• Journal of the Korea Institute of Military Science and Technology
• /
• v.20 no.4
• /
• pp.551-557
• /
• 2017

Commanders want to receive quickly scientific and analytic results about the battlefield situation. Unfortunately, decision support system of Army Tactical Command Information System(ATCIS) is restricted to message procedures and searching function based on manual work. In this paper, we propose applying Data Mining to ATCIS for supporting rapid decision making based on the scientific and analytic method. The purpose of this proposal is to efficiently execute the tactical planning and employment of the subordinate units in order to achieve the mission.

• Journal of the Korea Society for Simulation
• /
• v.30 no.3
• /
• pp.1-9
• /
• 2021

Commander and staffs on the battlefield are aware of the situation and, based on the results, they perform military activities through their military decisions. Recently, with the development of information technology, the demand for artificial intelligence to support military decisions has increased. It is essential to identify, collect, and pre-process the data set for reinforcement learning to utilize artificial intelligence. However, data on enemies lacking in terms of accuracy, timeliness, and abundance is not suitable for use as AI learning data, so a training model is needed to collect AI learning data. In this paper, a methodology for learning artificial intelligence was presented using the constructive wargame model exercise data. First, the role and scope of artificial intelligence to support the commander and staff in the military decision-making process were specified, and to train artificial intelligence according to the role, learning data was identified in the Chang-Jo 21 model exercise data and the learning results were simulated. The simulation data set was created as imaginary sample data, and the doctrine of ROK Army, which is restricted to disclosure, was utilized with US Army's doctrine that can be collected on the Internet.