A Faster Genetic Clustering Algorithm

Author(s):  
L Meng ◽  
Q H Wu ◽  
Z Z Yong
2007 ◽  
Vol 16 (06) ◽  
pp. 919-934
Author(s):  
YONGGUO LIU ◽  
XIAORONG PU ◽  
YIDONG SHEN ◽  
ZHANG YI ◽  
XIAOFENG LIAO

In this article, a new genetic clustering algorithm called the Improved Hybrid Genetic Clustering Algorithm (IHGCA) is proposed to deal with the clustering problem under the criterion of minimum sum of squares clustering. In IHGCA, the improvement operation including five local iteration methods is developed to tune the individual and accelerate the convergence speed of the clustering algorithm, and the partition-absorption mutation operation is designed to reassign objects among different clusters. By experimental simulations, its superiority over some known genetic clustering methods is demonstrated.


Effective software system must advance to stay pertinent, however this procedure of development can cause the product design to rot and prompt essentially diminished efficiency and even dropped projects. Remodularization tasks can be performed to fix the structure of a software system and evacuate the disintegration brought about by programming advancement. Software remodularization comprises in rearranging software entities into modules to such an extent that sets of substances having a place with similar modules are more comparable than those having a place with various modules.However, re-modularizing systems automatically is challenging in order to enhance their sustainability. In this paper, we have introduced a procedure of automatic software remodularization that helps software maintainers to enhance the software modularization quality by assessing the coupling and attachment among programming components. For precision coupling measures, the proposed technology uses structural coupling measurements. The proposed methodology utilizes tallying of class' part capacities utilized by a given class as a basic coupling measure among classes. The interaction between class files measures structural connections between software elements (classes). In this paper, probability based remodularization (PBR) approach has been proposed to remodularize the software systems. The file ordering process is done by performing probability based approach and remodularization is done based on the dependency strength or connectivity among the files. The proposed technique is experimented on seven software systems. The efficiency is measured by utilizing Turbo Modularization Quality (MQ) that promotes edge weighing module dependence graph (MDG). It very well may be presumed that when comparing performance with the subsisting techniques, for instance, Bunch – GA (Genetic Algorithm), DAGC (Development of Genetic Clustering Algorithm) and Estimation of Distribution Algorithm (EDA), the proposed methodology has greater Turbo MQ value and lesser time complexity with Bunch-GA in the software systems assessed


2008 ◽  
Vol 32 (6) ◽  
pp. 639-646
Author(s):  
Yanci Zhang ◽  
Hanqiu Sun ◽  
Enhua Wu

Sign in / Sign up

Export Citation Format

Share Document