DocumentCode :
258723
Title :
Genetic algorithm with different feature selection method for intrusion detection
Author :
Cleetus, Nimmy ; Dhanya, K.A.
Author_Institution :
Dept. of Comput. Sci. & Eng., SCMS Sch. of Eng. & Technol., Ernakulam, India
fYear :
2014
fDate :
17-18 Dec. 2014
Firstpage :
220
Lastpage :
225
Abstract :
Intrusion detection is used to protect the system from inside and outside attacks. Evolutionary algorithm has an important role in intrusion detection. Evolutionary algorithms are highly responsive for feature space reduction. The minimal number of features can improve the performance of an intrusion detection system. Thus we propose an intrusion detection system with various feature selection methods like information gain, mutual correlation, and cardinality of features. Genetic algorithm is applied into variable feature subset. The result depict that information based feature selection method can improve the detection rate. Accuracy of 87.54% is obtained in this model.
Keywords :
feature selection; genetic algorithms; security of data; feature cardinality; feature selection method; genetic algorithm; information gain; intrusion detection system; mutual correlation; variable feature subset; Accuracy; Correlation; Feature extraction; Genetic algorithms; Intrusion detection; Sociology; Evolutionary Algorithm; Feature Selection; Fitness Function; Genetic Algorithm; Intrusion Detection System;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Systems and Communications (ICCSC), 2014 First International Conference on
Conference_Location :
Trivandrum
Print_ISBN :
978-1-4799-6012-5
Type :
conf
DOI :
10.1109/COMPSC.2014.7032651
Filename :
7032651
Link To Document :
بازگشت