Research on Fuzzy Association Classification Algorithm for Large Transaction Database Based on SVM

DOI

10.2991/icieac-14.2014.3How to use a DOI?

Keywords

classification; decision tree;SVM; eigenvector;

Abstract

Aiming at the defects of inefficiency and hard classification boundary in large transaction database classification, A. fuzzy associative classification algorithm based on SVM was proposed, SVM input eigenvector was constructed by weighed index and compatibility measure of fuzzy associative classification role, the effect of quantitative attribute discretization on association classifier was effectively reduced. With reference to decision tree classification algorithm, linear kernel function was used to make the speed of classification because of classification of the test samples are not complete decision tree traversal, and adjustment of parameters when used the nonlinear kernel function was avoided. Experimental results verify the feasibility and effectiveness of the algorithm.

Copyright

© 2014, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Wen-qi Wang
AU  - Qiang Li
PY  - 2014/03
DA  - 2014/03
TI  - Research on Fuzzy Association Classification Algorithm for Large Transaction Database Based on SVM
BT  - Proceedings of the 2nd International Conference on Information, Electronics and Computer
PB  - Atlantis Press
SP  - 9
EP  - 13
SN  - 1951-6851
UR  - https://doi.org/10.2991/icieac-14.2014.3
DO  - 10.2991/icieac-14.2014.3
ID  - Wang2014/03
ER  -