Centroid neural network with Bhattacharyya kernel for GPDF data clustering

Authors:
Song-Jae Lee;Dong-Chul Park
Affiliations:
Dept. of Information Eng., and Myongji IT Eng. Research Inst., Myong Ji University, Korea;Dept. of Information Eng., and Myongji IT Eng. Research Inst., Myong Ji University, Korea
Venue:
PAKDD'07 Proceedings of the 11th Pacific-Asia conference on Advances in knowledge discovery and data mining
Year:
2007

Citing 7
Cited 2

An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Information Theoretic Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Clustering Algorithms

Clustering Algorithms
Centroid neural network for unsupervised competitive learning

IEEE Transactions on Neural Networks
An introduction to kernel-based learning algorithms

IEEE Transactions on Neural Networks
Mercer kernel-based clustering in feature space

IEEE Transactions on Neural Networks
Fuzzy kernel perceptron

IEEE Transactions on Neural Networks

Classification of Audio Signals Using a Bhattacharyya Kernel-Based Centroid Neural Network

PAKDD '09 Proceedings of the 13th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining
Application of Bhattacharyya Kernel-based centroid neural network to the classification of audio signals

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A clustering algorithm for GPDF data called Centroid Neural Network with Bhattacharyya Kernel (BK-CNN) is proposed in this paper. The proposed BK-CNN is based on the unsupervised competitive centroid neural network (CNN) and employs a kernel method for data projection. In order to cluster the GPDF data, the Bhattacharyya kernel is used to measure the distance between two probability distributions for data projection. When applied to GPDF data in an image classification model, the experiment results show that the proposed BKCNN algorithm is more efficient than other conventional algorithms such as k-means algorithm, SOM and CNN with Bhattacharyya distance.