• Journal of the Korea Society for Simulation
• /
• v.29 no.1
• /
• pp.39-46
• /
• 2020

The utilization of artificial intelligence (AI) in the engagement has been a key research topic in the defense field during the last decade. To pursue this utilization, it is imperative to acquire a realistic simulation to train an AI engagement agent with a synthetic, but realistic field. This paper is a case study of training an AI agent to operate with a hardware realism in the air-warfare dog-fighting. Particularly, this paper models the pursuit of an opponent in the dog-fighting setting with a gun-only engagement. In this context, the AI agent requires to make a decision on the pursuit style and intensity. We developed a realistic hardware simulator and trained the agent with a reinforcement learning. Our training shows a success resulting in a lead pursuit with a decreased engagement time and a high reward.

• Journal of Veterinary Clinics
• /
• v.16 no.1
• /
• pp.226-229
• /
• 1999

A 4-year old male Pitbull terrier dog was presented with a history of nasal discharge of left side and dyspnea for 3 days. This dog had a bitewound on the head due to dog-fighting two weeks ago. There was no abnomality except mild anemic sign on blood examination. Frontal projection of radiographs was taken. This was diagnosed as frontal sinusitis. After skin incision on frontal head, a silicone tube was inserted into the affected frontal sinus. Abscess of the frontal sinus was drainaged and irrigated with saline solution containing trypsin and cephazolin. This patient who also treated with enrofloxacin was recovered completely.

• Journal of the Korea Society for Simulation
• /
• v.30 no.1
• /
• pp.139-152
• /
• 2021

Simulations enable virtually experiencing rare events as well as analytically analyzing such events. Defense modeling and simulation research and develops the virtual and the constructive simulations to support these utilizations. These virtual and constructive(VC) simulations can interoperate to simultaneously virtual combat experience as well as evaluations on tactics and intelligence of combat entities. Moreover, recently, for artificial intelligence researches, it is necessary to retrieve human behavior data to proceed the imitation learning and the inverse reinforcement learning. The presented work illustrates a case study of VC interoperations in the aircombat scenario, and the work analyze the collected human behavior data from the VC interoperations. Through this case study, we discuss how to build the VC simulation in the aircombat area and how to utilize the collected human behavior data.

• Journal of Veterinary Clinics
• /
• v.32 no.1
• /
• pp.9-15
• /
• 2015

Purpose of this study is to determine the reasonable portal approach for thoracoscopic right middle lung lobectomy in small sized dogs under 10 kg. Ten healthy beagle dogs weighing $8.67{\pm}0.49kg$ were included. Under general anesthesia, one-lung ventilation (1LV) was achieved using endobronchial blocker with guidance of fiber-optic bronchoscope. Two portal approaches were used; 8-6-10 intercostal space (ICS) and 8-6-5 ICS approach. Thoracoscopic right middle lung lobectomy was performed using endoscopic linear self-cutting stapler and specimen retrieval bag. Each approach was evaluated by scoring 0; bad, 1; endurable, 2; good, 3; excellent in following five category, 1) visualization, 2) triangulation; instrumental sword fighting in the thoracic cavity, 3) approach to hilar pedicle; application of stapler, 4) any obstacles in applicating Lap Bag, and 5) the operator's convenience. Favorable working space was secured by 1LV and thoracoscopic right middle lung lobectomy was successfully completed in all dogs. There was no need to change the portal location and iatrogenic complication. Most of scores were good to excellent in both approaches. Consequently, both approaches are feasible methods for thoracoscopic right middle lung lobectomy with one lung ventilation using endoscopic linear self-cutting stapler in dogs weighing less than 10 kg.