Login New user?  
01-Applied Mathematics & Information Sciences
An International Journal
               
 
 
 
 
 
 
 
 
 
 
 
 
 

Content
 

Volumes > Volume 17 > No. 5

 
   

Detection Of Intrusion In Imbalanced Network Traffic Based On Machine Learning Approach

PP: 1195-1217
doi:10.18576/amis/170573
Author(s)
P Manimaran, R Ashwin Kumar, C Pooja, A Jeeva,
Abstract
Intrusion detection systems are essential for maintaining network security, as networks can be intentionally attacked from various directions. However, many intrusion detection models suffer from high false detection rates due to a lack of training data caused by data imbalance. To address this issue, we propose a network intrusion detection method based on the improved Random Forest and Synthetic Minority Oversampling (SMOTE) algorithms. Our approach uses a hybrid algorithm that combines the K-Means clustering algorithm with the SMOTE sampling strategy to increase the number of minority samples and create a balanced dataset that makes it easier to understand the properties of small samples. We then adjust the voting processing prediction results by assessing the type of network attacks using the similarity matrix of network assaults. The initial prediction results are generated using the improved random forest. We evaluate the performance of our method using the NSL-KDD dataset and achieve a classification accuracy of 99.72% on the training set and 78.47% on the test set, which outperforms other relevant articles.

  Home   About us   News   Journals   Conferences Contact us