoubi1, Miada Almasre1, Aishah Aseeri1

  • 1Information Technology Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia.

Sensors (Basel, Switzerland)
|December 31, 2025
PubMed
Summary

This study introduces a novel framework using graph-conditioned generative models and large language models (LLMs) to create synthetic network traffic. This method effectively addresses class imbalance in Internet of Things (IoT) security analytics, improving device identification accuracy.

Keywords:
IoT devices identificationIoT securityLLMMLWGANnetwork traffic classification

Related Experiment Videos

Last Updated: Apr 30, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

983

Area of Science:

  • Cybersecurity
  • Artificial Intelligence
  • Network Engineering

Background:

  • Internet of Things (IoT) device identification from network traffic faces challenges due to severe class imbalance, which degrades classifier performance.
  • Synthetic data generation is a potential solution, especially in privacy-sensitive security scenarios with limited access to real traffic data.

Purpose of the Study:

  • To propose a novel framework combining graph-conditioned generative modeling and large language model (LLM) guidance for generating realistic, semantically valid synthetic network traffic.
  • To address the critical issue of class imbalance in network traffic classification for improved Internet of Things (IoT) security analytics.

Main Methods:

  • Constructing feature relationship graphs (using Pearson correlation, Spearman rank correlation, mutual information) to condition a Wasserstein GAN (WGAN) for preserving traffic structure.
  • Employing an LLM to define and enforce class-specific semantic constraints (feature ranges, attribute correlations, protocol rules) for label-consistent and standards-compliant synthetic data.
  • Implementing a dual validation loop combining LLM feedback and classifier performance evaluation against traditional methods like SMOTE.

Main Results:

  • The proposed framework generates higher-fidelity synthetic network traffic by jointly leveraging structural (graph) and semantic (LLM) conditioning.
  • Consistent improvements in macro-F1 score and balanced accuracy for network traffic classification were observed when using datasets balanced by the new method.
  • The approach demonstrates significant utility for security analytics in data-scarce and privacy-constrained environments.

Conclusions:

  • The integration of graph-conditioned generative models and LLM guidance offers a powerful approach to synthetic data generation for imbalanced network traffic classification.
  • This framework enhances the reliability of device identification in Internet of Things (IoT) infrastructures, crucial for robust security analytics.
  • The method provides a viable solution for overcoming data limitations and privacy concerns in network security research and applications.