http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
편광현미경 이미지 기반 염기성 화산암 분류를 위한 인공지능 모델의 효용성 평가
심호,정원우,홍성식,서재원,박창윤,송윤구,Sim, Ho,Jung, Wonwoo,Hong, Seongsik,Seo, Jaewon,Park, Changyun,Song, Yungoo 대한자원환경지질학회 2022 자원환경지질 Vol.55 No.3
In order to minimize the human and time consumption required for rock classification, research on rock classification using artificial intelligence (AI) has recently developed. In this study, basic volcanic rocks were subdivided by using polarizing microscope thin section images. A convolutional neural network (CNN) model based on Tensorflow and Keras libraries was self-producted for rock classification. A total of 720 images of olivine basalt, basaltic andesite, olivine tholeiite, trachytic olivine basalt reference specimens were mounted with open nicol, cross nicol, and adding gypsum plates, and trained at the training : test = 7 : 3 ratio. As a result of machine learning, the classification accuracy was over 80-90%. When we confirmed the classification accuracy of each AI model, it is expected that the rock classification method of this model will not be much different from the rock classification process of a geologist. Furthermore, if not only this model but also models that subdivide more diverse rock types are produced and integrated, the AI model that satisfies both the speed of data classification and the accessibility of non-experts can be developed, thereby providing a new framework for basic petrology research.
김기태(Kitae Kim),양승현(Seunghyun Yang),정원우(Wonwoo Jung) 한국정보과학회 2020 정보과학회 컴퓨팅의 실제 논문지 Vol.26 No.4
OMG 표준 DDS는 발간/구독 구조의 확장성 및 신뢰성을 보장하는 미들웨어로 특히 미션 크리티컬한 실시간 분산시스템에서 실시간 정보 교환능력을 제공한다. 본 논문에서는 DDS를 적용한 작전/교전통제 분야에 특화된 실시간 정보공유 소프트웨어 프레임워크 LTIM을 제안한다. LTIM은 기존 개발된 작전/교전통제 시스템에 적용된 DDS의 실시간 정보 교환능력을 확장하여 DDS 캐시를 사용한 정보의 저장소 역할도 수행하도록 하여 진화된 DDS 활용 사례를 제시하였다. LTIM을 적용한 실제 시스템 구현사례를 제시하고 기존 개발된 작전/교전통제 시스템과 비교 분석하여 실시간 정보 공유 및 저장처리 성능과 프레임워크 사용에 따른 코드 품질의 우수성을 확인하였다. Real-time distribution middleware has been adopted widely for distributed real-time systems to interconnect distributed computing nodes and share practical domain information in real-time. In particular, the OMG standard Data-Distribution Service(DDS) is a guaranteed middleware that provides real-time data-delivery capability in terms of publishing/subscribing communications for various mission-critical distributed real-time systems. This paper proposes a DDS-based real-time data sharing software framework, LTIM designed for a mission-critical tactical and engagement control domain. The proposed LTIM presents an evolved practical use case for DDS that expands the real-time data-exchange capability of legacy systems by providing real-time data sharing and DDS cache. To evaluate the performance and quality of LTIM, we compared a command and control (C2) system with LTIM and a legacy C2 system in terms of data delivery, store latency, and code metrics.