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 Video

Updated: Jul 7, 2026

Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

Artificial neural networks for feature extraction and multivariate data projection.

J Mao1, A K Jain

  • 1IBM Almaden Res. Center, San Jose, CA.

IEEE Transactions on Neural Networks
|January 1, 1995
PubMed
Summary

This study introduces novel neural networks for feature extraction and data projection, enhancing pattern recognition. These adaptive networks offer improved visualization and generalization for dynamic data analysis.

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

Profiling CARD14 gene expression in Indian Psoriasis patients.

Scientific reports·2024
Same author

Exploring the diversity of virulence genes in the <i>Magnaporthe</i> population infecting millets and rice in India.

Frontiers in plant science·2023
Same author

The Implementation of a Resuscitative Endovascular Balloon Occlusion of the Aorta (REBOA) Program at a Level 1 New England Trauma Center: Feasibility and Early Outcomes.

The American surgeon·2023
Same author

Added value of the measles-rubella supplementary immunization activity in reaching unvaccinated and under-vaccinated children, a cross-sectional study in five Indian districts, 2018-20.

Vaccine·2022
Same author

Deep learning model for predicting tunnel damages and track serviceability under seismic environment.

Modeling earth systems and environment·2022
Same author

Role of GeneXpertMTB/RIF in the diagnosis of cutaneous tuberculosis.

The Indian journal of tuberculosis·2022

Area of Science:

  • Machine Learning
  • Pattern Recognition
  • Data Visualization

Background:

  • Classical feature extraction and data projection methods are foundational in pattern recognition and exploratory data analysis.
  • Existing methods may lack adaptability to changing data distributions or generalization capabilities for new data.

Purpose of the Study:

  • To propose novel neural networks and learning algorithms for feature extraction and data projection.
  • To provide alternative and enhanced tools for analyzing and visualizing high-dimensional data.
  • To facilitate hardware implementation of feature extraction and projection techniques.

Main Methods:

  • Development of specific neural networks: SAMANN for nonlinear projection, Linear Discriminant Analysis (LDA) network, Nonlinear Discriminant Analysis (NDA) network, and NP-SOM based on Kohonen's self-organizing map.

More Related Videos

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jul 7, 2026

Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

  • Utilizing adaptive learning algorithms suitable for time-varying pattern distributions.
  • Evaluation of five representative neural networks on eight datasets using visual judgment and quantitative criteria.

    • Main Results:

    • The proposed SAMANN network provides generalization for projecting new data, an improvement over the original Sammon's algorithm.
    • The NDA method and NP-SOM network offer powerful new approaches for visualizing high-dimensional data.
    • Adaptive learning algorithms make the networks suitable for environments with changing data patterns.

    Conclusions:

    • The developed neural networks offer advanced tools for feature extraction and data projection.
    • These networks enhance the visualization and analysis of complex, high-dimensional datasets.
    • The adaptive nature and generalization capabilities of these models are significant advancements in pattern recognition.