• Journal of Information Processing Systems
• /
• 제2권3호
• /
• pp.189-193
• /
• 2006

In this study we propose an automatic reading system for diagnostic DNA chips. We define a general specification for an automatic reading system and propose a possible implementation method. The proposed system performs the whole reading process automatically without any user intervention, covering image acquisition, image analysis, and report generation. We applied the system for the automatic report generation of a commercialized DNA chip for cervical cancer detection. The fluorescence image of the hybridization result was acquired with a $GenePix^{TM}$ scanner using its library running in HTML pages. The processing of the acquired image and the report generation were executed by a component object module programmed with Microsoft Visual C++ 6.0. To generate the report document, we made an HWP 2002 document template with marker strings that were supposed to be searched and replaced with the corresponding information such as patient information and diagnosis results. The proposed system generates the report document by reading the template and changing the marker strings with the resultant contents. The system is expected to facilitate the usage of a diagnostic DNA chip for mass screening by the automation of a conventional manual reading process, shortening its processing time, and quantifying the reading criteria.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제3권12호
• /
• pp.553-564
• /
• 2014

본 논문은 지금까지의 소셜미디어 분석과 분석보고서 생성의 세 가지 문제점을 해결하기 위해서 소셜 빅데이터 마이닝에 기반한 이슈분석보고서 자동 생성 시스템을 제안한다. 세 가지 문제점은 분석의 고립성, 전문가의 주관성과 고비용에 기인한 정보의 폐쇄성이다. 시스템은 자연언어 질의분석, 이슈분석, 소셜 빅데이터 분석, 소셜 빅데이터 상관성분석과 자동 보고서 생성으로 구성된다. 생성된 보고서의 유용성을 평가하기 위해, 본 논문에서는 리커트척도를 사용하였고, 빅데이터 분석 전문가 2명이 평가하였다. 평가결과는 리커트 척도 평가에서 보고서의 품질이 비교적 유용하고 신뢰할 수 있는 것으로 평가되었다. 보고서 생성의 저비용, 소셜 빅데이터의 상관성 분석과 소셜 빅데이터 분석의 객관성 때문에, 제안된 시스템이 소셜 빅데이터 분석의 대중화를 선도할 것으로 기대된다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권2호
• /
• pp.45-50
• /
• 2020

A Language model with neural networks commonly trained with likelihood loss. Such that the model can learn the sequence of human text. State-of-the-art results achieved in various language generation tasks, e.g., text summarization, dialogue response generation, and text generation, by utilizing the language model's next token output probabilities. Monotonous and boring outputs are a well-known problem of this model, yet only a few solutions proposed to address this problem. Several decoding techniques proposed to suppress repetitive tokens. Unlikelihood training approached this problem by penalizing candidate tokens probabilities if the tokens already seen in previous steps. While the method successfully showed a less repetitive generated token, the method has a large memory consumption because of the training need a big vocabulary size. We effectively reduced memory footprint by encoding words as sequences of subword units. Finally, we report competitive results with token level unlikelihood training in several automatic evaluations compared to the previous work.

• 대한공간정보학회지
• /
• 제1권2호
• /
• pp.131-141
• /
• 1993

본 논문에서는 선로시설 관리시스팀(TOMS)의 주요기능인 선로도면의 입출력 및 시설현황 통계보고서 작성 등의 기본적인 기능을 넘어서서 방대한 선로시설 데이타베이스의 효용성을 극대화시키고 단순한 시설관리 측면뿐만 아니라 가입자 서비스 증대를 목표로 선로시설과 가입자 정보를 통합적으로 관리할 수 있는 가입자시설 종합관리시스팀(SIMS)의 개발에 대해서 기술한다. SIMS가 제공하는 기능으로는 전화 가설용 공사명령서 제작, 외선자동선정, 케이블추적 및 구간별 유휴 심선 관리, 선전번 데이타 관리 및 통계보고서 작성, 가입자, 지번 정보관리 등이 있다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 추계학술대회 논문집 학회본부 B
• /
• pp.582-584
• /
• 1999

Generator has synchronized with power Network after build-up output voltage. In order to prevent a current surge when synchronizing, the conditions such as identical no-load voltages identical no-load frequencies and identical phase positions must be met between generator voltage and network voltage. Hydro-Pump generators or Gas-turbine generators, Co-generation Generators that serve peak load of network are synchronized many times. So, Automatic Synchronizing Circuits are very important service. This report apply Diagnosis methods the Automatic Synchronizing Circuits(Device) by developing simulator.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2768-2787
• /
• 2023

As an important research direction of the application of computer science in the medical field, the automatic generation technology of radiology report has attracted wide attention in the academic community. Because the proportion of normal regions in radiology images is much larger than that of abnormal regions, words describing diseases are often masked by other words, resulting in significant feature loss during the calculation process, which affects the quality of generated reports. In addition, the huge difference between visual features and semantic features causes traditional multi-modal fusion method to fail to generate long narrative structures consisting of multiple sentences, which are required for medical reports. To address these challenges, we propose a multi-feature optimization Transformer (MFOT) for generating radiology reports. In detail, a multi-dimensional mapping attention (MDMA) module is designed to encode the visual grid features from different dimensions to reduce the loss of primary features in the encoding process; a feature pre-fusion (FP) module is constructed to enhance the interaction ability between multi-modal features, so as to generate a reasonably structured radiology report; a detail enhanced attention (DEA) module is proposed to enhance the extraction and utilization of key features and reduce the loss of key features. In conclusion, we evaluate the performance of our proposed model against prevailing mainstream models by utilizing widely-recognized radiology report datasets, namely IU X-Ray and MIMIC-CXR. The experimental outcomes demonstrate that our model achieves SOTA performance on both datasets, compared with the base model, the average improvement of six key indicators is 19.9% and 18.0% respectively. These findings substantiate the efficacy of our model in the domain of automated radiology report generation.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.24-27
• /
• 2003

High-resolution satellite images at sub-5m footprint are becoming increasingly available to the earth observation community and their respective clients. The related cameras are all using linear array CCD technology for image sensing. The possibility and need for accurate 3D object reconstruction requires a sophisticated camera model, being able to deal with such sensor geometry. We have recently developed a full suite of new methods and software for the precision processing of this kind of data. The software can accommodate images from IKONOS, QuickBird, ALOS PRISM, SPOT5 HRS and sensors of similar type to be expected in the future. We will report about the status of the software, the functionality and some new algorithmic approaches in support of the processing concept. The functionality will be verified by results from various pilot projects. We put particular emphasis on the automatic generation of DSMs, which can be done at sub-pixel accuracy and on the semi-automated generation of city models.

• International Journal of CAD/CAM
• /
• 제5권1호
• /
• pp.83-90
• /
• 2005

This is a report on a new methodology to manage design knowledge by utilizing a knowledge-based CAD and a prototype system named $C^3$ (Cubic; CAD knowledge Code Capacitor), which is being developed using our methodology. $C^3$ facilitates (i) the automatic generation of a knowledge code for a knowledge-based CAD by processing design documents written in the format near the natural language, such as English or Japanese, and (ii) automatically generation of a design document written in the format near the natural language from the knowledge code. The features of the system facilitate document-based design knowledge management which reduces the designer's load to encode and maintain design knowledge, because it is easier for a designer to treat a natural language description than a coded description.

• 한국재난정보학회 논문집
• /
• 제19권2호
• /
• pp.432-438
• /
• 2023

연구목적: 생활안전 예방서비스 앱에서 신고되는 이미지를 AI를 사용하여 실시간으로 위험 카테고리를 자동으로 분류하여 사용자에게 편리한 위험신고를 가능하게 하는 것을 목적으로 한다. 연구방법: 인터넷으로 상호연결되는 생활안전 예방서비스 플랫폼, 생활안전 예방서비스 앱, AI 모델 서빙 서버와 sftp 서버로 구성되는 시스템을 통하여 신고된 생활안전 이미지를 실시간으로 자동분류하며, 이때 사용되는 AI모델 생성을 위한 AI 학습 알고리즘도 개발하였다. 연구결과: 이미지를 실시간으로 AI 처리하여 자동으로 분류할 수 있게 되어, 신고자가 생활안전 관련 사항을 보다 편리하게 신고할 수 있게 되었다. 결론: 본 논문에서 제시하는 AI 이미지 자동분류 시스템은 90% 이상의 분류 정확도로 신고 이미지를 실시간으로 자동분류하여 신고자가 간편하게 생활안전 관련 이미지를 신고할 수 있게 되었으며 향후 생활안전 예방서비스 앱의 사용자의 증가에 따라 더욱 빠르고 정확한 AI 모델 개발 및 시스템 처리용량 향상이 필요하다.

• 산업경영시스템학회지
• /
• 제41권4호
• /
• pp.248-255
• /
• 2018

Ensuring the quality of molds is one of the major issues in mass production. In general, securing the quality of the molds is achieved by repeating grinding and die spotting after machining the molds based on engineer's decision. However, this heuristic method is affected by the engineer's skill and working environment. Therefore, a lot of time and resources are needed in order to ensure quality. In this study, ensuring the quality of molds using grinding map which is generated using automatic measurement is proposed. An automatic measuring system based on CMM (Coordinate Measuring Machine) is developed for measuring the molds. This system generates the measurement path automatically using the 3D CAD model of products. CAD (ComputerAided-Design), CAM (Computer-Aided-Manufacturing), and CAQ (Computer-Aided-Quality) technology is integrated using DMIS (Dimensional Measuring Interface Standard) format in the automatic measuring system. After measuring the molds, a grinding map is generated using the gap between the CAD model and measured values of mold. The grinding map displays the machining tendency and the required amount of grinding with values on a 3D map. Therefore, the quality of molds can be ensured with exactness and quickness based on the grinding map. This study shows that integrating the planning, measuring, and analyzing based on computer technology can solve the problem of quality assurance of mold using the proposed method, therefore the productivity can be increased.