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 Video

Updated: May 14, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

A Privacy-Preserving Artificial Intelligence-Driven Sensing System for Distributed Multimodal Risk Detection.

Yawen Zhu1, Yiwei Song1,2, Yikun Xuan2

  • 1China Agricultural University, Beijing 100083, China.

Sensors (Basel, Switzerland)
|May 13, 2026
PubMed
Summary
This summary is machine-generated.

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

An automated, digital immunoassay on a microfluidic cartridge for on-demand cytokine profiling.

Microsystems & nanoengineering·2026
Same author

A Multimodal Sensor-Based Self-Supervised Learning Framework for Low-Noise System State Prediction and Anomaly Detection.

Sensors (Basel, Switzerland)·2026
Same author

An AI-Driven Multimodal Sensing Framework Integrating UAV Imagery and Environmental Sensors for Intelligent Farmland Monitoring.

Sensors (Basel, Switzerland)·2026
Same author

A next generation of the schema therapy model of personality pathology: A cross-cultural and international study protocol.

PloS one·2026
Same author

Does gender moderate the relationship between bullying victimization and depression? A longitudinal study.

BMC psychology·2026
Same author

[<i>Chonggu</i> Granules attenuate cartilage injury in knee osteoarthritis patients with liver-kidney deficiency syndrome by regulating the Nrf2 pathway].

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

This study introduces a federated multimodal security perception framework (FMS-LLM) for intelligent security. The FMS-LLM framework enhances security analysis by fusing multimodal data, improving accuracy and robustness in distributed environments.

Area of Science:

  • Artificial Intelligence
  • Cybersecurity
  • Machine Learning

Background:

  • Intelligent terminals, mobile payments, and IoT devices necessitate advanced security beyond traditional analysis.
  • Distributed security systems face challenges with multimodal data heterogeneity and privacy constraints.
  • Existing methods struggle with non-independent and identically distributed (Non-IID) data across nodes.

Purpose of the Study:

  • To propose an artificial intelligence-driven federated multimodal security perception framework (FMS-LLM).
  • To address challenges in distributed security perception, including data heterogeneity, Non-IID data, and privacy.
  • To enhance security analysis through intelligent perception of user behavior, device states, and environmental context.

Main Methods:

Keywords:
artificial intelligence-driven sensingcross-modal semantic reasoningfederated learningmultimodal sensingprivacy-preserving risk detection

Related Experiment Videos

Last Updated: May 14, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

  • Developed a federated multimodal security perception framework (FMS-LLM).
  • Introduced a Non-IID adaptive federated fusion mechanism for dual-level alignment (structural and semantic).
  • Integrated an LLM-driven semantic enhancement module for mapping low-level features to high-level risk representations.

    • Main Results:

    • Achieved high performance: 91.62% Accuracy, 90.70% F1-score, and 94.73% ROC-AUC.
    • Demonstrated strong robustness under Non-IID conditions (88.47% Accuracy, 87.11% F1-score at α=0.1).
    • Reduced communication cost to 18.92 MB/Round while maintaining performance.

    Conclusions:

    • The FMS-LLM framework effectively fuses multi-source sensing information under privacy preservation.
    • The proposed method supports intelligent security perception with high accuracy, robustness, and interpretability.
    • FMS-LLM outperforms baseline methods in distributed multimodal security perception tasks.