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

Temporal updating scheme for probabilistic neural network with application to satellite cloud classification.

B Tian1, M R Azimi-Sadjadi, T H Vonder Haar

  • 1Department of Electrical Engineering, Colorado State University, Fort Collins, CO 80523, USA.

IEEE Transactions on Neural Networks
|February 6, 2008
PubMed
Summary

This study introduces a new method to improve satellite cloud classification accuracy by adapting probabilistic neural networks (PNNs) to temporal image changes. The approach enhances classifier performance by tracking changes over time.

Related Concept Videos

Application of Linearization and Approximation01:29

Application of Linearization and Approximation

A drone flying through complex terrain often relies on more than one sensing method to estimate small changes in altitude. Along with direct measurements, air pressure provides a useful indirect indicator of vertical movement. Atmospheric pressure decreases as altitude increases, and this relationship is commonly described using an exponential model. Although accurate, converting pressure measurements into altitude values requires calculations that are too complex to perform repeatedly during...

You might also read

Related Articles

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

Sort by
Same author

Editorial Expression of Concern: Discovery of a BTK/MNK dual inhibitor for lymphoma and leukemia.

Leukemia·2026
Same author

[A review of research progress in integrated traditional Chinese and Western Medicine for liver diseases].

Zhonghua gan zang bing za zhi = Zhonghua ganzangbing zazhi = Chinese journal of hepatology·2025
Same author

[The application value of the magnetic resonance T2 mapping sequence in evaluating early cartilage injury of the glenohumeral joint].

Zhonghua yi xue za zhi·2025
Same author

[Establishing a predictive model for the activity of idiopathic inflammatory myopathy based on MRI and clinical features].

Zhonghua yi xue za zhi·2024
Same author

[A case report of ACTH-independent Cushing's syndrome associated with bilateral adrenal adenomas].

Zhonghua nei ke za zhi·2024
Same author

[Influencing factors of visual prognosis in patients with persistent submacular fluid after successful scleral buckle surgery for macula-off retinal detachment].

[Zhonghua yan ke za zhi] Chinese journal of ophthalmology·2023

Area of Science:

  • Remote Sensing
  • Artificial Intelligence
  • Meteorology

Background:

  • Temporal changes in satellite imagery degrade cloud classification performance.
  • Probabilistic neural networks (PNNs) are susceptible to performance degradation due to temporal variations.
  • Accurate cloud classification is crucial for weather forecasting and climate monitoring.

Purpose of the Study:

  • To develop a novel temporal updating approach for PNN classifiers to track changes in satellite image sequences.
  • To improve the robustness and accuracy of cloud classification in the presence of temporal variations.
  • To adapt PNN classifiers to evolving image characteristics over time.

Main Methods:

  • A novel temporal updating approach for PNN classifiers is proposed.

Related Experiment Videos

  • The method utilizes temporal contextual information to adjust PNNs for evolving image data.
  • A hybrid supervised/unsupervised updating scheme based on PNN prediction and Markov chain modeling is employed, using the Maximum Likelihood (ML) criterion.

    • Main Results:

    • The proposed scheme demonstrated improved classification accuracy on both simulated and real satellite cloud imagery (GOES 8).
    • The temporal updating approach effectively tracks changes in image sequences, mitigating performance degradation.
    • Comparison with existing methods indicates significant enhancements in classification performance.

    Conclusions:

    • The developed temporal updating approach significantly enhances PNN-based cloud classification accuracy from satellite imagery.
    • The method provides a robust solution for adapting classifiers to temporal changes, crucial for operational satellite data analysis.
    • This technique offers a promising advancement for improving the reliability of automated cloud classification systems.