• 한국물환경학회지
• /
• 제20권6호
• /
• pp.685-691
• /
• 2004

Water quality forecasting with long term flow is important for management and operation of river environment. However, it is difficult to set up and operate a physical model for water quality forecasting due to large uncertainty in the data required for model setting. Therefore, relatively simpler stochastic approaches are adopted for this problem. In this study we try several multivariate time series models such as ARMAX models for the possible substitute for water quality forecasting. Those models are applied to the BOD and COD levels at Noryangin station, Han river, and also evaluated the effect of release from Paldang dam on them. Monthly BOD and COD data from 1985 to 1991 (7 years) are used for model building and another two year data for model testing. As a result of the study, the effect of improvement on water quality is much more effective combining with the water quality improvement of dam release than considering only increment of dam release in the downstream Han river.

• 한국항만경제학회지
• /
• 제34권3호
• /
• pp.183-200
• /
• 2018

본 연구는 1996년 10월부터 2017년 4월까지의 건화물선, 컨테이너선, 유조선 가격과 운임 자료를 사용하여 선가의 합리적 거품 유무를 검정하였다. 기존의 연구와 달리, 컨테이너선, 유조선 가격으로 실증분석 범위를 확장하여 모형설정 오류에서 자유로운 안정성에 기초한 안정성 검정과 공적분 검정을 활용하였다. 안정성 검정 결과, 유조선 가격에 거품이 존재하였으며, 공적분 검정은 건화물선과 컨테이너선의 가격에 거품이 포함되었다는 결과를 나타내었다. 이러한 실증분석 결과는 우리나라 해운기업이 저선가 시기에 선박을 확보하는 선박투자 전략을 채택해야하며, 이를 촉진하기 위한 정부의 금융 지원과 안정적인 선복량 확보 정책 수립의 필요성을 시사한다.

• 열처리공학회지
• /
• 제36권6호
• /
• pp.374-381
• /
• 2023

This study develops and evaluates a deep learning model for predicting oxide and nitride layers based on plasma process data. We introduce a novel deep learning-based Varying Coefficient Regressor (VCR) by adapting the VCR, which previously relied on an existing unique function. This model is employed to forecast the oxide and nitride layers within the plasma. Through comparative experiments, the proposed VCR-based model exhibits superior performance compared to Long Short-Term Memory, Random Forest, and other methods, showcasing its excellence in predicting time series data. This study indicates the potential for advancing prediction models through deep learning in the domain of plasma processing and highlights its application prospects in industrial settings.

• 해양환경안전학회지
• /
• 제25권7호
• /
• pp.898-905
• /
• 2019

유색 용존 유기물의 빛 흡수와 해빙의 가속화는 수생생태계와 열수지 역동성 간의 양적 피드백에 영향을 줄 수 있으므로 극지 해양에서 유색 용존 유기물의 장기 모니터링이 필요하게 되었다. 그러나 극지 환경에서의 관측은 용이하지 않은 접근성과 거친 기상으로 장기 모니터링이 쉽지 않다. 따라서 유색 용존 유기물의 장기 모니터링 장소로서 남극 세종 기지의 가능성을 확인하기 위해, 마리안 소만과 맥스웰 만에서 유색 용존 유기물의 분포와 외부로부터의 영향을 파악하기 위한 관측을 수행하였다. 맥스웰 만 내의 세종 부두와 세종 곶의 72시간 유색 용존 유기물의 변동성을 관측하고, 외부 영향이 없었던 세종 부두에서 2010년 2월에서 11월까지 10개월간 유색 용존 유기물의 연간 변화와 계절변동을 관측하였다. 세종 부두의 유색 용존 유기물 농도는 가을과 겨울 동안 가장 높고 봄과 여름에 감소하는 뚜렷한 계절 변동성을 보였고, 남극 인근 해역에서 측정된 유색 용존 유기물 농도 자료와 비교하였다. 따라서 우리는 남극해의 열수지에 대한 중요한 요인이자 광화학적 및 생물학적 환경변화에 관한 지시자인 유색 용존 유기물을 장기 모니터링을 위해 적합한 장소로 맥스웰 만의 세종 부두를 제안한다.

• 기술혁신학회지
• /
• 제4권1호
• /
• pp.79-95
• /
• 2001

This paper examines the effects of information telecommunication (IT) capital and R&D stock variation on the growth of Korean industry, using a time series approach. Most specifically, we apply the Granger causality and impulse response analysis to our examination of Koreas industrial growth, IT capital, and R&D stocks. The Johansen co-integration test is performed in order to analyze long-term relations among these variables. This research explores the way in which IT capital and R&D stocks variation from economic shocks affects the growth of Koreas industrial sector. The effects are ambiguous, however, across industrial sectors. An impulse response function analysis shows that the effects of IT capital and R&D stock fluctuations in each industrial sector are presented for different time periods.

• Journal of information and communication convergence engineering
• /
• 제6권3호
• /
• pp.249-254
• /
• 2008

Moored ocean buoys are technically feasible approach for making sustained time series observation in the oceans and will be an important component of any long-term ocean observing system. The 3M disc buoy carried Zeno 3200, MCCB, Orbcomm, Global Star and Bluetooth module. The deployments have relied on Orbcomm and Global Star as the primary satellite communications system. In addition to detailing our practical experience in the use of Orbcomm and Global Star as high latitudes, we will present some of scientific sensor results regarding real-time oceanographic and meteorological parameters such as wind speed, wave height and etc. In this paper we present the design and implementation of a small-scale buoy sensor network. One of the major challenges is that the network is hard to access after its deployment and hence both hardware and software must be robust and reliable.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 하계학술대회 논문집 A
• /
• pp.722-724
• /
• 2004

Demand estimates in electric power systems have traditionally consisted of time-series analyses over long time periods. The resulting database consisted of huge amounts of data that were then analyzed to create the various coefficients used to forecast power demand. In this research, we take advantage of universally used analysis techniques analysis, but we also use easily available data-mining techniques to analyze patterns of days and special days(holidays, etc.). We then present a new method for estimating and forecasting power flow using decision tree analysis. And because analyzing the relationship between the estimate and power system ceiling Trices currently set by the Korea Power Exchange. We included power system ceiling prices in our estimate coefficients and estimate method.

• 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.

• 한국전자통신학회논문지
• /
• 제18권1호
• /
• pp.115-126
• /
• 2023

무작위 및 주기적인 변동하는 재생에너지 발전 전력 품질 교란으로 인해 발전 변환 송전 및 배전에서 더 자주 발생하게 된다. 전력 품질 교란은 장비 손상 또는 정전으로 이어질 수 있다. 따라서 서로 다른 전력 품질 외란을 실시간으로 자동감지하고 분류하는 것이 필요하다. 전통적인 PQD 식별 방법은 특징 추출 특징 선택 및 분류의 세 단계로 구성된다. 그러나 수동으로 생성한 특징은 선택 단계에서 정확성을 보장하기 힘들어서 분류 정확도를 향상하는 데에는 한계가 있다. 본 논문에서는 16가지 종류의 전력 품질 신호를 인식하기 위해 CNN(Convolution Neural Networ)과 LSTM(Long Short Term Memory)을 기반으로 시간 영역과 주파수 영역의 특징을 결합한 심층 신경망 구조를 제안하였다. 주파수 영역 데이터는 주파수 영역 특징을 효율적으로 추출할 수 있는 FFT(Fast Fourier Transform)로 얻었다. 합성 데이터와 실제 6kV 전력 시스템 데이터의 성능은 본 연구에서 제안한 방법이 다른 딥러닝 방법보다 일반화되었음을 보여주었다.

• Journal of Preventive Medicine and Public Health
• /
• 제51권3호
• /
• pp.140-147
• /
• 2018

Objectives: Environmental pollution is a negative consequence of the development process, and many countries are grappling with this phenomenon. As a developing country, Iran is not exempt from this rule, and Iran pays huge expenditures for the consequences of pollution. The aim of this study was to analyze the long- and short-run impact of air pollution, along with other health indicators, on private and public health expenditures. Methods: This study was an applied and developmental study. Autoregressive distributed lag estimating models were used for the period of 1972 to 2014. In order to determine the co-integration between health expenditures and the infant mortality rate, fertility rate, per capita income, and pollution, we used the Wald test in Microfit version 4.1. We then used Eviews version 8 to evaluate the stationarity of the variables and to estimate the long- and short-run relationships. Results: Long-run air pollution had a positive and significant effect on health expenditures, so that a 1.00% increase in the index of carbon dioxide led to an increase of 3.32% and 1.16% in public and private health expenditures, respectively. Air pollution also had a greater impact on health expenditures in the long term than in the short term. Conclusions: The findings of this study indicate that among the factors affecting health expenditures, environmental quality and contaminants played the most important role. Therefore, in order to reduce the financial burden of health expenditures in Iran, it is essential to reduce air pollution by enacting and implementing laws that protect the environment.