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

Adaptive fuzzy leader clustering of complex data sets in pattern recognition.

S C Newton¹, S Pemmaraju, S Mitra

¹Dept. of Electr. Eng., Texas Tech. Univ., Lubbock, TX.

IEEE Transactions on Neural Networks

|January 1, 1992

Summary

A new adaptive fuzzy leader clustering (AFLC) algorithm offers stable, efficient online learning for complex data. This unsupervised neural network successfully classifies real-world data, showing promise for advanced 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

Power cepstrum and spectrum techniques applied to image registration.

Applied optics·2010

Same author

Noise trauma impairs neurogenesis in the rat hippocampus.

Neuroscience·2010

Same author

Artifactual 'atrial flutter' caused by a continuous passive motion device after total knee replacement.

Anaesthesia and intensive care·2009

Same author

Quinolone-resistant Salmonella enterica Serovar typhi presenting as acute fulminant hepatitis.

The Journal of the Association of Physicians of India·2009

Same author

Hearing sensitivity in women following chemotherapy treatment for breast cancer: results from a pilot study.

Breast (Edinburgh, Scotland)·2009

Same author

Prepulse minimization in KALI-5000.

The Review of scientific instruments·2009

Area of Science:

Artificial Intelligence
Machine Learning
Data Mining

Background:

Complex datasets require robust clustering and classification methods.
Existing algorithms may lack efficiency or stability in online learning scenarios.

Purpose of the Study:

To introduce a novel modular, unsupervised neural network architecture for clustering and classification.
To present the adaptive fuzzy leader clustering (AFLC) architecture as a hybrid neural-fuzzy system capable of stable and efficient online learning.

Main Methods:

The AFLC architecture utilizes an Adaptive Resonance Theory (ART-1) like control structure for initial cluster center identification.
A two-stage classification process involving competitive and distance metric comparison stages is employed.
Cluster prototypes are incrementally updated using Fuzzy C-Means (FCM) equations for centroid relocation and membership values.

Related Experiment Videos

Main Results:

The AFLC algorithm demonstrated successful classification of features extracted from real-world datasets, including the Anderson iris and laser-luminescent finger image data.
The algorithm proved effective for both discrete and continuous data types.
The study discussed the operational characteristics and critical parameters of the AFLC algorithm.

Conclusions:

The AFLC algorithm presents a powerful new approach for analyzing complex datasets.
Its hybrid neural-fuzzy design and online learning capabilities offer significant potential in data mining and machine learning applications.