Scribd
Upload
49 views1 page

An Incremental Clustering Algorithm Based On Mahalanobis Distance

Uploaded by

Khairul

The document describes a paper presented at the 3rd International Conference on Quantitative Sciences and Its Applications titled "An Incremental Clustering Algorithm Based on Mahalanobis Distance". The paper proposes replacing the Euclidean distance used in fuzzy c-means clustering with Mahalanobis distance and applying it to incremental learning. Experimental results showed this Mahalanobis distance based fuzzy incremental clustering algorithm effectively addressed limitations in fuzzy c-means clustering while also increasing training accuracy for non-spherical datasets.

Copyright:

© All Rights Reserved
Download as DOC, PDF, TXT or read online from Scribd
Download as doc, pdf, or txt

An Incremental Clustering Algorithm Based On Mahalanobis Distance

Uploaded by

Khairul
49 views1 page
The document describes a paper presented at the 3rd International Conference on Quantitative Sciences and Its Applications titled "An Incremental Clustering Algorithm Based on Mahalanobis Distance". The paper proposes replacing the Euclidean distance used in fuzzy c-means clustering with Mahalanobis distance and applying it to incremental learning. Experimental results showed this Mahalanobis distance based fuzzy incremental clustering algorithm effectively addressed limitations in fuzzy c-means clustering while also increasing training accuracy for non-spherical datasets.

Original Description:

aaaa

Original Title

0.0 Abstract 0

Copyright

© © All Rights Reserved

Available Formats

DOC, PDF, TXT or read online from Scribd

Did you find this document useful?

Is this content inappropriate?

The document describes a paper presented at the 3rd International Conference on Quantitative Sciences and Its Applications titled "An Incremental Clustering Algorithm Based on Mahalanobis Distance". The paper proposes replacing the Euclidean distance used in fuzzy c-means clustering with Mahalanobis distance and applying it to incremental learning. Experimental results showed this Mahalanobis distance based fuzzy incremental clustering algorithm effectively addressed limitations in fuzzy c-means clustering while also increasing training accuracy for non-spherical datasets.

Copyright:

© All Rights Reserved
Download as DOC, PDF, TXT or read online from Scribd
Download as doc, pdf, or txt
49 views1 page

An Incremental Clustering Algorithm Based On Mahalanobis Distance

Uploaded by

Khairul
The document describes a paper presented at the 3rd International Conference on Quantitative Sciences and Its Applications titled "An Incremental Clustering Algorithm Based on Mahalanobis Distance". The paper proposes replacing the Euclidean distance used in fuzzy c-means clustering with Mahalanobis distance and applying it to incremental learning. Experimental results showed this Mahalanobis distance based fuzzy incremental clustering algorithm effectively addressed limitations in fuzzy c-means clustering while also increasing training accuracy for non-spherical datasets.

Copyright:

© All Rights Reserved
Download as DOC, PDF, TXT or read online from Scribd
Download as doc, pdf, or txt
You are on page 1/ 1

3rd International Conference on Quantitative Sciences and Its Applications

ICOQSIA2014

An Incremental Clustering Algorithm Based on


Mahalanobis Distance
Lim Eng Aika, and Tan Wee Choonb
a

Institut Matematik Kejuruteraan, Universiti Malaysia Perlis, 02600 Ulu Pauh, Perlis, Malaysia.
[email protected]
b
School of Mechatronics Engineering, Universiti Malaysia Perlis, 02600 Ulu Pauh, Perlis, Malaysia.
[email protected]

Abstract. Classical fuzzy c-means clustering algorithm is insufficient to cluster non-spherical or


elliptical distributed datasets. The paper replaces classical fuzzy c-means clustering euclidean
distance with Mahalanobis distance. It applies Mahalanobis distance to incremental learning for
its merits. A Mahalanobis distance based fuzzy incremental clustering learning algorithm is
proposed. Experimental results show the algorithm is an effective remedy for the defect in fuzzy
c-means algorithm but also increase training accuracy.
Keywords: fuzzy c-means, Mahalanobis distance, incremental learning.

You might also like