• 디지털융복합연구
• /
• 제18권8호
• /
• pp.169-177
• /
• 2020

본 연구의 목적은 비선형적인 특성과 시계열 특성을 가지고 있는 편의점 대표상품의 매출을 예측하는데 있다. 연구결과, '아이스 컵(Ice cup)'의 경우 3월부터 매출이 증가하여 여름인 7~8월에 가장 높은 값을 나타내고, 이후에는 매출이 떨어지는 계절성 패턴을 구현하였다. 한편 담배의 경우, 여름에 높은 매출을 기록하고 겨울에 낮은 매출을 기록하는 계절성을 나타냈으며, 미래 예측치도 하락하는 양상을 보였다. 본 연구의 학문적 시사점으로는 기존 연구에는 분석되지 않았던 편의점 재무성과 향상에 영향을 미치는 상위 매출상품에 집중하여 연구를 수행하여 미래 예측치를 제시하였다.

• 한국가스학회지
• /
• 제23권5호
• /
• pp.52-58
• /
• 2019

본 연구에서는 국내 도시가스 인수량에 대한 예측 모델을 개발하였다. 국내의 도시가스 회사는 KOGAS에 차년도 수요를 예측하여 보고해야 하므로 도시가스 인수량 예측은 도시가스 회사에 중요한 사안이다. 도시가스 사용량에 영향을 미치는 요인은 용도구분에 따라 다소 상이하나, 인수량 데이터는 용도별 구분이 어렵기 때문에 특정 용도에 관계없이 영향을 주는 요인으로 외기온도를 고려하여 모델개발을 실시하였다.실험 및 검증은 JB주식회사의 2008년부터 2018년까지 총 11년 치 도시가스 인수량 데이터를 사용하였으며, 전통적인 시계열 분석 중 하나인 ARIMA(Auto-Regressive Integrated Moving Average)와 딥러닝 기법인 LSTM(Long Short-Term Memory)을 이용하여 각각 예측 모델을 구축하고 두 방법의 단점을 최소화하기 위하여 다양한 앙상블(Ensemble) 기법을 사용하였다. 본 연구에서 제안한 일별 예측의 오차율 절댓값 평균은 Ensemble LSTM 기준 0.48%, 월별 예측의 오차율 절댓값 평균은 2.46%, 1년 예측의 오차율 절댓값 평균은 5.24%임을 확인하였다.

• 한국항만경제학회지
• /
• 제33권1호
• /
• pp.75-87
• /
• 2017

본 연구의 목적은 시스템 다이내믹스를 활용하여 선박 연료유 가격의 중장기 예측분석을 수행하는 것이다. 연료유 가격의 정확한 예측을 위해 가격 결정에 영향을 미치는 다양한 변수들 간의 인과적 관계를 바탕으로 정량화된 모델을 구축하였다. 연료유 가격 결정에는 유가에 영향을 미치는 원유 소비와 생산, 경제변화에 영향을 미치는 GDP, 환율 등과 함께 해운물류시장의 수요와 공급에 의해 결정되는 해상운임 등 다양한 구성변수들을 기반으로 시스템 다이내믹스를 활용한 연료유 가격을 예측하고 MAPEs 등을 통한 객관성을 검증하였다. 본 연구의 분석 결과 2029년까지의 연료유 가격은 2016년 대비 소폭 상승세를 보일 것으로 예상되지만 지난 2012년과 같은 급등세는 나타나지 않을 것으로 전망되었다. 본 연구는 각종 변수들 간의 동적인 인과관계를 활용하여 연료유 가격을 예측하여 합리적 추정결과를 유도할 수 있었다는 점과 가격 결정에 영향을 미치는 다양한 변수들의 구조적 관계를 손쉽게 파악함으로써 연료유 가격 변화에 대한 종합적인 위험 관리가 가능하여 해운기업의 효율적인 선대관리를 지원하는데 가치를 가지고 있다.

• 상하수도학회지
• /
• 제9권4호
• /
• pp.73-86
• /
• 1995

The propriety of the numerical model application was examined on Paldang resevoir and its inflow tributaries located in the center of the Korean peninsula and the long term water quality forecast of the oxygen profile was carried out in this syduy. The input data of the model was the capacity of the reservoir, catchment area, percolation, diffusion rate, vertical mixing rate, dissolution rate from the bottom of the reservoir, outflow of the resevoir, water quality measurement and meteorology data of the drainage basin, and the output result was the annual estimation value of the dissolved oxygen concentration and the biochemical oxygen demand. The modeling method is based on the measured or calculated boundary condition dividing the water area into several blocks from the macorscopic aspect and considering the mass balance in these blocks. As the result of the water quality forecast, it was expected that the water quality in Northern Han River and Paldang reservoir would maintain the recent level, but that the water quality in the Southern Han River and its inflow tributary would worsen below the grade 4 of the life environmental standard from around 2000 owing to the decrease of DO concentration and the increase of BOD concentration.

• 한국게임학회 논문지
• /
• 제5권2호
• /
• pp.3-9
• /
• 2005

인터렉티브 리얼 타임 3D(Interactive real-time 3D)는 유저가 가상의 3차원 세계를 탐색하고 또한 몰입하는 폼의 컨텐츠를 경험할 수 있게 해준다. 다른 매체와는 다르게, 인터렉티브 리얼 타임 3D의 사용자(user)는, 디지털 3D의 구조에서의 작용과 반작용이 즉시 일어나는 "실시간"에서 진행되는 프로세스에서 능동적인 역할을 수행한다.

• Geomechanics and Engineering
• /
• 제7권3호
• /
• pp.279-295
• /
• 2014

A series of one-dimensional consolidation tests and triaxial creep tests were performed on Nansha clays, which are interactive marine and terrestrial deposits, to investigate their time-dependent behaviour. Based on experimental observations of oedometer tests, normally consolidated soils exhibit larger secondary compression than overconsolidated soils; the secondary consolidation coefficient ($C_{\alpha}$) generally gets the maximum value as load approaches the preconsolidation pressure. The postsurcharge secondary consolidation coefficient ($C_{\alpha}$') is significantly less than $C_{\alpha}$. The observed secondary compression behaviour is consistent with the $C_{\alpha}/C_c$ concept, regardless of surcharging. The $C_{\alpha}/C_c$ ratio is a constant that is applicable to the recompression and compression ranges. Compared with the stage-loading test, the single-loading oedometer test can evaluate the entire process of secondary compression; $C_{\alpha}$ varies significantly with time and is larger than the $C_{\alpha}$ obtained from the stage-loading test. Based on experimental observations of triaxial creep tests, the creep for the drained state differs from the creep for the undrained state. The behaviour can be predicted by a characteristic relationship among axial strain rate, deviator stress level and time.

• 천문학회보
• /
• 제36권2호
• /
• pp.101.2-101.2
• /
• 2011

We have developed solar and space weather monitoring system for space weather users since 2007 as a project named 'Construction of Korea Space Weather Prediction Center'. In this presentation we will introduce space weather monitoring system for Geostationary Satellites and Polar Routes. These were developed for satisfying demands of space weather user groups. 'Space Weather Monitoring System for Geostationary Satellites' displays integrated space weather information on geostationary orbit such as magnetopause location, nowcast and forecast of space weather, cosmic ray count rate, number of meteors and x-ray solar flux. This system is developed for space weather customers who are managing satellite systems or using satellite information. In addition, this system provides space weather warning by SMS in which short message is delivered to users' cell phones when space weather parameters reach a critical value. 'Space Weather Monitoring System for Polar Routes' was developed for the commercial airline companies operating polar routes. This provides D-region and polar cap absorption map, aurora and radiation particle distribution, nowcast and forecast of space weather, proton flux, Kp index and so on.

• 대기
• /
• 제16권4호
• /
• pp.259-267
• /
• 2006

In the present study, the neural network (NN) model with cluster analysis method was developed to predict storm surge in the whole Korean coastal regions with special focuses on the regional extension. The model used in this study is NN model for each cluster (CL-NN) with the cluster analysis. In order to find the optimal clustering of the stations, agglomerative method among hierarchical clustering methods was used. Various stations were clustered each other according to the centroid-linkage criterion and the cluster analysis should stop when the distances between merged groups exceed any criterion. Finally the CL-NN can be constructed for predicting storm surge in the cluster regions. To validate model results, predicted sea level value from CL-NN model was compared with that of conventional harmonic analysis (HA) and of the NN model in each region. The forecast values from NN and CL-NN models show more accuracy with observed data than that of HA. Especially the statistics analysis such as RMSE and correlation coefficient shows little differences between CL-NN and NN model results. These results show that cluster analysis and CL-NN model can be applied in the regional storm surge prediction and developed forecast system.

• 농업과학연구
• /
• 제16권1호
• /
• pp.71-83
• /
• 1989

The purpose of this research are to forecast the demand and supply of milk in Korea, and to obtain information for attitudes affecting milk consumption, which is necessary to make a plan for increasing milk consumption in Korea. The estimation of the milk demand and production was made by the multiplicative decomposition method and the statistical function. Data on consumer were collected from 737 students who were attending primary school, middle school and university in Daejeon during the period of July 11 to July 21, 1988. The results obtained are as follows; 1. The prediction results showed that the production for milk will over supply 21,900 tons in 1,990, 70,800 tons in 1,995 by the multiplicative decomposition method and 45,400 tons in 1990, -51,500 tons in 1995 by the statistical function. 2. It was found that almost all the students awared milk as essential food-stuff of common food stuff for the Koreans. 3. Quite a few students were apt to believe that milk processors added water into fluid milk. 4. Most students showed obtaining information about the nutritional value of milk by school education and advertising of TV, Radio, and Printed media. 5. However, it was found that the advertising by TV, Radio, and Printed media did hardly give to consumers influences on the choice of a particular milk brand. Accordingly, the conclusions are as follows; 1. Need to provide consumers with well planned education programs on the nutritional value of milk. 2. Heavy brand advertising for fluid milk may mislead the understanding of consumer, since city milk is not much differentiated in Korea. Therefore the milk processors should put more efforts in generic milk promotion by reducing brand advertizement. 3. The milk processors should provide major portion of financing for generic milk promotion program.

• Structural Engineering and Mechanics
• /
• 제31권1호
• /
• pp.57-74
• /
• 2009

Power signals resulting from spindle and feed motor, present a rich content of physical information, the appropriate analysis of which can lead to the clear identification of the nature of the tool wear. The partial least-squares regression (PLSR) method has been established as the tool wear analysis method for this purpose. Firstly, the results of the application of widely used techniques are given and their limitations of prior methods are delineated. Secondly, the application of PLSR is proposed. The singular value theory is used to noise reduction. According to grey relational degree analysis, sample variable is filtered as part sample variable and all sample variables as independent variables for modelling, and the tool wear is taken as dependent variable, thus PLSR model is built up through adapting to several experimental data of tool wear in different milling process. Finally, the prediction value of tool wear is compare with actual value, in order to test whether the model of the tool wear can adopt to new measuring data on the independent variable. In the new different cutting process, milling tool wear was predicted by the methods of PLSR and MLR (Multivariate Linear Regression) as well as BPNN (BP Neural Network) at the same time. Experimental results show that the methods can meet the needs of the engineering and PLSR is more suitable for monitoring tool wear.