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

Fault classification on vibration data with wavelet based feature selection scheme.

Gary G Yen1, Wen Fung Leong

  • 1Intelligent Systems and Control Laboratory, School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, OK 74078, USA. gyen@okstate.edu

ISA Transactions
|May 3, 2006
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

Caformer: Rethinking Time-Series Forecasting From Causal Perspective.

IEEE transactions on cybernetics·2025
Same author

Imitation Learning for Multiobjective Optimization-AlphaMOEA.

IEEE transactions on cybernetics·2025
Same author

REaMA: Building Biomedical Relation Extraction Specialized Large Language Models Through Instruction Tuning.

IEEE transactions on neural networks and learning systems·2025
Same author

Uncovering Large Language Model Weaknesses in Character and Word Understanding and Manipulating.

IEEE transactions on neural networks and learning systems·2025
Same author

HMAMP: Designing Highly Potent Antimicrobial Peptides Using a Hypervolume-Driven Multiobjective Deep Generative Model.

Journal of medicinal chemistry·2025
Same author

Boundary-Based Active Domain Adaptation for Semantic Segmentation Under Adverse Conditions.

IEEE transactions on neural networks and learning systems·2025
Same journal

Neural network parameter identification-based prescribed-time adaptive control for morphing glide aircraft.

ISA transactions·2026
Same journal

Nonlinear system-guided continuous-time generalization for cross-aircraft engine state monitoring.

ISA transactions·2026
Same journal

Predefined-time distributed optimal formation control for constrained UAV-UGV systems.

ISA transactions·2026
Same journal

Fixed-time distributed secondary control for voltage/frequency restoration and power sharing in microgrids under switching topologies.

ISA transactions·2026
Same journal

A robust ATUB-Net for bearing fault diagnosis under unbalanced sample scenarios.

ISA transactions·2026
Same journal

Data-driven trajectory tracking control of UAV systems under a novel probability-selection event-triggered mechanism.

ISA transactions·2026
See all related articles

This study introduces a novel wavelet-based feature selection method for health usage monitoring systems. The technique significantly reduces feature dimensions, improving computational efficiency without sacrificing classification accuracy.

Area of Science:

  • Engineering
  • Signal Processing
  • Machine Learning

Background:

  • Health usage monitoring systems rely on vibration measurements for fault classification.
  • Multiple sensors enhance reliability but create high-dimensional feature sets, increasing computational cost.
  • Effective feature extraction and selection are crucial for managing complex data.

Purpose of the Study:

  • To develop an efficient feature selection scheme for vibration-based fault classification.
  • To reduce feature dimensionality in health usage monitoring systems.
  • To overcome limitations of existing methods by creating a generic, domain-independent feature set.

Main Methods:

  • A wavelet-based feature selection scheme utilizing local discriminant bases and genetic optimization.

Related Experiment Videos

  • Implementation of a 'divide and conquer' strategy to reduce computation time.
  • Evaluation through simulation to assess feature reduction and classification performance.

    • Main Results:

    • Achieved at least a 65% reduction in the total number of features.
    • Demonstrated no compromise in classification accuracy despite significant dimensionality reduction.
    • The proposed scheme requires no prior domain-specific information.

    Conclusions:

    • The proposed wavelet-based feature selection scheme is effective for vibration-based fault classification.
    • It offers significant computational advantages and maintains high accuracy.
    • This method provides a generic and efficient solution for health usage monitoring systems.