ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Importance of Information classification in the Data Manning

Journal: IPASJ International Journal of Electronics & Communication (IIJEC) (Vol.3, No. 8)

Publication Date:

Authors : ; ;

Page : 9-12

Keywords : ;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

ABSTRACT Classification is most difficult and innovative problem in data processing. Classification techniques had been focus of analysis since years. Logic, perception, instance and statistical ideas primarily based classifiers square measure accessible to resolve the classification downside. This work is concerning the logic primarily based classifiers referred to as call tree classifiers as a result of these use logic primarily based algorithms to classify knowledge on the premise of feature values. A rending criterion on attributes is employed to come up with the tree. A classifier is enforced serially or in parallel depending upon the dimensions of knowledge set. a number of the classifiers such as SLIQ, SPRINT, CLOUDS, BOAT and rain forest have the capability of parallel implementation. IDE 3, CART, C4.5 and C5.0 square measure serial classifiers. Building part has additional importance in some classifiers to boost the quantifiability beside quality of the classifier. This study can give an summary of various logic primarily based classifiers and can compare these against our pre-defined criteria. we have a tendency to conclude that SLIQ and SPRINT square measure suitable for larger knowledge sets whereas C4.5 and C5.0 are best suited for smaller knowledge sets.

Last modified: 2015-09-05 14:02:16