• 대한토목학회논문집
• /
• 제38권5호
• /
• pp.671-683
• /
• 2018

도시유역에 대한 집중호우에 따른 침수피해가 증가하고 있으며, 기존에 수행된 많은 연구에서 입증 되어진 바와 같이 도시 침수는 하수관망의 통수능을 상회함에 따라 발생하는 내수침수에 주로 기인하고 있다. 도시화가 상당히 진행되고 인구가 밀집되어 있는 지역에 대한 침수피해는 심각한 사회 경제적 피해를 야기한다. 이에 따라 도시지역에 대한 홍수 예측을 위한 확정 및 확률론적 연구가 진행되어 왔지만, 충분한 선행시간을 확보하며 단시간에 홍수량에 대한 예측결과를 도출하기에는 부족한 실정이다. 본 연구에서는 최적의 실시간 도시 홍수 예측 기법을 제시하기 위하여 도시유출해석 기반 실시간 홍수 예측을 위한 IDNN, TDNN 그리고 NARX 동적신경망을 비교하였다. 강남 지역의 2010, 2011년 실제 호우사상에 대하여 총 홍수량 예측 결과, 입력 지연 인공신경망의 최대 Nash-Sutcliffe 효율 계수는 각각 0.86, 0.53, 시간 지연 인공신경망의 경우 0.92, 0.41, 외생변수를 이용한 비선형 자기 회귀의 경우 0.99, 0.98으로 나타났다. 연구 대상지역에 대한 각 맨홀 누적월류량을 고려한 예측 결과의 오차분석을 통하여 외생변수를 이용한 비선형 자기 회귀 기법을 사용하는 것이 추후 도시 홍수 대응체계 구축에 적합할 것으로 나타났다.

• 한국항해항만학회지
• /
• 제35권1호
• /
• pp.83-91
• /
• 2011

예측의 정확성은 비용의 감소나 고객서비스의 제고를 위해 필수적으로 선행되어야 하기에 현재까지도 많은 연구자들에 의해 연구되고 있는 분야이다. 본 연구에서는 국내 항만의 컨테이너 물동량 예측에 있어 대표적인 비선형예측모형인 인공신경망모형과 ARIMA모형에 대한 비교연구를 수행하는데 목적을 두었고, 컨테이너 물동량 예측력 제고를 위해 ARIMA모형과 인공신경망(ANN)모형을 결합한 하이브리드모형을 사용해 다른 모형들과 예측성과를 비교하고자 한다. 특히 인공신경망모형의 네트워크 구조 설계에 부분에 있어 방대하며 복잡한 탐색공간에서도 전역해 찾기에 효과적인 기법으로 알려져 있는 유전알고리즘을 사용함과 동시에 인공신경망의 대표적인 모형으로 알려진 다층 퍼셉트론(MLP)뿐만 아니라 시간지연네트워크(TDNN)를 사용해 예측성과를 비교하였다. 그 결과 ANN모형과 하이브리드모형이 ARIMA모형보다 더 뛰어난 예측성과를 보이는 것으로 나왔다.

• Structural Engineering and Mechanics
• /
• 제50권1호
• /
• pp.105-119
• /
• 2014

This study presents a steel container crane movement analysis and assessment based on structural health monitoring (SHM). The accelerometers are used to monitor the dynamic crane behavior and a 3-D finite element model (FEM) was designed to express the static displacement of the crane under the different load cases. The multi-input single-output nonlinear autoregressive neural network with external input (NNARX) model is used to identify the crane dynamic displacements. The FEM analysis and the identification model are used to investigate the safety and the vibration state of the crane in both time and frequency domains. Moreover, the SHM system is used based on the FEM analysis to assess the crane behavior. The analysis results indicate that: (1) the mean relative dynamic displacement can reveal the relative static movement of structures under environmental load; (2) the environmental load conditions clearly affect the crane deformations in different load cases; (3) the crane deformations are shown within the safe limits under different loads.

• The Journal of Asian Finance, Economics and Business
• /
• 제8권9호
• /
• pp.165-176
• /
• 2021

The paper has used the Solow-Swan growth model to analyze the long-term impact of credit market development and stock market development on economic growth in Asia from 2000 to 2019. The empirical model is performed with panel cointegration analysis by Common Correlated Effects (CCE) method with cross-sectional dependencies. The results find that there exists a cointegration relationship among stock market, credit market development, and economic growth. These results also show that financial structure improves the exact impact of financial development on economic growth, namely the opposite effect of stock market development and credit market development. Moreover, the Granger causality test reveals a bi-directional relationship between credit market development and economic growth, while only unidirectional causality from stock market development to economic growth for the whole group panel. And it is different for a specific country, according to Kónya's test. The view of the new structuralism does not apply in the Asian financial system when we estimate the Nonlinear Autoregressive Distributed Lag model (NARDL) to analyze the asymmetric relationship between financial structure and economic growth. On the whole, policymakers can draw on the findings to provide policy implications to improve their country's financial system as well as pursue the goal of sustainable economic growth.

• The Journal of Asian Finance, Economics and Business
• /
• 제8권5호
• /
• pp.43-52
• /
• 2021

This study is the first to scrutinize how real effective exchange rate, together with the vehicle currency exchange rate, asymmetrically influences the total trade balance between ASEAN (Association of Southeast Asian Nations) and the EU (European Union). This research employs quarterly data between 2000Q1 and 2018Q1, which is derived from several sources. We introduce a method for constructing the double-aggregated real effective exchange rate between ASEAN and the EU that captures the roles of all their currencies. Moreover, we propose the formula to compute vehicle currency exchange rate to assess the importance of vehicle currency in ASEAN-EU trade. Additionally, as asymmetrical impacts of exchange rate on trade balance are well documented by current studies, we employ Nonlinear Autoregressive Distributed Lag (NARDL) model of Shin et al. (2014) to analyze the impacts of currency depreciation as well as appreciation in detail. The findings confirm the prominence of USD as vehicle currency in ASEAN-EU trade. Both depreciation and appreciation of ASEAN's currencies against USD can foster ASEAN's trade balance in the long run. Short-run asymmetrical impacts as well as J-curve effect are found in the vehicle currency models only. The results are robust for the cases of EU-28 and EU-27.

• Nuclear Engineering and Technology
• /
• 제51권3호
• /
• pp.702-708
• /
• 2019

This paper deals with break size estimation of loss of coolant accidents (LOCA) using a nonlinear autoregressive with exogenous inputs (NARX) neural network. Previous studies used static approaches, requiring time-integrated parameters and independent firing algorithms. NARX neural network is able to directly deal with time-dependent signals for dynamic estimation of break sizes in real-time. The case studied is a LOCA in the primary system of Bushehr nuclear power plant (NPP). In this study, number of hidden layers, neurons, feedbacks, inputs, and training duration of transients are selected by performing parametric studies to determine the network architecture with minimum error. The developed NARX neural network is trained by error back propagation algorithm with different break sizes, covering 5% -100% of main coolant pipeline area. This database of LOCA scenarios is developed using RELAP5 thermal-hydraulic code. The results are satisfactory and indicate feasibility of implementing NARX neural network for break size estimation in NPPs. It is able to find a general solution for break size estimation problem in real-time, using a limited number of training data sets. This study has been performed in the framework of a research project, aiming to develop an appropriate accident management support tool for Bushehr NPP.

• 전력전자학회논문지
• /
• 제26권6호
• /
• pp.381-389
• /
• 2021

Most diagnosis approaches rely on historical failure data that might not be feasible in real operating conditions because the battery voltage and internal parameters are nonlinear according to various operating conditions, such as cell-to-cell configuration and initial condition. To overcome this issue, the estimator and the predictor require integrated approaches that consider comprehensive data, with the degradation process and measured data taken into account. In this paper, vector autoregressive models (VAR) with various parameters that affect overdischarge to the cell in the battery pack were constructed, and the cell-to-cell parameters were identified using an adaptive model to analyze the influence of failure prognosis. The theoretical analysis is validated using experimental results in terms of the feasibility and advantages of fault prognosis.

• Nuclear Engineering and Technology
• /
• 제54권5호
• /
• pp.1664-1673
• /
• 2022

Achieving sustainable development requires an increasing share of green technologies. World energy demand is expected to rise significantly especially in developing economies. The increasing energy demands will be entertained with conventional energy sources at the cost of higher emissions unless eco-friendly technologies are used. This study examines the asymmetric effects of nuclear energy on carbon emissions for Pakistan from 1974 to 2019. Augmented Dickey-Fuller (ADF) and Phillips Perron (PP) unit root tests suggest that variables are integrated of order one and bound test of Autoregressive Distributed Lag (ARDL) and nonlinear ARDL confirm a long-run relationship among selected variables. The ARDL, Fully Modified Ordinary Least Squares (FMOLS), and Dynamic Ordinary Least Squares (DOLS) results show that the coefficient of nuclear energy has a negative and significant impact on emissions in both short and long run. Further, the NARDL finding shows that there exists an asymmetric long-run association between nuclear energy and CO₂ emissions. The vector error correction method (VECM) results indicate that there exists a bidirectional causal relationship between nuclear energy and carbon emissions in both the short and long run. Additionally, the impact of nuclear energy on ecological footprint has been examined and our findings remain robust.

• The Journal of Asian Finance, Economics and Business
• /
• 제10권1호
• /
• pp.79-89
• /
• 2023

The paper aims to investigate the asymmetric long-run and short-run relationships between inflation and remittance outflows in the Kingdom of Saudi Arabia (hereafter KSA) over the period 1971-2019 by using the Nonlinear Autoregressive Distributed Lag (NARDL) model. The statistical tests have supported the validity and stability of the model. The Wald F-test statistics confirm the existence of a long-run equilibrium relationship among the model variables; remittance outflows, positive (negative) shocks in inflation rates, investment, real GDP, and trade openness. Moreover, the empirical results confirm the existence of an asymmetric effect of the inflation rate on remittance outflows. The response of foreign workers to an increase in inflation rates differs from their response to a decrease in inflation rates. However, this asymmetric relationship between the increases/decreases in inflation and remittance outflows is significantly weak. The weakness of this relationship is due to the high marginal remittance propensity of migrant workers, which is explained by the low consumption propensity of foreign workers and their ability to adjust to the high cost of living due to inflation and the imposition of accompanying fees. Finally, the change in the inflation rate is not among the main factors influencing foreign remittance decisions in Saudi Arabia.

• 경영과정보연구
• /
• 제39권2호
• /
• pp.17-37
• /
• 2020

본 연구의 목적은 2007년~2010년 유로 도입 이후 금융위기 및 그에 따른 EU 부채위기까지의 기간 내에 미국, 유럽 및 BRIC 금융시장 간의 선형과 비선형 인과관계의 존재를 통해 글로벌 전이효과를 조사하는데 있다. 금융위기로 인한 글로벌 전이효과가 잘 설명되어 있지만, 미국, 유럽 및 BRIC 주식시장 간의 변동성 전이효과의 특성 뿐만 아니라 전달 메커니즘은 체계적으로 조사되지 않았다. 동적 선형 및 비선형 인과관계를 조사하기 위해 단계적인 필터링 방법론이 도입되었는데, 이는 벡터자기회귀모형과 다변량 GARCH 모형을 포함한다. 본 논문의 표본은 유로 이후 기간을 포함하고 또한 2007년 금융위기, 2008년 글로벌 금융위기, 2010년 유로존 부채위기도 포함한다. 본 연구의 실증결과는 BRIC 주식시장의 효율성에 많은 함의를 가질 수 있는데 시장의 예측가능성에 영향을 미칠 뿐만 아니라 시장의 금융통합의 과정을 수량화하기 위해서 미래의 연구에 유용할 수 있다. 미국, 유럽 및 BRIC 간의 상호 의존성이 감지되면 금융시장 규제, 헤징 및 거래 전략에 대한 중요한 함의를 나타낼 수 있다. 또한 결과는 BRIC이 미국발 서브프라임 금융위기 이후 국제적으로 통합되고 있고 전이효과가 더욱 구체화 되어 현저하게 나타나고 있다는 것을 보여준다. 더욱이, 탈동조화 견해를 지지하는 일관된 증거가 전혀 없다. 일부 비선형 인과관계는 조사기간 동안 필터링 후에도 지속된다. 비록 꼬리분포 의존성과 고적률이 나머지 상호 의존성의 유의한 요소일 수 있을지라도, 이것은 비선형 인과관계가 단순한 변동성 효과에 의해 대체로 설명될 수 있다.