Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

A New Methodology to Overcome High Dimensionality Problem in Data Mining


Affiliations
1 Department of Computer Science, St. Joseph's College, Tiruchirappalli - 620002, India
     

   Subscribe/Renew Journal


Classification is one of the important techniques of data mining. In the classification task, features play a vital role. Therefore, selecting the relevant features becomes an essential task. Though many feature selection algorithms are available many research works are been carried out to improve the classification accuracy. In this paper, a new methodology is proposed with three different feature selection algorithms to improve the classification accuracy by selecting the relevant features.


Keywords

Data Mining, Feature Selection, Filter Approach, k-NN Algorithm, Naïve Bayesian Algorithm, J48 Algorithm.
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 200

PDF Views: 3




  • A New Methodology to Overcome High Dimensionality Problem in Data Mining

Abstract Views: 200  |  PDF Views: 3

Authors

V. Arul Kumar
Department of Computer Science, St. Joseph's College, Tiruchirappalli - 620002, India
L. Arockiam
Department of Computer Science, St. Joseph's College, Tiruchirappalli - 620002, India

Abstract


Classification is one of the important techniques of data mining. In the classification task, features play a vital role. Therefore, selecting the relevant features becomes an essential task. Though many feature selection algorithms are available many research works are been carried out to improve the classification accuracy. In this paper, a new methodology is proposed with three different feature selection algorithms to improve the classification accuracy by selecting the relevant features.


Keywords


Data Mining, Feature Selection, Filter Approach, k-NN Algorithm, Naïve Bayesian Algorithm, J48 Algorithm.