Welcome to the InfoSci Platform
Reference Hub7
EFS-LSTM (Ensemble-Based Feature Selection With LSTM) Classifier for Intrusion Detection System

EFS-LSTM (Ensemble-Based Feature Selection With LSTM) Classifier for Intrusion Detection System

Preethi D., Neelu Khare
Copyright: © 2020 |Volume: 16 |Issue: 4 |Pages: 15
ISSN: 1548-3673|EISSN: 1548-3681|EISBN13: 9781799805182|DOI: 10.4018/IJeC.2020100106
Cite Article Cite Article

MLA

Preethi D., and Neelu Khare. "EFS-LSTM (Ensemble-Based Feature Selection With LSTM) Classifier for Intrusion Detection System." IJEC vol.16, no.4 2020: pp.72-86. http://doi.org/10.4018/IJeC.2020100106

APA

Preethi D. & Khare, N. (2020). EFS-LSTM (Ensemble-Based Feature Selection With LSTM) Classifier for Intrusion Detection System. International Journal of e-Collaboration (IJeC), 16(4), 72-86. http://doi.org/10.4018/IJeC.2020100106

Chicago

Preethi D., and Neelu Khare. "EFS-LSTM (Ensemble-Based Feature Selection With LSTM) Classifier for Intrusion Detection System," International Journal of e-Collaboration (IJeC) 16, no.4: 72-86. http://doi.org/10.4018/IJeC.2020100106

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In this article, an EFS-LSTM, a deep recurrent learning model, is proposed for network intrusion detection systems. The EFS-LSTM model uses ensemble-based feature selection (EFS) and LSTM (Long Short Term Memory) for the classification of network intrusions. The EFS combines five feature selection mechanisms namely, information gain, gain ratio, chi-square, correlation-based feature selection, and symmetric uncertainty-based feature selection. The experiments were conducted using the benchmark NSL-KDD dataset and implemented using Tensor flow and python. The EFS-LSTM classifier is evaluated using the classification performance metrics and also compared with all the 41 features without any feature selection as well as with each individual feature selection techniques and classified using LSTM. The performance study showed that the EFS-LSTM model outperforms better with 99.8% accuracy with a higher detection and less false alarm rates.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.