• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.429-437
• /
• 2022

Recently, the demand for a QA (Question Answering) system for human-machine communication has increased. Among the QA systems, a closed domain QA system that can handle spatial-related questions is called GeoQA. In this study, a new type of graph database, LPG (Labeled Property Graph) was used to overcome the limitations of the RDF (Resource Description Framework) based database, which was mainly used in the GeoQA field. In addition, GraphQL (Graph Query Language), an API-type query language, is introduced to address the fact that the LPG query language is not standardized and the GeoQA system may depend on specific products. In this study, database was built so that answers could be retrieved when spatial-related questions were entered. Each data was obtained from the national spatial information portal and local data open service. The spatial relationships between each spatial objects were calculated in advance and stored in edge form. The user's questions were first converted to GraphQL through FOL (First Order Logic) format and delivered to the database through the GraphQL server. The LPG used in the experiment is Neo4j, the graph database that currently has the highest market share, and some of the built-in functions and QGIS were used for spatial calculations. As a result of building the system, it was confirmed that the user's question could be transformed, processed through the Apollo GraphQL server, and an appropriate answer could be obtained from the database.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.587-589
• /
• 2021

메타버스 등 VR·AR을 기반으로 하는 가상세계의 현실화가 점차 가까워지고 있다. 이에 따라 가상세계에서 동작하는 게임이나 다양한 소프트웨어들이 등장하고 있어 이에 대한 QA 방안들이 연구되고 있다. VR·AR 게임은 일반 게임과 달리 장비의 사용 등에 따른 시간적, 공간적 특성 등 여러 가지 고려사항들이 있어 QA 진행에 어려움이 있다. 이를 극복하기 위해서는 VR·AR에 대한 이해를 바탕으로 개발팀과의 협조를 통해 콘텐츠를 세분화하여 작은 범위에서 QA를 단계적으로 진행하는 과정이 필요하다. 본 논문에서는 VR, AR 게임을 QA하는 과정에서 고려해야할 사항들을 알아본다.

• Progress in Medical Physics
• /
• v.13 no.3
• /
• pp.109-113
• /
• 2002

In recent years, the radiotherapy equipment has become much more sophisticated, and with the complication comes an increased set of quality assurance (QA) responsibilities. Today's computer controlled linear accelerator requiring QA of not only the radiation integrity, but also the mechanical accuracy of the linear accelerator. The existing QA sheets are adequate for acceptance testing and commissioning but those sheets are somewhat descriptive form for routine QA. establishing the QA sheets for a facility are more efficient if the sheets could estimate the long-term stability for the result of QA. We are going to develope new prototype of mechanical QA sheet to visualize and to verify long-term stability of mechanical QA for clinical linear accelerator. The items included in mechanical QA sheet were 1) gantry rotation, 2) collimator rotation, 3) couch rotation, 4) optical distance indicator (ODI), and 5) laser alignment. We compared new prototype sheet with conventional sheet for several hospitals in Korea for those items. The QA acceptance criteria in this study mainly followed published recommendations. The contents of test for mechanical QA are the following. Confirm that the digital and/or mechanical gantry angle readouts are correct. Verify that digital and/or mechanical readouts of collimator angle agree with the true angle, as determined with the protractor. Measure the light field using a graph paper and compare with the digital readouts. Confirm digital readout accuracy. Verify that the sagittal laser, the left and right lasers, and the ceiling laser intersect at the isocenter. In the design of new QA sheet, we emphasized the representation of the long-term stability of mechanical QA by using Excel program. By using the new prototype QA sheet, we simplified and visualized the mechanical QA process, and could estimate the long-term stability of mechanical error of linear accelerator.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.116-121
• /
• 2017

cQA(Community-based Question Answering) 시스템은 온라인 커뮤니티를 통해 사용자들이 질문을 남기고 답변을 작성할 수 있도록 만들어진 시스템이다. 신규 질문이 인입되면, 기존에 축적된 cQA 저장소에서 해당 질문과 가장 유사한 질문을 검색하고, 그 질문에 대한 답변을 신규 질문에 대한 답변으로 대체할 수 있다. 하지만, 키워드 매칭을 사용하는 전통적인 검색 방식으로는 문장에 내재된 의미들을 이용할 수 없다는 한계가 있다. 이를 극복하기 위해서는 의미적으로 동일한 문장들로 학습이 되어야 하지만, 이러한 데이터를 대량으로 확보하기에는 어려움이 있다. 본 논문에서는 질문이 제목과 내용으로 분리되어 있는 대량의 cQA 셋에서, 질문 제목과 내용을 의미 벡터 공간으로 사상하고 두 벡터의 상대적 거리가 가깝게 되도록 학습함으로써 의사(pseudo) 유사 의미의 성질을 내재화 하였다. 또한, 질문 제목과 내용의 의미 벡터 표현(representation)을 위하여, semi-training word embedding과 CNN(Convolutional Neural Network)을 이용한 딥러닝 기법을 제안하였다. 유사 질문 검색 실험 결과, 제안 모델을 이용한 검색이 키워드 매칭 기반 검색보다 좋은 성능을 보였다.

• Journal of Radiation Protection and Research
• /
• v.36 no.1
• /
• pp.28-34
• /
• 2011

The measurement-based verification for intensity modulated radiation therapy (IMRT) is a time-and labor-consuming procedure. Instead, this study aims to develop a MU fluence reconstruction method for IMRT QA. Total actual fluences from treatment planning system (TPS, Eclipse 8.6, Varian) were selected as a reference. Delivered leaf positions according to MU were extracted by the dynalog file generated after IMRT delivery. An in-house software was develop to reconstruct MU fluence from the acquired delivered leaf position data using MATLAB. We investigated five patient's plans delivered by both step-and-shoot IMRT and sliding window technologies. The total actual fluence was compared with the MU fluence reconstructed by using commercial software (Verisoft 3.1, PTW) and gamma analysis method (criteria: 3%/3 mm and 2%/1 mm). Gamma pass rates were $97.8{\pm}1.33$% and the reconstructed fluence was shown good agreement with RTP-based actual fluence. The fluence from step and shoot IMRT was shown slightly higher agreement with the actual fluence than that from sliding window IMRT. If moving from IMRT QA measurements toward independent computer calculations, the developed method can be used for IMRT QA. A point dose calculation method from reconstructed fluences is under development for the routine IMRT QA purpose.

• Progress in Medical Physics
• /
• v.19 no.2
• /
• pp.120-124
• /
• 2008

In this study, we developed the protopype of QA phantom for image QA including an additional component for image based radiation treatment system. The new phantom considered two main parts: Image quality and fusion accuracy. Image quality part included for daily CT number linearity and spatial resolution, and fusion accuracy part designed to simulate a simple translation-rotation setting. The CT scans of the phantom obtained from conventional CT, MVCT of Tomotherapy unit, and both image sets were satisfied the recommendation of spatial resolution. This phantom was simple and efficient for daily imaging QA, and it is important to provide a new concept of verification of image registration.

• Journal of KIISE
• /
• v.42 no.5
• /
• pp.601-608
• /
• 2015

In order to answer questions successfully on behalf of the human contestant in DeepQA environments such as 'Jeopardy!', the American quiz show, the computer needs to have the capability of fast temporal and spatial reasoning on a large-scale commonsense knowledge base. In this paper, we present a hybrid spatial reasoning algorithm, among various efficient spatial reasoning methods, for handling directional and topological relations. Our algorithm not only improves the query processing time while reducing unnecessary reasoning calculation, but also effectively deals with the change of spatial knowledge base, as it takes a hybrid method that combines forward and backward reasoning. Through experiments performed on the sample spatial knowledge base with the hybrid spatial reasoner of our algorithm, we demonstrated the high performance of our hybrid spatial reasoning algorithm.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.116-121
• /
• 2017

cQA(Community-based Question Answering) 시스템은 온라인 커뮤니티를 통해 사용자들이 질문을 남기고 답변을 작성할 수 있도록 만들어진 시스템이다. 신규 질문이 인입되면, 기존에 축적된 cQA 저장소에서 해당 질문과 가장 유사한 질문을 검색하고, 그 질문에 대한 답변을 신규 질문에 대한 답변으로 대체할 수 있다. 하지만, 키워드 매칭을 사용하는 전통적인 검색 방식으로는 문장에 내재된 의미들을 이용할 수 없다는 한계가 있다. 이를 극복하기 위해서는 의미적으로 동일한 문장들로 학습이 되어야 하지만, 이러한 데이터를 대량으로 확보하기에는 어려움이 있다. 본 논문에서는 질문이 제목과 내용으로 분리되어 있는 대량의 cQA 셋에서, 질문 제목과 내용을 의미 벡터 공간으로 사상하고 두 벡터의 상대적 거리가 가깝게 되도록 학습함으로써 의사(pseudo) 유사 의미의 성질을 내재화 하였다. 또한, 질문 제목과 내용의 의미 벡터 표현(representation)을 위하여, semi-training word embedding과 CNN(Convolutional Neural Network)을 이용한 딥러닝 기법을 제안하였다. 유사 질문 검색 실험 결과, 제안 모델을 이용한 검색이 키워드 매칭 기반 검색보다 좋은 성능을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.769-772
• /
• 2014

Jeopardy 퀴즈쇼와 같은 DeepQA 환경에서 인간을 대신해 컴퓨터가 효과적으로 답하기 위해서는 인물, 지리, 사건, 역사 등을 포함하는 광범위한 지식베이스와 이를 토대로 한 빠른 시공간 추론 능력이 필요하다. 본 논문에서는 대표적인 병렬 분산 컴퓨팅 환경인 하둡/맵리듀스 프레임워크를 이용하여 방향 및 위상 관계를 추론하는 효율적인 대용량의 공간 추론 알고리즘을 제시한다. 본 알고리즘에서는 하둡/맵리듀스 프레임워크의 특성을 고려하여 병렬 분산처리의 효과를 높이기 위해, 지식 분할 문제를 맵 단계에서 해결하고, 이것을 토대로 리듀스 단계에서 효과적으로 새로운 공간 지식을 유도하도록 설계하였다. 또한, 본 알고리즘은 초기 공간 지식베이스로부터 새로운 지식을 유도할 수 있는 기능뿐만 아니라 초기 공간 지식베이스의 불일치성도 미연에 감지함으로써 불필요한 지식 유도 작업을 계속하지 않도록 설계하였다. 본 연구에서는 하둡/맵리듀스 프레임워크로 구현한 대용량 공간 추론기와 샘플공간 지식베이스를 이용하여 성능 분석 실험을 수행하였고, 이를 통해 본 논문에서 제시한 공간 추론 알고리즘과 공간 추론기의 높은 성능을 확인 할 수 있었다.

• Journal of the Korean Society of Radiology
• /
• v.7 no.5
• /
• pp.339-345
• /
• 2013

In foreign countries, the impotance of quality assurance (QA) is increasing, whereas QA evaluation standards are not established properly in Korea. Thus this study was conducted to suggest improved QA evaluation standards and methods by studying/comparing/analyzing the literature in both Korea and foreign countries and prove its suitability through simulated evaluation. result of research in south korea, much check list using the evaluation method subjective, the evaluation of accuracy and reproducibility is meausred in the number of missing. Therefore, attempts to present a clear reference evaluation and objective way to solve the problem, examined the accuracy and reproducibility and 10times of measurement. The results of the simulated evaluation satisfied both proposed evaluation standards and methods. However the QA evaluation standards and methods for the items that are implemented only in Korea and high-contrast spatial resolution could have been established. In this regard, there is a need of further studies on the establishment of QA evaluation standards and methods that suits Korean situation.