http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
이건영,고형화,최기호,김복기,Yi Keon-Young,Ko Hyung-Hwa,Choi Ki-Ho,Kim Bok-Ki 한국공학교육학회 2004 공학교육연구 Vol.7 No.4
공학인으로 갖추어야 할 능력 중에서 문제를 인식하고, 이를 공식화 한 후 창의적이며 체계적으로 해결해 나갈 수 있는 능력을 길러주기 위한 방법으로 설계교육을 체계적으로 해 가는 것이 효과적이다. 이를 위하여 본 대학에서는 1학년에서 창의력을 길러주며, 효과적인 설계 추진 과정을 길러주기 위한 공학설계입문을 개설하여 운영하고 있다. 또한 나머지 학년에서도 실험과 설계가 융합된 과목, 이론과 설계가 융합된 과목을 개설하여 각종 설계문제를 해결하도록 교육하고 있다. 본 논문에서는 2학년의 교과목 중 기존의 실험실습 과목을 실험과 설계가 융합된 새로운 개념의 과목으로 개편하여 지난 2년간 운영해온 실적을 분석하여 공학인증에서 요구하는 학습성과 중 팀원으로써의 역할 수행능력이 증가함을 보여준다. 뿐만 아니라, 교과운영 내용을 비교적 상세히 소개하여 공학인증에서 요구하는 설계교육을 효율적으로 운영하는 예시를 보여주며, 주요한 학습성과를 달성하는 한 방법을 제시한다. Well organized design based education is the one of the best way to develop the abilities needed for the engineer such as the recognizing and formulating a problem and then solving it creatively and systematically. In order for this, we prepared a course named 'Introduction to the Engineering Design' for the first-year students, which aims at developing creativity and ability to promote a project. Experiment-design mixed courses and theory-design mixed courses, where students have to solve various design problems, are provided for the higher grade students. In this paper, we are focused on the experiment-design mixed course for the second-year students which has been operating from two years ago. Here we show how the teamwork ability is improved. We also present how to operate the course in detail so that anyone can easily get the way to reach the outcomes needed for the engineers.
이건영(Keon Young Yi),정선재(Sunjae Jeong),서기성(Kisung Seo) 대한전기학회 2020 전기학회논문지 Vol.69 No.2
A machine vision based industrial inspection requires little computation time and localizing defects robustly with high accuracy. Recent mobile and embedded systems require computationally efficient machine intelligence with a deep learning model. In order to improve detection performance and processing time, various network modification methods are proposed. The experiments for defect detection on the metal surfaces data are executed using the various YOLO networks on embedded GPU system Nvidia Tx-1. The results for detection performance and inspection time are compared and analysed. Among them, modified YOLOv2-tiny model shows a better performance in both detection rate and fps.
이건영(Keon Young Yi),서기성(Kisung Seo) 대한전기학회 2020 전기학회논문지 Vol.69 No.2
As commercial drones have been widely used, concerns for collision accidents with people and invading secured properties are emerging. The identification and localization drone is a challenging problem. DroneTracker, commercially available SW, for two dones with Inspire2, Phantom4Pro is tested but the performances of identification and localization are very low. We have suggest a image processing based identification and localization method for drones using the relationship between drone image size and real distance. It is tested for same experimental environments. We have obtained not only clear identification of each drone, but much superior performances of identification and localization. Furthermore the exactness of tracking is very close to the original tracking path.