• 한국군사과학기술학회지
• /
• 제16권3호
• /
• pp.295-303
• /
• 2013

The Operational Mode Summary/Mission Profile(OMS/MP) is a document which describes how a system or training device will be used in wartime and/or peacetime at the time it is field with focus on the future. OMS/MP is also typically used for the RAM goal setting in an early phase of weapon system development. This paper provides OMS/MP and RAM goal of the Next-MILSATCOM which is following military satellite system after ANASIS. We propose operational concepts, user-side OMS/MP model and RAM goal.

• 한국군사과학기술학회지
• /
• 제9권1호
• /
• pp.60-71
• /
• 2006

With the increased reliance on M & S(Modeling & Simulation) in military training, defense analysis, and system acquisition. The credibility of M & S becomes even more critical issue in the M & S application community. In this paper, we have introduced the VV & A(Verification, Validation and Accreditation) concept of M & S for the assurance of its credibility, and proposed the VV & A model applicable to a military simulator development with the illustrative example of MSAM(Medium range-Surface to Air Missile) system simulator.

• 한국군사과학기술학회지
• /
• 제13권1호
• /
• pp.147-155
• /
• 2010

Landcover information of access-denied area was extracted from low-medium and high resolution satellite image. Training for supervised classification was performed to refer visually by landcover map which is made and distributed from The Ministry of Environment. The classification result was compared by relating data of FACC land classification system. As we rasterize digital military map with same pixel size of satellite classification, the accuracy test was performed by image to image method. In vegetation case, ancillary data such as NDVI and image for seasons are going to improve accuracy. FACC code of FDB need to recognize the properties which can be automated.

• 한국군사과학기술학회지
• /
• 제26권2호
• /
• pp.139-148
• /
• 2023

Safety standards for long-range artillery ammunition test and training sites follow the US artillery shooting range safety zone standards. Although the South Korean geographical conditions of shooting ranges are different from those of the United States, there is no safety standard reflecting the South Korean topographical characteristics. Probable error associated with the shooting range, trajectory should be considered in establishing the safety standards. In this study, we present the safety standards for the ammunition testing site suitable for the Korean situation, with applying a concept of trajectory and probable error differed by ammunition type, which are currently confirmed by the South Korean Army's artillery shooting.

• 한국군사과학기술학회지
• /
• 제23권2호
• /
• pp.139-146
• /
• 2020

The camouflage pattern was difficult to distinguish from the surrounding background, so it was difficult to classify the object and the background image when the color image is used as the training data of deep-learning. In this paper, we proposed a red-green color blindness image transformation method using the principle that people of red-green blindness distinguish green color better than ordinary people. Experimental results show that the camouflage soldier's recognition performance improved by proposed a deep learning model of the ensemble technique using the imitated red-green-blind image data and the original color image data.

• 한국군사과학기술학회지
• /
• 제11권1호
• /
• pp.33-42
• /
• 2008

Many advanced countries including the U.S. consider defense standardization as a critical task for the efficient acquisition and effective operation of weapon systems and have implemented the appropriate standardization policy by synchronizing the defense acquisition strategies and nation standardization policy with defense standardization. It is required to develop the long-term defense standardization policy that can cope with the future domestic and international defense environmental changes. Therefore, it is an inevitable task to investigate the standardization trends and strategy in the domestic and international perspectives. The study aims to provide the vision of defense standardization policy, act/regulation, organization/personnel, education/training and information system.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2004년도 춘계 종합학술대회 논문집
• /
• pp.429-433
• /
• 2004

컴퓨터 시뮬레이션을 통해 실제 전투 자산을 가동하지 않고 실전과 같은 전투경험을 부여하기 위해서는 데이터베이스를 포함한 페더레이트(federate)간의 연동(federation)이 네트워크상에서 잘 수행되어야 한다. 이에 본 논문에서는 전장 데이터(이하 액티브 패킷)의 신속한 전달을 필요로 하는 실제상황과 유사한 전장공간을 구축할 수 있도록 액티브 네트워크 상에서 페더레이트(혹은 액티브 노드) 간의 효율적인 트래픽 처리가 가능한 가상 전장 환경을 구성하고, 이에 대한 유효성을 모의 실험을 통하여 검증하였다.

• Bulletin of the Korean Chemical Society
• /
• 제35권2호
• /
• pp.655-658
• /
• 2014

• 한국군사과학기술학회지
• /
• 제13권5호
• /
• pp.841-851
• /
• 2010

We examine interoperability for integrated training simulation of a mechanized infantry battalion that uses a war game model of Korean army, Combat 21, and virtual simulators of K1 tanks. We discuss issues and problems for integrated simulation of the virtual and constructive models, including differences between the model scopes, model resolutions, engagement algorithms, and data consistency and training audiences of the war game model and virtual simulators. From these, we identify interoperability requirements. We propose ways of resolving the problems using a model converter.

• 한국군사과학기술학회지
• /
• 제26권4호
• /
• pp.361-370
• /
• 2023

Swarm has recently become a critical component of offensive and defensive systems. Multi-agent reinforcement learning(MARL) empowers swarm systems to handle a wide range of scenarios. However, the main challenge lies in MARL's scalability issue - as the number of agents increases, the performance of the learning decreases. In this study, transfer learning is applied to advanced MARL algorithm to resolve the scalability issue. Validation results show that the training efficiency has significantly improved, reducing computational time by 31 %.