http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
작업자 성격유형 지표 개발을 통한 건설현장 안전관리 기초 연구
홍은빈(Hong, Eunbin),이준성(Yi, June-Seong),노희진(Rho, HeeJin) 대한건축학회 2021 대한건축학회 학술발표대회 논문집 Vol.41 No.2
Accidents at industrial sites and consequent injuries and deaths are a serious social problem. According to the Ministry of Employment and Labor, the estimated economic loss due to industrial accidents has been increasing over the past five years. It is expected that the damage caused by the occurrence of safety accidents will increase further as it is implemented from today. In order to reduce construction accidents, which account for half of deaths in industrial accidents, it is necessary to analyze the root causes of accidents and establish correct measures. Since it is difficult to identify the root cause of construction accidents, it is difficult to present practical preventive measures, so it can be said that the reduction effect of construction accidents is low. Therefore, in order to understand the root cause of construction accidents, it is necessary to utilize various information such as organizational culture and psychology, which seem not to have much to do with accidents on the surface, rather than focusing on the ‘occurrence of accidents’ itself. This study intends to suggest a way to prevent construction accidents starting from the ‘prescribed root cause’ rather than preventing construction accidents starting with the ‘occurrence of an accident’. In this regard, basic research is conducted to utilize the main characteristics of the thinker regarding personality/attitude for safety management. In this study, a literature review is conducted to develop the personality type indicators of workers.
홍은빈(Eunbin Hong),전준호(Junho Jeon),이승용(Seungyong Lee) Korean Institute of Information Scientists and Eng 2016 정보과학회논문지 Vol.43 No.12
This paper proposes a novel aesthetic photo recomposition method using a deep convolutional neural network (DCNN). Previous recomposition approaches define the aesthetic score of photo composition based on the distribution of salient objects, and enhance the photo composition by maximizing the score. These methods suffer from heavy computational overheads, and often fail to enhance the composition because their optimization depends on the performance of existing salient object detection algorithms. Unlike previous approaches, we address the photo recomposition problem by utilizing DCNN, which shows remarkable performance in object detection and recognition. DCNN is used to iteratively predict cropping directions for a given photo, thus generating an aesthetically enhanced photo in terms of composition. Experimental results and user study show that the proposed framework can automatically crop the photo to follow specific composition guidelines, such as the rule of thirds.