DocumentCode :
3699026
Title :
Application of hybrid ant colony algorithm for mining maximum frequent item sets
Author :
Gao Ye;Tang Xiao-lan
Author_Institution :
College of Computer Science and Technology, Xi´an University of Science and Technology, Xi´an, Shaanxi 710054, China
fYear :
2015
Firstpage :
1
Lastpage :
4
Abstract :
In order to avoid the effect of initial pheromones for Ant Colony Algorithm, Ant Colony Algorithm and Genetic Algorithm are integrated to mine maximum frequent item sets in this paper. First of all, this paper introduces the ideas of Hybrid Ant Colony Algorithm and briefly explains how to process the data of database. In the second place, Ant Colony Algorithm and Genetic Algorithm are designed respectively, including the method of encoding, parameters setting, the choice of evaluation function and so on. Finally, the Hybrid Ant Colony Algorithm is compared with Max-Min Ant Colony Algorithm (MMAS) on the issue of mining maximum frequent item sets. The results show that the qualities of maximum frequent item sets mined by Hybrid Ant Colony Algorithm are better than MMAS.
Keywords :
"Algorithm design and analysis","Genetic algorithms","Databases","Sociology","Statistics","Encoding","Computers"
Publisher :
ieee
Conference_Titel :
Signal Processing, Communications and Computing (ICSPCC), 2015 IEEE International Conference on
Print_ISBN :
978-1-4799-8918-8
Type :
conf
DOI :
10.1109/ICSPCC.2015.7338918
Filename :
7338918
Link To Document :
بازگشت