http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김병천(Kim Byung Cheon),윤병주(Yoon Byung Joo) 한국정보처리학회 1999 정보처리학회논문지 Vol.6 No.5
In order to learn in dynamic environments, reinforcement learning algorithms like Q-learning, TD(0)-learning, TD(%u03BB)-learning have been proposed, However, most of them have a drawback of very slow learning because the reinforcement value is given when they reach their goal state. In this thesis, we have proposed a reinforcement learning method that can approximate fast to the goal state in maze environments. The proposed reinforcement learning method is separated into global learning and local learning, and then it executes learning. Global learning is a learning that uses the replacing eligibility trace method to search the goal state. In local learning, it propoagates the goal state value that has been searched through global learning to neighboring state, and then searches goal state in neighboring states. We can show through experiments that the reinforcement learning method proposed in this thesis can find out an optimal solution faster than other reinforcement learning methods like Q-learning, TD(0)-learning, TD(%u03BB)-learning.
김병천(Kim Byung Cheon),윤병주(Yoon Byung Joo) 한국정보처리학회 1999 정보처리학회논문지 Vol.6 No.3
Reinforcement learning performs learning through interacting with trial-and-error in dynamic environment. Therefore, in dynamic environment, reinforcement learning method like Q-learning and TD(Temporal Difference)-learning are faster in learning than the conventional stochastic learning method. However, because many of the proposed reinforcement learning algorithms are given the reinforcement value only when the learning agent has reached its goals state, most of the reinforcement algorithms are given the reinforcement value only when the learning agent has reached its goal state, most of the reinforcement algorithms converge to the optimal solution too slowly. In this paper, we present COMREL(COMpressed REinforcement Learning) algorithm for finding the shortest path fast in a maze environment. COMREL compress the given maze environment, select the candidate states that can guide the shortest path in compressed maze environment, and learn only the candidate states to find the shortest path. After comparing COMREL algorithm with the already existing Q-learning and Priortized Sweeping algorithm, we could see that the learning time shortened very much.
중앙냉방시스템의 실시간 준최적제어 적용에 따른 실험적 연구
안병천(Byung-Cheon Ahn),송재엽(Jae-Yeob Song),주영덕(Yong-Duk Joo),김진(Jin Kim) 대한설비공학회 2008 설비공학 논문집 Vol.20 No.7
The near-optimal control algorithm for central cooling system has been developed for minimizing energy consumption while maintaining the comfort of indoor thermal environment in terms of the environmental variables such as time varying indoor cooling load and outdoor temperatures. The optimal set-points of control parameters with near-optimal control are supply air and chilled water temperatures. The near optimal control algorithm has been implemented by using Lab VIEW program in order to analyze energy performance for central cooling control system.
이형일,김병천,Lee, Hyong-Ill,Kim, Byung-Cheon 한국정보처리학회 2003 정보처리학회논문지B Vol.10 No.3
The most important problems in the multi-agent system are to accomplish a goal through the efficient coordination of several agents and to prevent collision with other agents. In this paper, we propose a new control strategy for succeeding the goal of the prey pursuit problem efficiently. Our control method uses reinforcement learning to control the multi-agent system and consider the distance as well as the space relationship between the agents in the state space of the prey pursuit problem. 다중 에이전트 시스템에서 가장 중요한 문제는 여러 에이전트가 서로 효율적인 협동(coordination)을 통해서 목표(goal)를 성취하는 것과 다른 에이전트들과의 충돌(collision) 을 방지하는 것이다. 본 논문에서는 먹이 추적 문제의 목표를 효율적으로 성취하기 위해 새로운 전략 방법을 제안한다. 제안된 제어 전략은 다중 에이전트를 제어하기 위해 강화 학습을 이용하였고, 에이전트들간의 거리관계와 공간 관계를 고려하였다.
중앙난방시스템의 난방수 순환펌프 인버터제어 및 밸브 제어방식에 따른 에너지소모특성 비교연구
송재엽(Jae-Yeob Song),안병천(Byung-Cheon Ahn),주영덕(Yung-Duk Ju),김진(Jin Kim),백승재(Seung-Jae Baek) 대한설비공학회 2010 대한설비공학회 학술발표대회논문집 Vol.2010 No.6
In this study, performance and energy from each flow-rate control method were reviewed with the simulation. The heating system is classified such as fan coil unit and HVAC system currently used in buildings with valve control, and pump inverter control. The simulation analysis program is made by TRNSYS ver. 15 with the actual data. As a result of this study, the central heating system with pump inverter control decreases electricity energy and reduces gas consumption. Inverter control method shows better performance in comparison with valve control one for energy saving.
빌딩 내 중앙냉방시스템의 제어기법에 따른 제어성능 및 에너지 비교에 관한 연구
송재엽(Jae-Yeob Song),안병천(Byung-Cheon Ahn),김진(Jin Kim),백승재(Seung-Jae Baek) 대한설비공학회 2009 대한설비공학회 학술발표대회논문집 Vol.2009 No.-
In this study, performance and energy from each control method were reviewed with the simulation. The methods are classified as systems such as cooling system using fan coil unit and HVAC currently used in buildings, VAV system, and optimal control-algorithm system. The simulation analysis program is made by TRNSYS 15, based on the actual data. As a result of this study, the central cooling system with optimal control-algorithm increases electricity energy and reduces gas consumption. Taken as a whole, it uses energy less than any other existing method.
중앙난방시스템의 Feedforward 및 Feedback 제어에 따른 난방성능특성 연구
송재엽(Jae-Yeob Song),안병천(Byung-Cheon Ahn),주영덕(Yung-Duk Ju),김진(Jin Kim),백승재(Seung-Jae Baek) 대한설비공학회 2010 대한설비공학회 학술발표대회논문집 Vol.2010 No.6
In this study, heating performance from feedforward and feedback control were researched with the simulation. The simulation analysis program is made by TRNSYS ver. 15 with the actual data. The parametric study on proportional factor, control time interval and outdoor air temperatures changes were done to compare control characteristics and energy performance., respectively.
열원 및 공조설비의 최적제어시스템 현장 적용성에 관한 연구
백승재(Seung-Jae Baek),김진(Jin Kim),안병천(Byung-Cheon Ahn),송재엽(Jae-Yeob Song) 대한설비공학회 2009 대한설비공학회 학술발표대회논문집 Vol.2009 No.-
The optimal control system for heat source and HVAC system has been developed for minimizing energy consumption while maintaining the comfort of indoor thermal environment in terms of the environmental variables such as time varying indoor load and outdoor temperatures. The optimal set-points of control parameters are supply air temperature and chilled or hot water temperatures. The optimal control study has been implemented for biosafety laboratory by using TRNSYS simulation program in order to investigate energy performance for heat source and HVAC system.
한재원(Jae-Won Han),이신영(Shin-Young Lee),박진성(Jin-Seong Park),김병천(Byung-Cheon Kim),김동우(Dong-Woo Kim),한창욱(Chang-Wook Han) 대한전기학회 2021 대한전기학회 학술대회 논문집 Vol.2021 No.7
우리나라만의 문제가 아닌 전 세계적으로 풀어야 할 환경오염에 대한 대책을 강구하기 위해 재활용 쓰레기 자동분류 시스템을 생각했다. 아두이노와 센서를 이용해 재활용 쓰레기 종류에 따라 자동으로 분리하는 시스템을 설계하였다.
金漢雄,金炳天 안성산업대학교 1990 論文集 Vol.22 No.-
입력영상에서 특정 물체를 인식하기 위해서는 영상을 분할한 후, 분할된 각각의 영역마다 서로 다른 라벨값을 할당하고, 고유의 라벨값이 할당된 각 영역의 특성을 구하여 물체를 인식한다. 본 논문에서는 기존의 2-패스 라벨링 알고리즘(2-pass labelling algorithm) 보다 빠르고 기억장소의 낭비가 적은 1-패스 라벨링 알고리즘을 제안한다. 이 알고리즘은 서로 다른 라벨값을 가지고 있는 동일 영역에 대해서 부분적인 백트랙킹(backtracking)을 수행하여 같은 라벨값을 할당하고 있다. 끝으로 제안된 알고리즘의 성능을 평가하기 위하여 기존의 2-패스 라벨링 알고리즘과 제안된 알고리즘의 수행시간 및 기억장소 사용량을 비교분석한다.