http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
고광일,임혁규 여수대학교 1998 論文集 Vol.13 No.2
In this study six symmetrical tension test specimens were made and tested to investigate their bond behaviors(steel stress, average bond stress, average slip, local slip, and bond stiffness). The compressive strength of concrete which is main experimental variable of this study varied in three steps(σck=203, 458, 706kg/㎠). The principal result of this study was that concentration of bond stress was observed at load-end commonly at the initial load stage of the beam test. As tension load is increased, the bond stress distribution showed difference gradually. It was observed that the location of peak bond stress moved from load-end to supporting point as the load was increased. The magnitude and distribution of bond stress are governed by the location of cracks. From the test, it was observed that the value of average bond stress was linearly proportional to the compressive strength of concrete.
이동규,이기정,황보택근,임혁규 한국콘텐츠학회 2006 한국콘텐츠학회논문지 Vol.6 No.9
This paper proposes an automatic video monitoring system and its application to emergency detection by analyzing human behavior using neural network. The object area is identified by subtracting the statistically constructed background image from the input image. The identified object area then is transformed to the feature vector. Neural network has been adapted for analyzing the human behavior using the feature vector, and is designed to classify the behavior in rather simple numerical calculation. The system proposed in this paper is able to classify the three human behavior: stand, faint, and squat. Experiment results shows that the proposed algorithm is very efficient and useful in detecting the emergency situation. 본 논문에서는 신경망을 이용한 동작분석 기법을 통한 자동화 영상감시시스템의 구현과 응급상황 검출에의 응용을 제안한다. 카메라로부터 입력된 영상은 통계적 배경 모델에 의한 배경 감산법에 의해 객체 영역이 분리되고, 분리된 객체영역의 특징을 표현할 수 있는 특징벡터의 형태로 변형된다. 특징벡터를 이용한 동작분석을 위해 신경망을 사용하였고 간단한 연산에 의해 동작을 구분할 수 있도록 하였다. 본 논문에서는 실험을 위해 stand, faint, squat 등 3가지의 동작 상태를 분류할 수 있도록 하였고, 실험 결과 응급상황을 검출하기위한 알고리즘으로 유용함을 보였다.