@article{ART003280406},
author={Hyeon-Mo Kim and Won-Seok Jang and Hyoung-Jo Huh and Ju-Mi Park and Woo-Hyeon Moon and Seo-Ho Lee and Ji-Seok Yoon},
title={An Efficient Approach for Constructing Intelligent Naval Combat System Dataset based on Combat Structural Data Cleansing Techniques},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2025},
volume={30},
number={12},
pages={87-100}
TY - JOUR
AU - Hyeon-Mo Kim
AU - Won-Seok Jang
AU - Hyoung-Jo Huh
AU - Ju-Mi Park
AU - Woo-Hyeon Moon
AU - Seo-Ho Lee
AU - Ji-Seok Yoon
TI - An Efficient Approach for Constructing Intelligent Naval Combat System Dataset based on Combat Structural Data Cleansing Techniques
JO - Journal of The Korea Society of Computer and Information
PY - 2025
VL - 30
IS - 12
PB - The Korean Society Of Computer And Information
SP - 87
EP - 100
SN - 1598-849X
AB - The combat management system(CMS) integrates sensors and weapon systems to effectively perform a series of procedures from detection of targets to engagement. In this paper, we propose a method of improving the generalization performance of the CMS core functions by refining the message-based structural data. The proposed method refines data contamination, including outliers, by employing publicly available cleansing algorithms and cluster-based re-sampling techniques. Two artificial intelligence tasks were defined for the engagement function of CMS, and models trained on contaminated and refined datasets were compared and analyzed. When generating data, data based on sensor failure and mission bias scenario were collected and used as experimental data. The performance differences before and after data refinement across various models were analyzed, and effective combinations of cleansing algorithms were estimated. In addition, the experimental evaluation using the sum of weighting scenarios was conducted to verify the performance improvement after data refinement, and statistical tests were performed in order to confirm its significance. Through comprehensive experiments, it was verified that the pair of LightGBM and AutoEncoder outperformed other approaches in both regression and classification tasks. This study is expected that will be usefully used for developing AI-based intelligent combat management system and reviewing the applicability of new technologies in a maritime domain.
KW - Combat Management System(CMS);Data cleansing;Tabular data;Engagement dataset;;Intelligent combat system
DO -
UR -
ER -
Hyeon-Mo Kim, Won-Seok Jang, Hyoung-Jo Huh, Ju-Mi Park, Woo-Hyeon Moon, Seo-Ho Lee and Ji-Seok Yoon. (2025). An Efficient Approach for Constructing Intelligent Naval Combat System Dataset based on Combat Structural Data Cleansing Techniques. Journal of The Korea Society of Computer and Information, 30(12), 87-100.
Hyeon-Mo Kim, Won-Seok Jang, Hyoung-Jo Huh, Ju-Mi Park, Woo-Hyeon Moon, Seo-Ho Lee and Ji-Seok Yoon. 2025, "An Efficient Approach for Constructing Intelligent Naval Combat System Dataset based on Combat Structural Data Cleansing Techniques", Journal of The Korea Society of Computer and Information, vol.30, no.12 pp.87-100.
Hyeon-Mo Kim, Won-Seok Jang, Hyoung-Jo Huh, Ju-Mi Park, Woo-Hyeon Moon, Seo-Ho Lee, Ji-Seok Yoon "An Efficient Approach for Constructing Intelligent Naval Combat System Dataset based on Combat Structural Data Cleansing Techniques" Journal of The Korea Society of Computer and Information 30.12 pp.87-100 (2025) : 87.
Hyeon-Mo Kim, Won-Seok Jang, Hyoung-Jo Huh, Ju-Mi Park, Woo-Hyeon Moon, Seo-Ho Lee, Ji-Seok Yoon. An Efficient Approach for Constructing Intelligent Naval Combat System Dataset based on Combat Structural Data Cleansing Techniques. 2025; 30(12), 87-100.
Hyeon-Mo Kim, Won-Seok Jang, Hyoung-Jo Huh, Ju-Mi Park, Woo-Hyeon Moon, Seo-Ho Lee and Ji-Seok Yoon. "An Efficient Approach for Constructing Intelligent Naval Combat System Dataset based on Combat Structural Data Cleansing Techniques" Journal of The Korea Society of Computer and Information 30, no.12 (2025) : 87-100.
Hyeon-Mo Kim; Won-Seok Jang; Hyoung-Jo Huh; Ju-Mi Park; Woo-Hyeon Moon; Seo-Ho Lee; Ji-Seok Yoon. An Efficient Approach for Constructing Intelligent Naval Combat System Dataset based on Combat Structural Data Cleansing Techniques. Journal of The Korea Society of Computer and Information, 30(12), 87-100.
Hyeon-Mo Kim; Won-Seok Jang; Hyoung-Jo Huh; Ju-Mi Park; Woo-Hyeon Moon; Seo-Ho Lee; Ji-Seok Yoon. An Efficient Approach for Constructing Intelligent Naval Combat System Dataset based on Combat Structural Data Cleansing Techniques. Journal of The Korea Society of Computer and Information. 2025; 30(12) 87-100.
Hyeon-Mo Kim, Won-Seok Jang, Hyoung-Jo Huh, Ju-Mi Park, Woo-Hyeon Moon, Seo-Ho Lee, Ji-Seok Yoon. An Efficient Approach for Constructing Intelligent Naval Combat System Dataset based on Combat Structural Data Cleansing Techniques. 2025; 30(12), 87-100.
Hyeon-Mo Kim, Won-Seok Jang, Hyoung-Jo Huh, Ju-Mi Park, Woo-Hyeon Moon, Seo-Ho Lee and Ji-Seok Yoon. "An Efficient Approach for Constructing Intelligent Naval Combat System Dataset based on Combat Structural Data Cleansing Techniques" Journal of The Korea Society of Computer and Information 30, no.12 (2025) : 87-100.
