Jove
Visualize
Contact Us

Related Experiment Video

Updated: Jul 7, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Decision-based neural networks with signal/image classification applications.

S Y Kung1, J S Taur

  • 1Dept. of Electr. Eng., Princeton Univ., NJ.

IEEE Transactions on Neural Networks
|January 1, 1995
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Classification of Signals01:30

Classification of Signals

In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...

You might also read

Related Articles

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

Sort by
Same author

Flexible complexity reduced PID-like fuzzy controllers.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2008
Same author

Probabilistic principal component subspaces: a hierarchical finite mixture model for data visualization.

IEEE transactions on neural networks·2008
Same author

Estimation of elliptical basis function parameters by the EM algorithm with application to speaker verification.

IEEE transactions on neural networks·2008
Same author

Segmentation of psoriasis vulgaris images using multiresolution-based orthogonal subspace techniques.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2006
Same author

Multi-metric and multi-substructure biclustering analysis for gene expression data.

Proceedings. IEEE Computational Systems Bioinformatics Conference·2006
Same author

Adaptive fuzzy terminal sliding mode controller for linear systems with mismatched time-varying uncertainties.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2004
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

This study introduces the decision-based neural network (DBNN), a supervised learning model effective for static and temporal pattern recognition. DBNNs offer computational efficiency and high performance in classification tasks like OCR and ECG analysis.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Pattern Recognition

Background:

  • Supervised learning networks are crucial for pattern recognition.
  • Existing models may have limitations in handling complex data variations.

Purpose of the Study:

  • To propose and explore a novel decision-based neural network (DBNN).
  • To evaluate the DBNN's effectiveness in static and temporal pattern recognition.
  • To analyze the DBNN's computational efficiency and performance.

Main Methods:

  • Developed a decision-based neural network (DBNN) integrating perceptron-like learning and hierarchical nonlinear structures.
  • Proposed hidden-node and subcluster hierarchical structures for static pattern recognition.
  • Utilized model-based discriminant functions for temporal DBNNs to handle waveform variations.

Related Experiment Videos

Last Updated: Jul 7, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Main Results:

  • DBNNs demonstrated high effectiveness in computation time and performance across various applications.
  • Simulations confirmed DBNN efficacy in texture classification, Optical Character Recognition (OCR), and Electrocardiogram (ECG) analysis.
  • Established relationships between DBNNs and other models like LVQ and PNN.

Conclusions:

  • DBNNs provide a powerful and efficient approach for both static and temporal pattern recognition.
  • The proposed hierarchical structures enhance DBNN capabilities for complex classification tasks.
  • DBNNs represent a significant advancement in supervised learning for practical applications.