Search icone
Search and publish your papers

Performance comparison of feature selection technique for distributed database

Or download with : a doc exchange

About the author


About the document

Published date
documents in English
term papers
3 pages
0 times
Validated by
0 Comment
Rate this document
  1. Abstract
  2. Introduction
  3. Classifcation techniques
    1. Radial Basis Function (RBF)
    2. Naive Bayes
    3. J48, PART, GRIP and JRIP
    4. Feature selection techniques
    5. 10-fold cross validations
  4. Experimental set-up, results and discussions
    1. Dataset description and pre-processing
    2. Experimental set-up
    3. Results and discussions
  5. Conclusion
  6. References

Feature subset selection plays an essential role in all data mining applications. It speeds up a data mining algorithm and improves mining performance. This paper investigates the performance of several feature selection methods for classification: filter, wrapper and hybrid. The two filter methods used are based on information gain and correlation measures. Correlation Feature Selection (CFS) filters and wrappers were implemented using three different search mechanisms: Best First, Greedy Stepwise and Genetic. The effectiveness of the selected features was investigated by comparing accuracy and runtime of five traditional classification algorithms applied to only these selected features versus all features.

[...] In this study we compared the feature selection performance of the filter and wrapper models and combine the two models to create new hybrid models for feature selection. The remainder of this paper is organized as follows: Section 2 describes various feature selection methods and classification algorithms used. Section 3 presents the proposed approach. Section 4 presents dataset description, experimental results and discussions. The conclusions and future research are presented in section CLASSIFICATION TECHNIQUES We consider 5 popular classification techniques such as RBF, Naïve Bayes, J48, decision tree, PART and JRIP rule learning algorithms. [...]

[...] Performance of the methods have been evaluated by calculating accuracy, execution time and the reduction in number of selected features RESULTS AND DISCUSSIONS For applying classification and feature selection methods we have used WEKA software The results reported in this section were obtained with 10-fold cross validation over the dataset. Combinations of feature selection and classification methods were examined for the dataset. The accuracy and runtime performance of the classifiers obtained using filter methods are shown in Table 1. Table 2 provides the performance of the classifiers with wrapper feature selection methods ACKNOWLEDGEMENT The authors would like to thank Dr. [...]

Similar documents you may be interested in reading.

Geographic Information Systems: Modeling and Analytical Shortcomings with a Landscape...

 Science & technology   |  Geology   |  Case study   |  04/14/2008   |   .doc   |   24 pages

Risk management in the asset management industry (risk measurement techniques): An evaluation of...

 Economics & finance   |  Finance   |  Research papers   |  05/09/2009   |   .doc   |   112 pages

Recent documents in computer science category

Net neutrality in United States

 Science & technology   |  Computer science   |  Presentation   |  10/02/2018   |   .doc   |   3 pages

Reconstructing householder vectors from tall-skinny QR

 Science & technology   |  Computer science   |  Presentation   |  04/21/2017   |   .doc   |   4 pages