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

Classification of normal and abnormal electrogastrograms using multilayer feedforward neural networks

Z Lin1, J Maris, L Hermans

  • 1University of Virginia Health Science Center, Charlottesville, USA.

Medical & Biological Engineering & Computing
|May 1, 1997
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

[Survey on mosquito species diversity and pathogen spectrum of arbovirus in tropical regions of China].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2026
Same author

Cat Scratch Colon.

Acta gastro-enterologica Belgica·2025
Same author

A sustainable approach toward mechanical recycling unsortable post-consumer WEEE: Reactive and non-reactive compatibilization.

Waste management (New York, N.Y.)·2024
Same author

Short communication: Circadian variations and day-to-day variability of clinical signs used for the early diagnosis of pneumonia within and between calves.

Research in veterinary science·2023
Same author

[Ventilatory management of SARS-CoV-2 acute respiratory failure].

Revue des maladies respiratoires·2023
Same author

[Evaluation of ankle joint protection effect of parachute ankle brace on paratrooper landing].

Zhonghua lao dong wei sheng zhi ye bing za zhi = Zhonghua laodong weisheng zhiyebing zazhi = Chinese journal of industrial hygiene and occupational diseases·2023

This study introduces a neural network for classifying electrogastrograms (EGG). The scaled conjugate gradient algorithm demonstrated superior performance, achieving 95% accuracy with power spectral or ARMA parameters as input.

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence
  • Signal Processing

Background:

  • Automated classification of electrogastrograms (EGG) is crucial for diagnosing gastrointestinal disorders.
  • Multilayer feedforward neural networks (MFNN) offer a promising approach for analyzing complex biomedical signals like EGG.
  • Evaluating different input representations and learning algorithms is essential for optimizing neural network performance.

Purpose of the Study:

  • To propose and evaluate a neural network approach for automated normal and abnormal EGG classification.
  • To compare the performance of quasi-Newton, scaled conjugate gradient, and error backpropagation learning algorithms for MFNN.
  • To investigate the effectiveness of raw EGG data, power spectral data, and autoregressive moving average (ARMA) modelling parameters as input features.

Related Experiment Videos

Main Methods:

  • Implemented multilayer feedforward neural networks (MFNN) with configurations determined experimentally.
  • Trained and compared three learning algorithms: quasi-Newton, scaled conjugate gradient, and error backpropagation.
  • Utilized raw EGG data, power spectral data, and ARMA modelling parameters as input features for the MFNN.
  • Evaluated algorithm performance using percent correct, sum-squared error, and complexity per iteration.

Main Results:

  • The scaled conjugate gradient algorithm exhibited robust performance and a super-linear convergence rate, outperforming other tested algorithms.
  • Both power spectral representation and ARMA modelling parameters as input features yielded a high percent correctness of 95% on the test set.
  • The study identified optimal input features and learning algorithms for EGG classification using neural networks.

Conclusions:

  • The scaled conjugate gradient algorithm is highly effective for EGG classification with MFNN.
  • Power spectral and ARMA features provide superior input representations for EGG analysis compared to raw data.
  • The developed neural network approach offers a valuable tool for automated EGG classification and has potential applications in other biomedical signal analyses.