• 무역학회지
• /
• 제44권2호
• /
• pp.127-141
• /
• 2019

In this study, the relationship between Baltic Dry Index(BDI) and maritime trade volume in the dry cargo market was verified using the vector autoregressive (VAR) model. Data was analyzed from 1992 to 2018 for iron ore, steam coal, coking coal, grain, and minor bulks of maritime trade volume and BDI. Granger causality analysis showed that the BDI affects the trade volume of coking coal and minor bulks but the trade volume of iron ore, steam coal and grain do not correlate with the BDI freight index. Impulse response analysis showed that the shock of BDI had the greatest impact on coking coal at the two years lag and the impact was negligible at the ten years lag. In addition, the shock of BDI on minor cargoes was strongest at the three years lag, and were negligible at the ten years lag. This study examined the relationship between maritime trade volume and BDI in the dry bulk shipping market in which uncertainty is high. As a result of this study, there is an economic aspect of sustainability that has helped the risk management of shipping companies. In addition, it is significant from an academic point of view that the long-term relationship between the two time series was analyzed through the causality test between variables. However, it is necessary to develop a forecasting model that will help decision makers in maritime markets using more sophisticated methods such as the Bayesian VAR model.

• International Journal of Computer Science & Network Security
• /
• 제22권7호
• /
• pp.301-307
• /
• 2022

Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.

• 한국항공운항학회지
• /
• 제31권1호
• /
• pp.92-98
• /
• 2023

This paper used the golf course visitors' data in Jeju region to forecast the growth of inbound air traveler to Jeju. This is because the golf course visitors were proven to bring the highest economic and production inducement effect to the Jeju region. Based on such a data, this paper forecast the short-term growth rate of inbound air traveler using ARIMA to the Jeju until December 2025. According to ARIMA (0,1,0) (0,1,1) model, it was analyzed that the monthly number of golf course visitors to Jeju has been increasing steadily even since COVID-19 pandemic and the number is expected to grow until the end of 2025. Applying the same parameters of ARIMA (0,1,0) (0,1,1) to inbound air travel data, it was found the growth rate of inbound air travelers would be higher than the growth rate of 2019 shortly without moderate variation even though the monthly number of inbound travelers to Jeju had been dropped during COVID-19 pandemic.

• 무역학회지
• /
• 제45권3호
• /
• pp.119-132
• /
• 2020

In this paper we explore the two analyses to know the urbanization effect on trade. First, the granger causality test to examine the relationship between trade and urbanization. The Granger causality test is a statistical hypothesis test for determining whether one time series is useful for forecasting another. The results indicated that the existence of a bidirectional causality running from trade to urbanization when six lags were applied. When eight lags were applied, we found unidirectional causality running from urbanization to trade. Second, gravity models were used to investigate the urbanization effect on trade. The production cost and specification are affected by the economies of scale, and the economies of scale increased as the greater geographically agglomeration. However, the gravity model to explain the bilateral trade flows ignores the urbanization variables. Therefore we added the urbanization variable represented as the geographically agglomeration into gravity model. The results show that the degree of urbanization of both countries has statistically positive effect on trade (export and import) and the bigger coefficients of trade partner's urbanization. The reason is that the trade share of industrial supplies, intermediate goods and capital goods is much higher than finished consumer goods. The urbanization is more important the improved the efficiency of production than demand market.

• 한국건설관리학회논문집
• /
• 제19권2호
• /
• pp.107-116
• /
• 2018

2010년 이후 한국 해외건설 수주가 극적 변동을 보임에 따라, 이에 대한 원인과 대응방안을 모색하고자 한다. 한국 해외건설은 2010년 716억불을 정점으로 2011년에서 2014년까지 연평균 638억불을 기록하였다. 하지만, 2014년 하반기부터 시작된 국제유가 하락으로 2015년 461억불을, 2016년 282억불, 2017년 290억불의 수주에 그쳤다. 국제 유가 하락과 더불어, 세계 경제 저성장 지속과 우리 기업의 EPC 수주 역량 한계점 봉착 등으로 불확실성이 과거 어느 때보다 증가하고 있다. 이와 같은 불확실한 해외건설시장 상황 속에서 적절한 대응방안을 모색하고, 많은 가능성과 글로벌 경쟁력을 갖추고 있는 해외건설산업을 국가수 출전략산업으로 육성 발전시키기 위하여, 세계건설시장과 해외건설시장의 발주 및 수주 구조와 그 변화추세를 분석하고, 향후 해외건설 수주 규모를 예측함으로써 해외건설산업의 건전한 육성 및 발전을 위한 정책 방향을 제시하고자 한다.

• 한국산학기술학회논문지
• /
• 제22권6호
• /
• pp.453-459
• /
• 2021

계통한계가격은 발전회사들이 생산한 전력을 판매하고 받게 되는 가격으로서, 발전설비의 건설 및 보수에 대한 의사결정에서 중요한 역할을 한다. 본 논문에서는 천연가스 가격이나 원유 가격 등을 이용하여 계통한계가격을 장기 예측하는 모형을 제안한다. 분석대상 변수들이 비정상시계열적 특성을 지니므로 변수 간 장기관계인 공적분관계에 대한 검정을 시행하고, 공적분 관계와 단기적 동학에 대한 관계식을 추정하여 오차수정모형을 구성하였다. 분석대상 기간이 짧아 분석결과의 안정성이 낮은 문제를 고려하여, 다양한 검정 및 추정기법을 사용하여 분석의 강건성을 제고하고자 하였다. 기존 연구에 비해 다양한 연료가격을 검토하고, 시계열 분석의 엄밀성과 강건성을 제고했다는 점이 본 연구가 기여한 부분이다. 분석 결과 계통한계가격과 천연가스가격, 계통한계가격과 유가, 계통한계가격과 천연가스가격 및 유가 간에 공적분 관계가 존재하는 것으로 나타나, 각각의 공적분 관계를 기반으로 오차수정모형을 추정하고 예측력을 비교하였다. 단기식에서는 오차수정항, 전력공급예비율, 시차항을 고려하였다. 각 오차수정모형의 표본외 예측력을 비교한 결과, 계통한계가격과 천연가스가격 간 공적분 관계를 이용하는 모형이 평균제곱근오차와 평균절대백분율오차 모두 가장 낮은 값을 보이는 등 예측력이 좋은 것으로 평가되었다.

• 한국ITS학회 논문지
• /
• 제3권1호
• /
• pp.45-52
• /
• 2004

현재 여러 지자체에서 혼잡한 도시교통의 이동성 및 안전성을 향상시키기 위해 첨단교통관리체계(ITS)를 구축 $\cdot$ 운영중인데 이러한 시스템에서 수집하는 교통상황에 대한 실시간 자료가 노면상황, 악천후, 통신 및 장비자체의 결함 등으로 인해 수많은 자료가 결측된다. 이러한 결측 자료로 인해 통행시간 예측 및 각종 연구가 불가능한 경우가 발생하며 또한 도로의 계획과 기하구조 설계시 기본 자료가 되는 AADT 및 DHV 등의 교통 파라메터들이 과소 또는 과대 추정될 수 있어서 심각한 손해를 끼칠수 있다. 따라서 본 연구에서는 부득이하게 누락되는 교통량 자료에 대해 전 $\cdot$ 후기간 평균, 회귀 모형, EM, 시계열 모형들을 활용한 대체기법들을 살펴보았고, 그 결과 시계열 모형을 이용한 대체의 경우 MAPE, 불균등계수, RMSE 가 각각 5.0$\%$, 0.030, 110으로 가장 좋은 결과를 보였고 나머지 대체기법들은 평가지표에 따라 조금씩 다른 결과를 보였으나 대체로 만족할 만한 수준의 결과를 낳았다

• 한국환경과학회:학술대회논문집
• /
• 한국환경과학회 2003년도 International Symposium on Clean Environment
• /
• pp.73-78
• /
• 2003

In this research, we implement Realtime Air Diffusion Prediction System which is a parallel Fortran model running on distributed-memory parallel computers. The system is designed for air diffusion simulations with four-dimensional data assimilation. For regional air quality forecasting a series of dynamic downscaling technique is adopted using the NCAR/Penn. State MM5 model which is an atmospheric model. The realtime initial data have been provided daily from the KMA (Korean Meteorological Administration) global spectral model output. It takes huge resources of computation to get 24 hour air quality forecast with this four step dynamic downscaling (27km, 9km, 3km, and lkm). Parallel implementation of the realtime system is imperative to achieve increased throughput since the realtime system have to be performed which correct timing behavior and the sequential code requires a large amount of CPU time for typical simulations. The parallel system uses MPI (Message Passing Interface), a standard library to support high-level routines for message passing. We validate the parallel model by comparing it with the sequential model. For realtime running, we implement a cluster computer which is a distributed-memory parallel computer that links high-performance PCs with high-speed interconnection networks. We use 32 2-CPU nodes and a Myrinet network for the cluster. Since cluster computers more cost effective than conventional distributed parallel computers, we can build a dedicated realtime computer. The system also includes web based Gill (Graphic User Interface) for convenient system management and performance monitoring so that end-users can restart the system easily when the system faults. Performance of the parallel model is analyzed by comparing its execution time with the sequential model, and by calculating communication overhead and load imbalance, which are common problems in parallel processing. Performance analysis is carried out on our cluster which has 32 2-CPU nodes.

• 한국빅데이터학회지
• /
• 제5권1호
• /
• pp.1-9
• /
• 2020

이 연구는 2018년도 정부(농림축산식품부)의 재원으로 농림식품기술기획평가원 지원을 받아 수행된 연구이다. 최근 시계열 및 텍스트 마이닝에서 활발히 사용되는 모델은 딥러닝(Deep Learning) 모델 구조를 활용한 LSTM(Long Short-Term Memory models) 모델이다. LSTM 모델은 RNN의 BPTT(Backpropagation Through Time) 과정에서 발생하는 Long-Term Dependency Problem을 해결하기 위해 등장한 모델이다. LSTM 모델은 가변적인 Sequence data를 활용하여 예측하는 문제를 굉장히 잘 해결했고, 지금도 널리 사용되고 있다. 본 논문 연구에서는 KT가 제공하는 CDR(Call Detailed Record) 데이터를 활용하여 바이러스와 밀접한 관계가 있을 것으로 예측되는 사람의 이동 경로를 파악하였다. 해당 사람의 경로를 활용하여 LSTM 모델을 학습시켜 이동 경로를 예측한 결과를 소개한다. 본 연구 결과를 활용하여 HPAI가 전파되는 경로를 예측하여 방역에 중점을 둘 경로 또는 지역을 선정해 HPAI 확산을 줄이는 데 이용될 수 있을 것이다.

• 시스템엔지니어링학술지
• /
• 제18권2호
• /
• pp.75-93
• /
• 2022

Machine learning (ML) data-driven meta-model is proposed as a surrogate model to reduce the excessive computational cost of the physics-based model and facilitate the real-time prediction of a nuclear power plant's transient response. To forecast the transient response three machine learning (ML) meta-models based on recurrent neural networks (RNNs); specifically, Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and a sequence combination of Convolutional Neural Network (CNN) and LSTM are developed. The chosen accident scenario is a control element assembly withdrawal at power concurrent with the Loss Of Offsite Power (LOOP). The transient response was obtained using the best estimate thermal hydraulics code, MARS-KS, and cross-validated against the Design and control document (DCD). DAKOTA software is loosely coupled with MARS-KS code via a python interface to perform the Best Estimate Plus Uncertainty Quantification (BEPU) analysis and generate a time series database of the system response to train, test and validate the ML meta-models. Key uncertain parameters identified as required by the CASU methodology were propagated using the non-parametric Monte-Carlo (MC) random propagation and Latin Hypercube Sampling technique until a statistically significant database (181 samples) as required by Wilk's fifth order is achieved with 95% probability and 95% confidence level. The three ML RNN models were built and optimized with the help of the Talos tool and demonstrated excellent performance in forecasting the most probable NPP transient response. This research was guided by the Systems Engineering (SE) approach for the systematic and efficient planning and execution of the research.