Abstract This paper proposes Swarm based hybrid technique CFS-PSO, which combines the characteristics of Correlation Based Feature Selection Technique (CFS) and Particle Swarm Optimization (PSO) strategy. PSO is an optimization approach motivated by swarm conduct which uses the real-number randomness & the global communication among the swarm particles. Feature selection (pre-processing technique) is very crucial part of Data Mining & Machine Learning.The aims of feature selection includes building of simpler & more logical models and improving the performance in terms of reducing the time to build the learning model and increasing the accuracy. We assess the performance of CFS-PSO on WEBSPAM-UK2006 with five classifiers. Experimental results show reduction in original features & increasing the F-measure upto 88% & 45.83% respectively.
[1]
Waleed H. Abdulla,et al.
Reduced feature-set based parallel CHMM speech recognition systems
,
2003,
Inf. Sci..
[2]
Carine G. Webber,et al.
Testing Phishing Detection Criteria and Methods
,
2011,
ICFCE.
[3]
Tommy W. S. Chow,et al.
Estimating optimal feature subsets using efficient estimation of high-dimensional mutual information
,
2005,
IEEE Transactions on Neural Networks.
[4]
Huan Liu,et al.
Feature Selection for Classification
,
1997,
Intell. Data Anal..
[5]
Ashutosh Kumar Singh,et al.
Comprehensive Literature Review on Machine Learning Structures for Web Spam Classification
,
2015
.
[6]
Nanda Kambhatla,et al.
Dimension Reduction by Local Principal Component Analysis
,
1997,
Neural Computation.