Title :
An Improved Weighted Feature Abstracting Algorithm
Author :
Meng, Fanrong ; Zhu, Mu
Author_Institution :
Sch. of Comput. Sci. & Technol., China Univ. of Min. & Technol., Xuzhou, China
Abstract :
In nonsupervised data set, the importance of each feature is different. If the feature is setted with a proper weight, which can fully considers the lever of the influence on the cluster effect, then the clustering result will be improved. A feature evaluate function is proposed to obtain a set of feature weight vectors by minimizing the function, which is a multi-objective problem. So a fast and elitist multi-objective genetic algorithm is used to solve the problem and obtain the weight of feature. Finally, the weight of feature is introduced into the standard K-Means algorithm and the experiments on the UCI dataset show the validity of the algorithm.
Keywords :
abstracting; data handling; genetic algorithms; K-means algorithm; UCI dataset; feature evaluate function; multiobjective genetic algorithm; nonsupervised data set; weighted feature abstracting algorithm; Automatic control; Automation; Clustering algorithms; Computer science; Control systems; Data engineering; Euclidean distance; Genetic algorithms; Systems engineering and theory; Weight measurement; K-Means; clustering; feature evaluate function; weight of feature;
Conference_Titel :
Control, Automation and Systems Engineering, 2009. CASE 2009. IITA International Conference on
Conference_Location :
Zhangjiajie
Print_ISBN :
978-0-7695-3728-3
DOI :
10.1109/CASE.2009.92
