• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.425-428
• /
• 2020

본 논문에서는 경계 합성곱 신경망(Convolutional neural network, CNN)기반의 슈퍼 해상도 기법을 이용하여 저해상도 옷감 메쉬를 슈퍼 해상도로 노이즈 없이 안정적으로 표현할 수 있는 기법을 제안한다. 저해상도와 고해상도 메쉬들 간의 쌍은 옷감 시뮬레이션을 통해 얻을 수 있으며, 이렇게 얻어진 데이터를 이용하여 고해상도-저해상도 데이터 쌍을 설정한다. 학습할 때 사용되는 데이터는 옷감 메쉬를 지오메트리 이미지로 변환하여 사용한다. 우리가 제안하는 경계 합성곱 신경망은 저해상도 이미지를 고해상도 이미지로 업스케일링 시키는 이미지 합성기를 학습시키기 위해 사용된다. 테스트 결과로 얻어진 고해상도 이미지가 고해상도 메쉬로 다시 변환되면, 저해상도 메쉬에 비해 주름이 잘 표현되며, 경계 부근에서 나타나는 노이즈 문제가 완화된다. 합성 결과에 대한 성능으로는 전통적인 물리 기반 시뮬레이션보다 약 10배 정도 빠른 성능을 보여준다.

• Journal of the Korean Society of Radiology
• /
• v.11 no.6
• /
• pp.429-435
• /
• 2017

In order to increase the therapeutic effect of radiation, there has been an increase in the use of conventional photon therapy. The intensive care unit should pay more attention to the radiation safety evaluation due to the higher energy and the larger facility compared to the existing Photon treatment. These radiation safety evaluations are mainly performed by using Monte Carlo simulation, and the first thing to be done is geometric modeling. The Heavy-ion treatment facility uses synchrotron as the accelerating device, which is difficult to precisely model geometrically and is mostly modeled briefly. This study investigated the effect of simplification and precise implementation of Dipole magnet among the components of synchrotron acceleration device on the radiation safety evaluation. The results show that the simplified geometric model is overestimated with the precisely implemented geometric model. Therefore, it is considered that the radiological safety evaluation results in more reliable results of the precise geometric modeling.

• Journal of Navigation and Port Research
• /
• v.30 no.8 s.114
• /
• pp.623-629
• /
• 2006

Recently, bemuse of extensive use of hydrographic information, interoperability of Marine Geographic products is very important for efficient use of geographic information systems. Open GIS Consortium(OGC) developed the Open Geodata Interoperability Specification(OpenGIS) to support the interoperability in the distributed environment, especially Geography Markup Language(GML) Implementation Specification. Geography Markup Language is an XML grammar written in XML Schema for the modelling, transporting, and storing of geographic information GML provides a variety of objects for describing geography including features, coordinate reference systems, geometry, topology, time, units of measure and generalized values. S-57 is currently the IHO standard for the exchange of digital hydrographic data. To date, it ms been used almost exclusively for encoding Electronic Navigational Charts(ENCs). Even though, S-57 is intended to support all types of hydrographic data. In order to meet this requirement, a new standard is being developed. GML will be the core encoding rule of IHO's new standard. But there has been no study that tried to develop the GML for ENC that are recognized as base mop in the Marine GIS. This paper presents the process and results on development of application schema for converting ENC into GML.