In this study, to estimate the combination of earthquake magnitude (Mw) and distance (R) corresponding to the design spectrum defined in Korean Building Code (KBC) 2016, the response spectra predicted from the attenuation relationships with the variation of Mw (5.0~7.0) and R (10~30km) are compared with the design spectrum in KBC 2016. Four attenuation relationships, which were developed based on local site characteristics and seismological parameters in Southern Korea and Eastern North America (ENA), are used. As a result, the scenario ground motions represented by the combinations of Mw and R corresponding to the design spectrum for Seoul defined in KBC 2016 are estimated as (1) when R =10 km, Mw = 6.2~6.7; (2) when R = 15 km, Mw = 6.5~6.9; and (3) when R = 20 km, Mw = 6.7~7.1.

This paper proposes a model and train method that can real-time detect objects and distances estimation based on a monocular camera by applying deep learning. It used YOLOv2 model which is applied to autonomous or robot due to the fast image processing speed. We have changed and learned the loss function so that the YOLOv2 model can detect objects and distances at the same time. The YOLOv2 loss function added a term for learning bounding box values x, y, w, h, and distance values z as 클래스ification losses. In addition, the learning was carried out by multiplying the distance term with parameters for the balance of learning. we trained the model location, recognition by camera and distance data measured by lidar so that we enable the model to estimate distance and objects from a monocular camera, even when the vehicle is going up or down hill. To evaluate the performance of object detection and distance estimation, MAP (Mean Average Precision) and Adjust R square were used and performance was compared with previous research papers. In addition, we compared the original YOLOv2 model FPS (Frame Per Second) for speed measurement with FPS of our model.

하천 홍수해석 분야에서 가장 널리 이용되고 있는 1차원 동수역학 수치모형의 입력자료는 상하류단 경계조건, 조도계수, 하도단면 등이며, 계산 시간간격 및 거리간격의 선정은 계산결과의 정확성, 안정성, 효율성 확보를 위한 핵심 요소이다. 본 연구에서는 기존 단면간격 선정기법의 이론적 배경을 검토하였고, 매 시간단계별로 도출되는 흐름특성을 반영하여 계산거리간격을 추정하는 가변 계산거리간격 추정 기법을 제안하였다. 제안된 기법을 1차원 부정류 수치모형과 연계하