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

A feature extraction unsupervised neural network for an environmental data set.

Giuseppe Acciani1, Ernesto Chiarantoni, Girolamo Fornarelli

  • 1Department of Electrotecnology and Electronic, Politecnico di Bari-Italy, Via E. Orabona 4, 70125, Bari, Italy.

Neural Networks : the Official Journal of the International Neural Network Society
|April 4, 2003
PubMed
Summary

This study introduces a novel unsupervised neural network for analyzing time-dependent environmental data. The method efficiently extracts features to identify human and meteorological impacts on chemical pollutant datasets.

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

Fast Detection of Olive Trees Affected by Xylella Fastidiosa from UAVs Using Multispectral Imaging.

Sensors (Basel, Switzerland)ยท2020
See all related articles

Area of Science:

  • Environmental Science
  • Data Science
  • Artificial Intelligence

Background:

  • Environmental datasets are large and heterogeneous, requiring efficient analysis strategies.
  • Time-dependent, non-stationary data presents unique challenges for analysis.
  • Feature extraction is crucial for data compression and validation.

Purpose of the Study:

  • To propose a novel feature extraction technique for non-stationary environmental data.
  • To develop an unsupervised neural network model suitable for analyzing time-dependent environmental datasets.
  • To demonstrate the model's capability in identifying environmental influences.

Main Methods:

  • Development of a new unsupervised neural network model for feature extraction.
  • Application of the model to a real-world chemical pollutant dataset.

Related Experiment Videos

  • Analysis of extracted features to identify patterns and influences.

    • Main Results:

    • The proposed neural network effectively extracts relevant features from complex environmental data.
    • The model successfully identifies human and/or meteorological effects within the chemical pollutant dataset.
    • Validation-compression of the dataset was achieved through feature selection.

    Conclusions:

    • The novel unsupervised neural network is a powerful tool for analyzing time-dependent environmental data.
    • The feature extraction technique aids in understanding complex environmental interactions.
    • This approach offers efficient data analysis for environmental monitoring and research.