Comparison on Machince Learning Techniques for Intrusion Detection in Wireless Sensor Network 


Vol. 47,  No. 11, pp. 1804-1814, Nov.  2022
10.7840/kics.2022.47.11.1804


PDF
  Abstract

Sensors constituting a wireless sensor network have open and distributed characteristics, and are very vulnerable to attacks due to factors such as limited resources of sensor nodes and real-time data collection. Attackers use these vulnerabilities to attempt attacks such as injecting fake messages and wasting network resources. Among these attacks, tree-based machine learning is used to analyze and classify patterns for DoS attacks. In the performance comparison analysis of machine learning, differences in training methods, feature importance, and characteristics of each attack type were considered. For comparative analysis of the experimental results, F1-Score was used among the machine learning performance evaluation indicators. Through the analysis results, it was proved that the decision tree with a single tree structure showed the lowest performance, and the boosting-based model, which trains the model using weights, showed high performance.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

S. Lim and M. Yoo, "Comparison on Machince Learning Techniques for Intrusion Detection in Wireless Sensor Network," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 11, pp. 1804-1814, 2022. DOI: 10.7840/kics.2022.47.11.1804.

[ACM Style]

SungWook Lim and Myungsik Yoo. 2022. Comparison on Machince Learning Techniques for Intrusion Detection in Wireless Sensor Network. The Journal of Korean Institute of Communications and Information Sciences, 47, 11, (2022), 1804-1814. DOI: 10.7840/kics.2022.47.11.1804.

[KICS Style]

SungWook Lim and Myungsik Yoo, "Comparison on Machince Learning Techniques for Intrusion Detection in Wireless Sensor Network," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 11, pp. 1804-1814, 11. 2022. (https://doi.org/10.7840/kics.2022.47.11.1804)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880