Sign in
Back
A Novel Genetic Algorithm Based k-means Algorithm for Cluster Analysis
Conference proceeding

A Novel Genetic Algorithm Based k-means Algorithm for Cluster Analysis

M. A. El-Shorbagy, A. Y. Ayoub, I. M. El-Desoky and A. A. Mousa
INTERNATIONAL CONFERENCE ON ADVANCED MACHINE LEARNING TECHNOLOGIES AND APPLICATIONS (AMLTA2018), Vol.723, pp.92-101
Advances in Intelligent Systems and Computing
01/01/2018
DOI: https://doi.org/10.1007/978-3-319-74690-6_10

Abstract

Computer Science Computer Science, Artificial Intelligence Science & Technology Technology
This paper proposed a novel genetic algorithm (GA) based k-means algorithm to perform cluster analysis. In the proposed approach, the population of GA is initialized by k-means algorithm. Then, the GA operators are applied to generate a new population. In addition, new mutation is proposed depending on the extreme points of clustering. The proposed approach is applied on a set of test problems. The results proved the superiority of the new methodology to perform cluster analysis well.

Metrics

1 Record Views

Details