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

Higher order statistics and neural network for tremor recognition.

Jacek Jakubowski1, Krzystof Kwiatos, Augustyn Chwaleba

  • 1Institute of Fundamental Electronics, Military University of Technology, Warsaw, Poland.

IEEE Transactions on Bio-Medical Engineering
|June 18, 2002
PubMed
Summary

This study introduces higher-order polyspectra for tremor characterization, improving recognition accuracy for parkinsonian, essential, and physiological tremors. The novel approach achieved over 97% accuracy using a neural network classifier.

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

Dataset for developing deep learning models to assess crack width and self-healing progress in concrete.

Scientific data·2025
Same author

Assessment of the Bending Moment Capacity of Naturally Corroded Box-Section Beams.

Materials (Basel, Switzerland)·2021
Same author

Key Factors Determining the Self-Healing Ability of Cement-Based Composites with Mineral Additives.

Materials (Basel, Switzerland)·2021
Same author

Self-Sealing Process Evaluation Method Using Ultrasound Technique in Cement Composites with Mineral Additives.

Materials (Basel, Switzerland)·2020
Same author

LEFMIS: locally-oriented evaluation framework for medical image segmentation algorithms.

Physics in medicine and biology·2018
Same author

Computerized System for Quantitative Assessment of Atherosclerotic Plaques in the Femoral and Iliac Arteries Visualized by Multislice Computed Tomography.

IEEE transactions on bio-medical engineering·2015

Area of Science:

  • Biomedical Engineering
  • Signal Processing
  • Neurology

Background:

  • Standard statistical methods struggle to differentiate between parkinsonian, essential, and physiological tremors.
  • Accurate tremor characterization is crucial for diagnosis and treatment planning.

Purpose of the Study:

  • To develop and evaluate a novel method for tremor characterization and recognition.
  • To improve the classification accuracy of different tremor types.

Main Methods:

  • Utilized higher-order polyspectra (third- and fourth-order cumulants) for tremor time series analysis.
  • Extracted a set of 30 features based on polyspectral analysis.
  • Employed a multilayer perceptron neural network as the classification model.

Related Experiment Videos

Main Results:

  • The proposed polyspectral features significantly enhanced tremor recognition capabilities.
  • The neural network classifier achieved high accuracy in distinguishing between the three tremor types.
  • The average recognition error for the three tremor types was less than 3%.

Conclusions:

  • Higher-order polyspectral analysis provides a robust and effective method for tremor characterization.
  • The developed approach demonstrates high efficiency and accuracy in classifying common tremor types.
  • This technique holds promise for improving diagnostic tools in neurology.