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 5, 2026

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

1.7K

A Neural Network-Enhanced Kalman Filter for Time Series Anomaly Detection in Cyber-Physical Systems.

Zhongnan Ma1, Wentao Xu1, Hao Zhou1

  • 1School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China.

Sensors (Basel, Switzerland)
|May 4, 2026
PubMed
Summary

Related Concept Videos

State Space Representation01:27

State Space Representation

785
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
785

You might also read

Related Articles

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

Sort by
Same author

Molecular dialogue between arbuscular mycorrhizal fungi and the nonhost plant Arabidopsis thaliana switches from initial detection to antagonism.

The New phytologistยท2019
See all related articles

This study introduces a Neural Network-Enhanced Kalman Filter (NNEKF) for robust time series anomaly detection in cyber-physical systems (CPSs). The NNEKF framework significantly improves anomaly detection accuracy and speed for secure CPS operations.

Area of Science:

  • Cyber-physical systems
  • Time series analysis
  • Machine learning

Background:

  • Cyber-physical systems (CPSs) integrate computational, communication, and physical processes across critical domains.
  • Secure CPS operation necessitates effective time series anomaly detection, challenged by complex dynamics and sensor noise.
  • Existing methods struggle with real-world CPS complexities, demanding novel approaches.

Purpose of the Study:

  • Introduce a novel Neural Network-Enhanced Kalman Filter (NNEKF) for anomaly detection in CPS.
  • Combine model-based filtering with data-driven learning for enhanced accuracy and efficiency.
  • Address limitations of current anomaly detection techniques in dynamic and noisy CPS environments.

Main Methods:

  • Developed a two-stage neural network architecture for NNEKF.
Keywords:
Cyber-Physical SystemsKalman Filteranomaly detectionneural networktime series

Related Experiment Videos

Last Updated: May 5, 2026

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

1.7K
  • First stage learns CPS underlying dynamics; second stage optimizes Kalman gain computation.
  • Utilized an enhanced Kalman filter for recursive anomaly detection with batched parallel inference.

    • Main Results:

    • NNEKF achieved an average F1-score of 0.935 on benchmark datasets.
    • Demonstrated substantial speedups in inference time.
    • Outperformed competitive baselines in accuracy and efficiency.

    Conclusions:

    • NNEKF provides a dependable solution for real-time anomaly detection in CPS.
    • The framework offers rapid inference and a minimal model footprint.
    • NNEKF enhances the security and reliability of cyber-physical systems.