본문 바로가기
  • Home

Research on the application of Machine Learning to threat assessment of combat systems

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2023, 28(7), pp.47-55
  • DOI : 10.9708/jksci.2023.28.07.047
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : June 22, 2023
  • Accepted : July 21, 2023
  • Published : July 31, 2023

Seung-Joon Lee 1

1한화시스템

Accredited

ABSTRACT

This paper presents a method for predicting the threat index of combat systems using Gradient Boosting Regressors and Support Vector Regressors among machine learning models. Currently, combat systems are software that emphasizes safety and reliability, so the application of AI technology that is not guaranteed to be reliable is restricted by policy, and as a result, the electrified domestic combat systems are not equipped with AI technology. However, in order to respond to the policy direction of the Ministry of National Defense, which aims to electrify AI, we conducted a study to secure the basic technology required for the application of machine learning in combat systems. After collecting the data required for threat index evaluation, the study determined the prediction accuracy of the trained model by processing and refining the data, selecting the machine learning model, and selecting the optimal hyper-parameters. As a result, the model score for the test data was over 99 points, confirming the applicability of machine learning models to combat systems.

Citation status

* References for papers published after 2023 are currently being built.