http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
이동제,김인식,이민중,최영규 대한전기학회 2003 전기학회논문지 D Vol.53 No.8
The acts of biological immune system are similar to the navigation for autonomous mobile robots under dynamically changing environments. In recent years, many researchers have studied navigation algorithms using artificial immune networks. Conventional artificial immune algorithms consist of an obstacle-avoidance behavior and a goal-reaching behavior. To select a proper action, the navigation algorithm should combine the obstacle-avoidance behavior with the goal-reaching behavior. In this paper, the neural network is employed to combine the behaviors. The neural network is trained with the surrounding information. the outputs of the neural network are proper combinational weights of the behaviors in real-time. Also, a velocity control algorithm is constructed with the artificial immune network. Through a simulation study and experimental results for a autonomous mobile robot, we have shown the validity of the proposed navigation algorithm.
라이다 및 카메라 융합을 이용한 선박 크기 추정 기반 접안 상태 관측 시스템
이동제,김한근,전대윤,이승목 제어·로봇·시스템학회 2024 제어·로봇·시스템학회 논문지 Vol.30 No.3
Berthing accidents are serious problems that can cause damage to the ship and port facilities. Accident prevention and management are critical challenges in port operations and maritime safety. This study proposes a ship berthing monitoring system that combines camera image data and LiDAR point cloud data. The camera recognizes the ship and estimates its size. The LiDAR sensor uses the iterative closest point (ICP) algorithm to calculate the distance between the ship, the quay wall, and the ship’s approach direction. Additionally, to overcome the short detection range of LiDAR, we propose a sensor fusion method that predicts the berthing direction and size of the ship and creates a new point cloud to expand the detection range. Field tests are conducted in a real port to validate the performance of the proposed camera and LiDAR fusion-based monitoring system. The estimation results of the proposed monitoring system are compared with the ship’s Automatic Identification System (AIS) results to validate its performance.
이동제,최영규,Lee, Dong-Je,Choi, Young-Kiu 한국정보통신학회 2007 한국정보통신학회논문지 Vol.11 No.11
본 논문은 초음파 센서에 의해 인식된 정보를 항체와 항원으로 모델링 된 퍼지 인공 명역망에 의한 하위 행위기와 상위 행동 선택기로 설계된 자율이동로봇 시스템에 관한 연구이다. 외부 환경과 행동 패턴의 관계는 매우 많은 조합이 가능하다. 이러한 복잡한 관계 속에서 행동의 우선 순위를 어떻게 결정하는가 하는 문제가 가장 중요하다. 이런 복잡한 결정을 위해 본 논문에서는 퍼지 인공 면역망 알고리즘을 제시하고, 컴퓨터 시뮬레이션에 의해 제안된 자율이동로봇의 행위 선택기의 유용성을 보여준다. In this paper addresses the low-level behavior of fuzzy control and the high-level behavior selector for Autonomous Mobile Robots(AMRs) based on a Fuzzy Artificial Immune Network. The sensing information that comes from ultrasonic sensors is the antigen it, and stimulates antibodies. There are many possible combinations of actions between action-patterns and external situations. The question is how to handle the situations to decide the proper action. We propose a fuzzy artificial immune network to solve the above problem. and the computer simulation for an AMR action selector shows the usefulness of the proposed action selector.
국군간호사관생도의 영어 학습 도우미(APP) 개발을 위한 요구도
이동제,조문환,이승환 국군간호사관학교 군건강정책연구소 2019 군진간호연구 Vol.37 No.1
Purpose: The study investigates demands of Korea Armed Forces Nursing Academy (KAFNA) cadets to develop an English learning application to facilitate learning process. Methods: This descriptive survey was conducted to 120 KAFNA cadets divided into 5 groups according to level of TOEIC scores using self-report questionnaires between June 10 and September 5 in 2017. Results: The group below 600 points in TOEIC reported speaking as difficult, wordbook as desired function, and movies as desired content. The group between 601~700 points reported speaking as difficult, recording as desired function and movies as desired content. The group between 701~800 points and the group between 801~900 points reported speaking as difficult, recording as desired function, and TV shows as desired content. The group more than 900 points reported speaking as difficult, text revision, wordbook, and recording as desired functions, and TV shows as desired content. Conclusion: The results indicate that an application for KAFNA cadets should focus on improving its users' speaking skills through functions such as voice-recording and contents such as American TV shows and movies.
이동제(Dong-Je Lee),김형만(Hyung-Man Kim),이동호(Dong-Ho Lee),홍기호(Ki-Ho Hong),배명환(Myung-\han Bae) 한국자동차공학회 2002 한국자동차공학회 지부 학술대회 논문집 Vol.2002 No.3
In the present study, surface temperature measurement of the cylinder head was done in a diesel Engine by K-type and E-type thermocouples. The thermocouples are welded on the surface of the cylinder head to measure the surface temperature, and drawn out through the hole of safety valve. A connector is designed and manufactured in the hole of safety valve, and Ceramic bond was used to prevent the leakage of combustion gas. Surface temperature distribution of the cylinder head have been measured with various engine torque. The results show that the surface temperature of exhaust valve side is much higher than other parts.<br/>
입력성형필터 최적 설계를 위한 인공 명역망과 유전 알고리즘 비교에 관한 연구
이동제(Dong-Je Lee),최영규(Young-Kiu Choi) 대한전기학회 2010 전기학회논문지 Vol.59 No.8
Recently to increase the productivity and improve the quality in the industrial process, suppressing the residual vibration in motion control systems becomes the essential problem to solve. One of the methods to suppress the residual vibration is the input shaping technique. It is based on parameters of the system model; however, the parameters are usually difficult to obtain. This paper shows the effects of the residual vibration caused by the variation of the general velocity profile for the system with two vibration modes, and also shows the effects of the input shaping filter based on the parameters of system model. Finally, the simulation results show that the proposed input shaping filter using an artificial immune algorithm is more effective for suppressing residual vibrations than genetic algorithm.