Skip to search boxSkip to navigationSkip to main content

Moth–Flame Optimization based ensemble classification for intrusion detection in intelligent transport system for smart cities

  • Thippa Reddy Gadekallu(corresponding author)
    ,
  • Neeraj Kumar
    ,
  • ,
  • Deepa Natarajan
    ,
  • Prabadevi Boopathy
    ,
  • Praveen Kumar Reddy Maddikunta
*Corresponding author for this work
  • Vellore Institute of Technology
    ,
  • Lovely Professional University
    ,
  • Lebanese American University
    ,
  • Jiaxing University
    ,
  • Zhejiang Province
    ,
  • Thapar Institute of Engineering & Technology
Research Output:
Contribution to journal
Article
Research
Peer-review

Abstract

<p>The number of vehicles travelling on the road has increased tremendously over the past few decades throughout the globe. The advent of Intelligent Transport System (ITS) enabled the vehicles to be managed intelligently. However, the ITS network can be intruded by malicious users to access the sensitive information. So a strong Intrusion Detection System (IDS) is required to safeguard the ITS network. Due to the huge volume of data generated by the sensors in the vehicles in ITS, there is a dire need to extract the most important features from the ITS data for classification phase in IDS. Even though, many researchers have worked on building an IDS system in ITS, not much work is done on addressing the aforementioned issue. To address this problem, we have utilized the Moth–Flame Optimization (MFO) in this work. In the proposed work, a MFO based ensemble machine learning model is proposed to classify the IDS dataset in ITS. Firstly the IDS dataset is normalized using the standard-scaler method. Then optimal features from the IDS dataset are chosen by MFO. These optimal features are trained by an ensemble classifier comprising of linear regression, random forest and XGBoost classification algorithms for intelligent decision making. The performance of the proposed model is compared against several state of the art meta-heuristic algorithms based on ensemble models which achieved a superior accuracy and recall of 100%, and precision of 99.5% on shellcode attacks.</p>

Research Output Information

Output type

Research Output:
Contribution to journal
Article
Research
Peer-review

Original language

English

Article number

104935

Journal (Volume, Issue Number)

Microprocessors and Microsystems (Volume 103)

Publication milestones

  • Published - 11/2023

Publication status

Published - 11/2023

ISSN

0141-9331

Publication IDs

  • Scopus: 85174721408

Publication metrics

Metrics

SciVal
FWCI
1.05
Scopus
citations

PlumX, opens in new tab

Mentions
1
Captures
51
Citation count
18

Sustainable Development Goals

  • SDG 11 - Sustainable Cities and Communities
    SDG 11 Sustainable Cities and Communities