본문 바로가기
  • Home

A Virtual Battlefield Situation Dataset Generation for Battlefield Analysis based on Artificial Intelligence

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2022, 27(6), pp.33-42
  • DOI : 10.9708/jksci.2022.27.06.033
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : May 4, 2022
  • Accepted : June 21, 2022
  • Published : June 30, 2022

Eunji Cho 1 Soyeon Jin 1 Yukyung Shin 1 Woosin Lee 1

1한화시스템

Accredited

ABSTRACT

In the existing intelligent command control system study, the analysis results of the commander's battlefield situation questions are provided from knowledge-based situation data. Analysis reporters write these results in various expressions of natural language. However, it is important to analyze situations about information and intelligence according to context. Analyzing the battlefield situation using artificial intelligence is necessary. We propose a virtual dataset generation method based on battlefield simulation scenarios in order to provide a dataset necessary for the battlefield situation analysis based on artificial intelligence. Dataset is generated after identifying battlefield knowledge elements in scenarios. When a candidate hypothesis is created, a unit hypothesis is automatically created. By combining unit hypotheses, similar identification hypothesis combinations are generated. An aggregation hypothesis is generated by grouping candidate hypotheses. Dataset generator SW implementation demonstrates that the proposed method can be generated the virtual battlefield situation dataset.

Citation status

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

This paper was written with support from the National Research Foundation of Korea.