IG-C4.5:An Improved Feature Selection Method Based on Information Gain

DOI

10.2991/meic-14.2014.244How to use a DOI?

Keywords

Collusive attack detection; Reputation Aggregation; Relationship; Social Network; Collusion factor

Abstract

Feature selection is an important means to solve the problem of dimension reduction in anomaly network traffic detection. Focusing on the problem of traditional feature selection algorithm based on information gain neglect the redundancy between features, this paper proposes an improved feature selection method combining CFS and C4.5 algorithms—IG-C4.5. In the improved algorithm, the irrelevant features and the redundant features were removed by adding the judgments of redundancy between features, which effectively simplified the feature subset. The experimental results show that the proposed algorithm can effectively find the feature subsets with good separability, which results in the low-dimensional data and the good classification accuracy.

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  - Kai Luo
AU  - JunYong Luo
AU  - MeiJuan Yin
AU  - JianLin Li
PY  - 2014/11
DA  - 2014/11
TI  - IG-C4.5:An Improved Feature Selection Method Based on Information Gain
BT  - Proceedings of the 2014 International Conference on Mechatronics, Electronic, Industrial and Control Engineering
PB  - Atlantis Press
SP  - 1097
EP  - 1100
SN  - 2352-5401
UR  - https://doi.org/10.2991/meic-14.2014.244
DO  - 10.2991/meic-14.2014.244
ID  - Luo2014/11
ER  -