• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.159-159
• /
• 2017

스마트 시설환경은 대표적으로 원예, 축산 분야 등 여러 형태의 농업현장에 정보 통신 및 데이터 분석 기술을 도입하고 있는 시설화된 생산 환경이라 할 수 있다. 근래에 하드웨어적으로 급증한 스마트 시설환경에서 생산되는 방대한 생육/환경 데이터를 올바르고 적합하게 사용하기 위해서는 일반 산업 현장과는 차별화 된 분석기법이 요구된다고 할 수 있다. 소프트웨어 공학 분야에서 연구된 빅데이터 처리 기술을 기계적으로 농업 분야의 빅데이터에 적용하기에는 한계가 있을 수 있다. 시설환경 내/외부의 다양한 환경 변수는 시계열 데이터의 난해성, 비가역성, 불특정성, 비정형 패턴 등에 기인하여 예측 모델 연구가 매우 난해한 대상이기 때문이라 할 수 있다. 본 연구에서는 근래에 관심이 급증하고 있는 인공신경망 연구 소프트웨어인 Tensorflow (www.tensorflow.org)와 대표적인 Open source인 OpenNN (www.openn.net)을 스마트 시설환경 환경변수 상호간 상관성 분석에 응용하였다. 해당 소프트웨어 라이브러리의 운영환경을 살펴보면 Tensorflow 는 Linux(Ubuntu 16.04.4), Max OS X(EL capitan 10.11), Windows (x86 compatible)에서 활용가능하고, OpenNN은 별도의 운영환경에 대한 바이너리를 제공하지 않고 소스코드 전체를 제공하므로, 해당 운영환경에서 바이너리 컴파일 후 활용이 가능하다. 소프트웨어 개발 언어의 경우 Tensorflow는 python이 기본 언어이며 python(v2.7 or v3.N) 가상 환경 내에서 개발이 수행이 된다. 주의 깊게 살펴볼 부분은 이러한 개발 환경의 제약으로 인하여 Tensorflow의 주요한 장점 중에 하나인 고속 연산 기능 수행이 일부 운영 환경에 국한이 되어 제공이 된다는 점이다. GPU(Graphics Processing Unit)의 제공하는 하드웨어 가속기능은 Linux 운영체제에서 활용이 가능하다. 가상 개발 환경에 운영되는 한계로 인하여 실시간 정보 처리에는 한계가 따르므로 이에 대한 고려가 필요하다. 한편 근래(2017.03)에 공개된 Tensorflow API r1.0의 경우 python, C++, Java언어와 함께 Go라는 언어를 새로 지원하여 개발자의 활용 범위를 매우 높였다. OpenNN의 경우 C++ 언어를 기본으로 제공하며 C++ 컴파일러를 지원하는 임의의 개발 환경에서 모두 활용이 가능하다. 특징은 클러스터링 플랫폼과 연동을 통해 하드웨어 가속 기능의 부재를 일부 극복했다는 점이다. 상기 두 가지 패키지를 이용하여 2016년 2월부터 5월 까지 충북 음성군 소재 딸기 온실 내부에서 취득한 온도, 습도, 조도, CO2에 대하여 Large-scale linear model을 실험적(시간단위, 일단위, 주단위 분할)으로 적용하고, 인접한 세그먼트의 환경변수 예측 모델링을 수행하였다. 동일한 조건의 학습을 수행함에 있어, Tensorflow가 개발 소요 시간과 학습 실행 속도 측면에서 매우 우세하였다. OpenNN을 이용하여 대등한 성능을 보이기 위해선 병렬 클러스터링 기술을 활용해야 할 것이다. 오프라인 일괄(Offline batch)처리 방식의 한계가 있는 인공신경망 모델링 기법과 현장 보급이 불가능한 고성능 하드웨어 연산 장치에 대한 대안 마련을 위한 연구가 필요하다.

• Journal of the Korean Geographical Society
• /
• v.41 no.2 s.113
• /
• pp.212-226
• /
• 2006

Surface data generally represent continuous distribution of geographical or social phenomena of a region in urban analysis. Instances include distribution of temperature, population of region, and various distributions related to human activities. When spatial data are given in the form of surface, surface comparison is required as a way of comprehending the surface change or the relationship between two surfaces. As for previous approaches of surface comparison, there are visualization, quantitative methods and qualitative method. All those approaches, however, show the difference between two surfaces in a limited way. Especially, they are not able to distinguish spatial difference between two surfaces. To overcome such problem, this paper proposes a method of comparing two surfaces in terms of their spatial structure. Main concept of the method comes from earth moving problem and the method is named minimum surface transformation, here. When a surface is transformed into another, total surface volume moved in the process of transformation should be the minimum. Both quantitative and spatial differences between two surfaces are evaluted by total surface volume moved and the distribution of moved surface volume of each cell respectively. The method is applied to hypothetical and actual data. From the former, it is understood that the method explains how two surfaces are quantitatively and spatially different. The result of the latter shows that moved total surface volume decreases as time goes by which fits the actual situation that population change rate gets smaller. Concerning the other measure of surface difference, the distribution of $X_{ij}$ describes detailed flow of surface volume than that of simply subtracting surface volume by indicating to what direction the population change occurs.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.11
• /
• pp.140-149
• /
• 1996

Cursive characters are written on an economical principle to reduce the motion of a pen in the limit of distinction between characters. That is, the pen is not lifted up to move for writing a next stroke, the pen is not moved at all, or connected two strokes chance their shapes to a similar and simple shape which is easy to be written. For these reasons, strokes and korean alphabets are not only easy to be changed, but also difficult to be splitted. In this paper, we propose a curvature stroke modeling method for splitting and matching by using a structural primitive. A curvature stroke is defined as a substroke which does not change its curvanture. Input strokes handwritten in a cursive style are splitted into a sequence of curvature strokes by segmenting the points which change the direction of rotation, which occur a sudden change of direction, and which occur an excessive rotation Each reference of korean alphabets is handwritten in a printed style and is saved as a sequence of curvature strikes which is generated by splitting process. And merging process is used to generate various sequences of curvature strikes for matching. Here, it is also considered that imaginary strokes can be written or omitted. By using a curvature stroke as a unit of recognition, redundant splitting points in input characters are effectively reduced and exact matching is possible by generating a reference curvature stroke, which consists of the parts of adjacent two korean alphasbets, even when the connecting points between korean alphabets are not splitted. The results showed 83.6% as recognition rate of the first candidate and 0.99sec./character (CPU clock:66MHz) as processing time.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.20 no.4
• /
• pp.296-304
• /
• 2018

The objective of this study was to analyze the impact of climate change on rice yield and quality. Experiments were conducted using SPAR(Soil-Plant-Atmosphere-Research) chambers, which was designed to create virtual future climate conditions, in the National Institute of Crop Science, Jeonju, Korea, in 2016. In the future climate conditions($+2.8^{\circ}C$ temp, 580 ppm $CO_2$) of year 2051~2060 according to RCP 8.5 scenario, elevated temperature and $CO_2$ accelerated the heading date by about five days than the present climate conditions, resulted in a high temperature environment during grain filling stage. Rice yield decreased sharply in the future climate conditions due to the high temperature induced poor ripening. And the spikelet numbers, ripening ratio, and 1000-grain weight of brown rice were significantly decreased compared to control. The rice grain quality was also decreased sharply, especially due to the increased immature grains. In the future climate conditions, expression of starch biosynthesis-related genes such as granule-bound starch synthase(GBSSI, GBSSII, SSIIa, SSIIb, SSIIIa), starch branching enzyme(BEIIb) and ADP-glucose pyrophosphorylase(AGPS1, AGPS2, AGPL2) were repressed in developing seeds, whereas starch degradation related genes such as ${\alpha}-amylase$(Amy1C, Amy3D, Amy3E) were induced. These results suggest that the reduction in yield and quality of rice in the future climate conditions is likely caused mainly by the poor grain filling by high temperature. Therefore, it is suggested to develop tolerant cultivars to high temperature during grain filling period and a new cropping system in order to ensure a high quality of rice in the future climate conditions.