Paper Info
Title
On combining fractal dimension with GA for feature subset selecting
Abstract
Selecting a set of features which is optimal for a given task is a problem which plays an important role in a wide variety of contexts including pattern recognition, adaptive control, and machine learning. Recently, exploiting fractal dimension to reduce the features of dataset is a novel method. FDR (Fractal Dimensionality Reduction), proposed by Traina in 2000, is the most famous fractal dimension based feature selection algorithm. However, it is intractable in the high dimensional data space for multiple scanning the dataset and incapable of eliminating two or more features simultaneously. In this paper we combine GA with the Z-ordering based FDR for addressing this problem and present a new algorithm GAZBFDR(Genetic Algorithm and Z-ordering Based FDR). The algorithm proposed can directly select the fixed number features from the feature space and utilize the fractal dimension variation to evaluate the selected features within the comparative lower space. The experimental results show that GAZBFDR algorithm achieves better performance in the high dimensional dataset.
Year
DOI
Venue
2006
10.1007/11925231_51
MICAI
Keywords
Field
DocType
fractal dimension variation,comparative lower space,feature selection algorithm,high dimensional dataset,famous fractal dimension,gazbfdr algorithm,fractal dimension,new algorithm,feature space,feature subset selecting,high dimensional data space,adaptive control,pattern recognition,genetic algorithm,machine learning,feature selection,high dimensional data
Dimensionality reduction,Feature selection,Computer science,Artificial intelligence,Genetic algorithm,Feature vector,Clustering high-dimensional data,Pattern recognition,Fractal dimension,Fractal,Algorithm,Adaptive control,Machine learning
Conference
Volume
ISSN
ISBN
4293
0302-9743
3-540-49026-4
Citations 
PageRank 
References 
3
0.48
11
Authors
3
Name
Order
Citations
PageRank
Guanghui Yan1144.97
Zhanhuai Li227051.04
Liu Yuan3193.23