• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.59-62
• /
• 2016

본 논문에서는 실종자 데이터베이스에 등록된 실종자에 대한 색인으로 텍스트 기반의 통제 색인만을 사용할 때 발생하는 문제점에 대한 해결책을 다룬다. 기존 실종자를 등록할 때 함께 등록하게 되는 실종자에 대한 이미지는 정형화 할 수 없어 실종자 조회에 사용될 수 없었다. 이러한 문제점을 해결하고자 OpenCV와 TensorFlow 를 이용하여 영상의 유사도를 추출함으로써 실종자의 이미지를 정형화시켜 유의미한 정보로 변경하여 사용하고자 하는 방법을 제안한다.

• Wind and Structures
• /
• v.8 no.1
• /
• pp.13-34
• /
• 2005

This paper presents an analysis of wind velocity and pressure data obtained in a rural environment with a view to identifying the vortex structures present within the flow and examining the relationship between pressure and dynamic pressure. The data is analysed using both conventional analysis and conditional sampling. A method examining the eigenvalues of a matrix formed by the addition of the square of the strain tensor and the square of the vorticity tensor is also investigated. This method illustrates that there are a number of vortex structures present in the flow. The work presented in this paper suggests that the extreme events occur as a result of the superposition of two independent mechanisms.

• Macromolecular Research
• /
• v.9 no.3
• /
• pp.164-170
• /
• 2001

Recently in order to describe the complex rheological behavior of polymer melts with long side branches like low density polyethylene, new constitutive equations called the pom-pom equations have been derived by McLeish and Larson on the basis of the reptation dynamics with simplified branch structure taken into account. In this study mathematical stability analysis under short and high frequency wave disturbances has been performed for the simplified differential version of these constitutive equations. It is proved that they are globally Hadamard stable except for the case of maximum constant backbone stretch (λ = q) with arm withdrawal s$\_$c/ neglected, as long as the orientation tensor remains positive definite or the smooth strain history in the now is previously given. However this model is dissipative unstable, since the steady shear How curves exhibit non-monotonic dependence on shear rate. This type of instability corresponds to the nonlinear instability in simple shear flow under finite amplitude disturbances. Additionally in the flow regime of creep shear flow where the applied constant shear stress exceeds the maximum achievable value in the steady now curves, the constitutive equations will possibly violate the positive definiteness of the orientation tensor and thus become Hadamard unstable.

• Korea Multimedia Society
• /
• v.20 no.3
• /
• pp.53-61
• /
• 2016

• Journal of computational fluids engineering
• /
• v.9 no.4
• /
• pp.20-33
• /
• 2004

In this study a stretching-mapping method is proposed for calculating the materials' stretching exponents, which are to be used in quantification of the mixing effect. In this method, the mapping tensor associated with the deformation of each fluid material is first obtained. Then deformations of a lot of materials are obtained by applying the mapping tensor. The local stretching rates and their space-average values are next computed with the mapped deformations. Application to a simple time-periodic flow within a cavity shows that the method is indeed effective compared with the conventional method; i.e. the mapping method is fast and yields the same results as the conventional one.

• Journal of Advanced Information Technology and Convergence
• /
• v.9 no.1
• /
• pp.89-102
• /
• 2019

Collagen can be used in building artificial skin replacements for treatment of burns and towards the reconstruction of bone as well as researching cell behavior and cellular interaction. The strength of collagen in connective tissue rests on the characteristics of collagen fibers. 3D confocal imaging of collagen fibers enables the characterization of their spatial distribution as related to their function. However, the image stacks acquired with confocal laser-scanning microscope does not clearly show the collagen architecture in 3D. Therefore, we developed a new method to reconstruct, visualize and characterize collagen fibers from fluorescence confocal images. First, we exploit the tensor voting framework to extract sparse reliable information about collagen structure in a 3D image and therefore denoise and filter the acquired image stack. We then propose to segment the collagen fibers by defining an energy term based on the Hessian matrix. This energy term is minimized by a min cut-max flow algorithm that allows adaptive regularization. We demonstrate the efficacy of our methods by visualizing reconstructed collagen from specific 3D image stack.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.140-140
• /
• 2019

본 연구에서는 Terra MODIS 위성자료와 Tensorflow를 활용해 1 km 공간 해상도의 토양수분을 산정하는 알고리즘을 개발하고, 국내 관측 자료를 활용해 검증하고자 한다. 토양수분 모의를 위한 입력 자료는 Terra MODIS NDVI(Normalized Difference Vegetation Index)와 LST(Land Surface Temperature), GPM(Global Precipitation Measurement) 강우 자료를 구축하고, 농촌진흥청에서 제공하는 1:25,000 정밀토양도를 기반으로 모의하였다. 여기서, LST와 GPM의 자료는 기상청의 종관기상관측지점의 LST, 강우 자료와 조건부합성(Conditional Merging, CM) 기법을 적용해 결측치를 보간하였고, 모든 위성 자료의 공간해상도를 1 km로 resampling하여 활용하였다. 토양수분 산정 기술은 인공 신경망(Artificial Neural Network) 모형의 딥 러닝(Deep Learning)을 적용, 기계 학습기반의 패턴학습을 사용하였다. 패턴학습에는 Python 라이브러리인 TensorFlow를 사용하였고 학습 자료로는 농촌진흥청 농업기상정보서비스에서 101개 지점의 토양수분 자료(2014 ~ 2016년)를 활용하고, 모의 결과는 2017 ~ 2018년까지의 자료로 검증하고자 한다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.349-350
• /
• 2022

Recently, AI (Artificial Intelligence) has been applied to various technologies such as automatic driving, robot and smart communication. Currently, AI system is developed by software-based method using tensor flow, and GPU (Graphic Processing Unit) is employed for processing unit. In this work, we developed an FPGA-based (Field Programmable Gate Array) AI system , and report on image recognition system to realize the AI system.

• Tunnel and Underground Space
• /
• v.27 no.2
• /
• pp.100-108
• /
• 2017

As a measure of the combined effect of fracture geometry, the fabric tensor parameters could quantify the status of the connected fluid flow paths in discrete fracture network (DFN). The correlation analysis between fabric tensor parameters and hydraulic properties of the 2-D DFN was performed in this study. It is found that there exists a strong nonlinear relationship between the directional conductivity and the fabric tensor component estimated in the direction normal to the direction of hydraulic conductivity. The circular radial plots without significant variation of the first invariant ($F_0$) of fabric tensor for different sized 2-D DFN block are a necessary condition for treating representative element volume (REV) of a fractured rock mass. The relative error (ER) between the numerically calculated directional hydraulic conductivity and the theoretical directional hydraulic conductivity decreases with the increase in $F_0$. A strong functional relation seems to exist between the $F_0$ and the average block hydraulic conductivity.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.08a
• /
• pp.30.1-30.1
• /
• 2008