http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
인간-컴퓨터 상호작용을 위한 신경망 알고리즘기반 레이저포인터 검출
정찬웅(Chanwoong Jung),정성문(Sungmoon Jeong),이민호(Minho Lee) 한국산업정보학회 2011 한국산업정보학회논문지 Vol.16 No.1
본 논문에서는 인간-컴퓨터 상호작용 시스템 구현을 위해 신경망 알고리즘을 적용하여 스크린 상의 레이저포인터를 효과적으로 검출하는 방법을 제안하였다. 제안된 신경망 알고리즘은 먼저 레이저포인터가 없는 입력 카메라 영상의 패치들을 학습시킨다. 학습된 선경망은 카메라 영상으로부터 얻은 입력 패치에 대해 출력 값을 발생시킨다. 만약 미세한 레이저빔의 변화가 입력영상에 감지되면 이를 증폭시켜 레이저 빔을 검출하는 역할을 한다. 제안된 시스템은 레이저포인터, 싼 가격의 웹캠 그리고 영상처리 프로그램으로 구현할 수 있다. 그리고 레이저포인터와 컴퓨터의 배경화면 색상이 유사한 경우에도 레이저포인터를 검출할 수 있는 장점이 있으므로 인간-컴퓨터 상호작용 시스템의 성능개선에 기여할 것이다. In this paper, an effective method to detect the laser pointer on the screen using the neural network algorithm for implementing the human-computer interaction system. The proposed neural network algorithm is used to train the patches without a laser pointer from the input camera images, the trained neural network then generates output values for an input patch from a camera image. If a small variation is perceived in the input camera image, amplify the small variations and detect the laser pointer spot in the camera image. The proposed system consists of a laser pointer, low-price web-camera and image processing program and has a detection capability of laser spot even if the background of computer monitor has a similar color with the laser pointer spot. Therefore, the proposed technique will be contributed to improve the performance of human-computer interaction system.
여영준 ( Yeongjun Yeo ),김세준 ( Sejun Kim ),정성문 ( Sungmoon Jung ),이정동 ( Jeong-dong Lee ) 한국생산성학회 2018 生産性論集 Vol.32 No.2
Investments to human capital have important roles in securing human resources with enhanced skill-sets to create new knowledge, and boosting innovative capacity of the knowledge-based economy, However, since it is not possible to expand the investments to human capital indefinitely due to tight budgets of individuals and the government, it is crucial to think about how to effectively generate rates of return to investment in education from the economy-wide perspective. In this study, we use a knowledge-based CGE model to quantitatively analyze the macroeconomic effects of the investments in education focusing on Korea, in order to estimate returns to investments in education in accordance of policy scenarios which cover quantitative expansion of investments in education, as well as the quality improvement of the educational system in terms of the wave of rapid technological innovation. As a result, it is confirmed that the returns to investments in education of Korea can be achieved ranging from 5.39% to 7.29%, depending on the designed policy scenario. In addition, by comparing macroeconomic effects by scenarios, it is found that it is important for Korea economy to establish lifelong education systems that promotes active accumulation and improvement of workers' skills, strengthen on-the-job training and workplace-based vocational training programs, and make reforms of educational system to cope with the rapid changes of technological innovation.
췌장 관 선암종의 디지털 병리이미지에서 AI 활용의 임상적의의
김종광(Jongkwang Kim),배수목(Sumok Bae),윤성미(Seong-Mi Yoon),Ho Young Chung,Myungsoo Kim,정성문(Sungmoon Jeong) 한국정보통신학회 2024 한국정보통신학회논문지 Vol.28 No.1
Pancreatic Ductal Adenocarcinoma (PDAC) is the most common and deadly form of pancreatic cancer. Currently, histopathological diagnosis and prognosis of PDAC are time-consuming and labor-intensive for pathologists. Recent advances in pathological AI research aim to alleviate this. We accumulated training data, distinguishing PDAC areas in Whole Slide Images (WSIs) based on medical findings. Using this data, we trained a deep convolutional neural network for supervised learning to automatically interpret PDAC areas. The AI model achieved high Dice scores and, by visualizing the segmentation results of the predicted histological images, validated that PDAC diagnosis and identification of associated regions are automatically possible, similar to pathologists. Additionally, the AI model, which showed high specificity, suggests its potential as a co-pilot for pathological diagnosis and annotation.