Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Structured neural networks for pattern recognition.

¹Dept. of Math. & Comput. Sci., Udine Univ.

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society

|February 8, 2008

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

Classification of schizophrenia using feature-based morphometry.

Journal of neural transmission (Vienna, Austria : 1996)·2011

Same author

Brain morphometry by probabilistic latent semantic analysis.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2010

Same author

DCE-MRI data analysis for cancer area classification.

Methods of information in medicine·2009

Same author

A confidence-based approach to enhancing underwater acoustic image formation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008

Same author

Special issue on 3-D image analysis and modeling.

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

Same journal

Strategic Ability Updating in Concurrent Games by Coalitional Commitment.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2015

Same journal

Meta-Analysis of the First Facial Expression Recognition Challenge.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012

Same journal

Adjustable model-based fusion method for multispectral and panchromatic images.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012

Same journal

Face Feature Weighted Fusion Based on Fuzzy Membership Degree for Video Face Recognition.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012

Same journal

A New Adaptive Fast Cellular Automaton Neighborhood Detection and Rule Identification Algorithm.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012

Same journal

Human-arm-and-hand-dynamic model with variability analyses for a stylus-based haptic interface.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012

See all related articles

This study introduces a novel neural network design for pattern recognition by breaking down complex problems into simpler, hierarchical tasks. This approach enhances classification performance in surveillance systems compared to traditional methods.

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Pattern recognition tasks often involve complex classification problems.
Traditional statistical methods and single neural networks can face limitations in performance and scalability.

Purpose of the Study:

To propose a novel hierarchical approach for designing neural network structures for pattern recognition.
To enhance classification performance in complex surveillance scenarios.

Main Methods:

Decomposition of a large classification problem into smaller, manageable sub-problems at different hierarchical levels.
Utilizing multilayer perceptrons (MLPs) as nodes within the complex neural architecture, each trained to discriminate subsets of classes.
Application of three distinct neural structures to a railway waiting room surveillance system for classifying dangerous situations.

Related Experiment Videos

Main Results:

The proposed hierarchical neural network structures demonstrated superior performance compared to classical statistical classification procedures.
The novel approach outperformed a single, non-hierarchical neural network in classification accuracy.
Effective classification of potential dangerous situations in a real-world surveillance setting was achieved.

Conclusions:

Hierarchical neural network architectures offer a more effective strategy for complex pattern recognition tasks.
Decomposing classification problems into hierarchical levels improves recognition performance and robustness.
The presented approach shows significant potential for advanced surveillance and pattern recognition applications.