http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
박상근(Sangkun Park) (사)한국CDE학회 2021 한국CDE학회 논문집 Vol.26 No.2
This paper proposes a 3D image augmentation method for improving the generalization performance of deep neural networks. It allows us to enrich the diversity of training data samples that is essential in medical image segmentation tasks, thus reducing the data overfitting problem caused by the fact the scale of medical image dataset is typically smaller. It also enables us to predict medical segmentation surfaces in Euclidean space without additional labeled datasets. This method includes image transformation functions, which are comprised of a spatial deformation and image intensity change, enabling the synthesis of complex effects such as variations in anatomy and image acquisition procedures. Our numerical experiments demonstrate that the proposed approach provides significant improvements over state-of-the-art methods for 3D medical image segmentation.
BPMN 이벤트 기호를 활용한 가상플랜트 시스템 기능 통합 설계와 구현
이재현,서효원 한국CDE학회 2019 한국CDE학회 논문집 Vol.24 No.1
CPS (cyber-physical system) or digital-twin systems for companies’ operational systems requires diverse interactions with enterprise-wide information systems. An information system development methodology is necessary to capture and express the interactions among functional modules and relevant data characteristics. The proposed modeling approach adopts the event notations of the BPMN (Business Process Modeling Notations) standard. The event notations are expressed in data models and module architecture design. The proposed modeling approach helps engineers to understand periodic or time related issues in data and system modules. The usage of the proposed approach is described with a sensor-based virtual plant system example. A sensor-based virtual plant system is a digital-twin system for a refinery plant, and analysis/ design examples of the system are shown to show effectiveness of the proposed approach.