Evaluation of feature selection techniques on network traffic for comparing model accuracy

被引：2

作者：

Kaur, Prabhjot ^{[1
]}

Awasthi, Amit ^{[2
]}

Bijalwan, Anchit ^{[3
]}

机构：

[1] Uttaranchal Univ, Dehra Dun, Uttarakhand, India

[2] Univ Petr & Energy Studies, Dept Phys, Dehra Dun, Uttarakhand, India

[3] Arba Minch Univ, Fac Elect & Comp Engn, Arba Minch, Ethiopia

来源：

INTERNATIONAL JOURNAL OF COMPUTATIONAL SCIENCE AND ENGINEERING | 2021年 / 24卷 / 03期

关键词：

feature selection; fast correlation-based feature; FCBF; network traffic; Chi(2); Gini decrease; information gain; DDOS ATTACK DETECTION; INTRUSION DETECTION; NEURAL-NETWORK; ALGORITHM; DESIGN;

D O I：

10.1504/IJCSE.2021.115654

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

The accuracy and performance of any machine learning model are highly dependent on the number of qualitative features taken into consideration while training the model. The selection of qualitative features depends on the considerate choice of feature selection technique. In this study, feature selection is performed using different techniques such as information gain, Gini decrease, Chi(2) and FCBF on the same dataset, and subsequently, the accuracy has been measured. The results showed that the FCBF method has dramatically reduced the number of features and moderated the accuracy compared with other feature selection methods.

引用

页码：228 / 243

页数：16

共 51 条

[1] Statistical Model to Study the Effect of Agriculture Crop Residue Burning on Healthy Subjects [J].