An improved genetic approach

In this paper, we propose an improved genetic algorithm, which is based on an incremental genetic K-means algorithm. This approach combines an incremental genetic algorithm with K-means clustering. The main difference of our approach from the original lies in that we get rid of illegal solutions, wh...

Full description

Saved in:
Bibliographic Details
Main Authors: Liu Fuyan, Chen Chouyong, Lv Shaoyi
Format: Conference Proceeding
Language:English
Subjects:
Algorithm design and analysis
Biological cells
Clustering algorithms
Genetic algorithms
Genetic mutations
Information management
Robustness
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose an improved genetic algorithm, which is based on an incremental genetic K-means algorithm. This approach combines an incremental genetic algorithm with K-means clustering. The main difference of our approach from the original lies in that we get rid of illegal solutions, which were allowed in the original, during whole evolution process of the genetic algorithm from initialization to its termination. The improvement in our approach is accomplished through changing the way of generating initial population in initialization phase and changing the method of dealing with empty clusters in mutation operation. Thus, the illegal solutions were eliminated from our algorithm and resulting more efficient time performance. Experimental results show that our improved genetic approach is promising
DOI:10.1109/ICNNB.2005.1614714