• Journal of The Korean Institute of Defense Technology
• /
• v.5 no.3
• /
• pp.1-7
• /
• 2023

Recently, in the defense field, efforts are being made to collect data by building data centers to incorporate artificial intelligence technology. Weapon system training data can be used as input data for artificial intelligence models and can be used as high-quality data to maximize training performance and develop military strategies. However, training data contains personal information such as the names and military numbers of the personnel who operated the equipment, and training records that reveal the characteristics of the weapon system. If such data is passed on to the enemy, not only the specifications and performance of the weapon system but also the proficiency of each operator may be exposed. In this paper, we propose a pseudonym processing methodology for education and training data security and also suggest a direction for revising related laws.

• (The)Study of the Eastern Classic
• /
• no.57
• /
• pp.263-299
• /
• 2014

This study aims to look into weapons names mentioned in "Unhae", a book of traditional martial arts annotated into Korean. Comprehensive conclusions drawn from this are as follow. First, the annotated martial arts book is compiled to the order of Muyejaebo of year 1598, Muyejaebobunyuksokjib(A annotated attachment to Mooyejebo) of year 1610, Moojesinbo of year 1759, and Muyedobotongji of year 1790. Second, in the martial arts book are a total of 24 weapons with 4 types of spears, swords, bare hands & poles, and horseback weapons. Weapon names of ?Unhae? taken into detailed analysis, spears are 5 types of Jangchang (long spears), Jukjangchang (long spears made of bamboo), Keechang (flagged spears), Dgangpa (skewered spears), and Nangseon (forked spears). Swords are 10 types of Ssangsoodo (two-handed swords), Yedo (pointed swords), Waegum (Japanese swords), Waegumkyojun (Japanese battle swords), Jedokgum (Admiral's swords), Bongukgum (native swords), Ssanggum (coupled swords), Woldo (moon swords), Hyupdo (narrow swords), Deungpae (swords made of rattan). Bare hands & poles are 3 types of Gwonbeop (fists), 7070 Gonbang (clubs), and Pyeon-gon (flailed clubs). Horseback weapons are 6 types of flagged spears, MasangSsanggum (coupled horseback spears), MasangWoldo (horseback moon swords), MasangPyeon-gon (horseback flailed clubs), Kyukgoo (striking poles), and Masangjae (horse postures). Third, spears of the martial arts book, "Unhae" had the function as long weapons and were used for military drills of the infantry. Swords had the function as short weapons, and were used for military drills of the infantry. Bare hands & poles had the function as short weapons and were used for military drills of the infantry. Horseback weapons composed of short and long weapons were used for military drills of the cavalry. In addition to these, Kyukgoo (striking poles), and Masangjae (horse postures) were martial arts to which entertaining elements were added. Fourth, the difference in its compiling is that Mooyejebo and A annotated attachment to Mooyejebo place both Chinese characters and Korean annotation in the context together with introduction of weapons while Moojedobo Tongji explains weapons in Chinese and compiles a separate copy of Korean annotation that explains mainly postures in each lineage of martial arts for soldiers to acquire practical skills.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.11-17
• /
• 2020

In this paper, we propose a method to build a knowledge base based on natural language processing for intelligent battlefield awareness service. The current command and control system manages and utilizes the collected battlefield information and tactical data at a basic level such as registration, storage, and sharing, and information fusion and situation analysis by an analyst is performed. This is an analyst's temporal constraints and cognitive limitations, and generally only one interpretation is drawn, and biased thinking can be reflected. Therefore, it is essential to aware the battlefield situation of the command and control system and to establish the intellignet decision support system. To do this, it is necessary to build a knowledge base specialized in the command and control system and develop intelligent battlefield awareness services based on it. In this paper, among the entity names suggested in the exobrain corpus, which is the private data, the top 250 types of meaningful names were applied and the weapon system entity type was additionally identified to properly represent battlefield information. Based on this, we proposed a way to build a battlefield-aware knowledge base through mention extraction, cross-reference resolution, and relationship extraction.