An intrusion detection system using network traffic profiling and online sequential extreme learning machine

作者：

Highlights：

• Alpha profiling reduces the number of comparisons by 85.76%.

• Optimal features (21 out of 41) are suggested. Features are reduced by 48.78%.

• Beta profiling is used to reduce the size of training dataset by 7.83%.

• Network traffic profiling and feature selection reduce space and time complexity.

• Accuracy of 98.66% and false positive rate of 1.74% are achieved in 2.43 s.

摘要

•Alpha profiling reduces the number of comparisons by 85.76%.•Optimal features (21 out of 41) are suggested. Features are reduced by 48.78%.•Beta profiling is used to reduce the size of training dataset by 7.83%.•Network traffic profiling and feature selection reduce space and time complexity.•Accuracy of 98.66% and false positive rate of 1.74% are achieved in 2.43 s.

论文关键词：Intrusion detection system,Feature selection technique,Network traffic dataset,Network traffic profiling,Online sequential extreme learning machine (OS-ELM)

论文评审过程：Received 17 April 2015, Revised 10 June 2015, Accepted 12 July 2015, Available online 17 July 2015, Version of Record 29 August 2015.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.07.015