• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.7-14
• /
• 2023

Recently, the importance of impact-based forecasting has increased along with the socio-economic impact of severe weather have emerged. As news articles contain unconstructed information closely related to the people's life, this study developed and evaluated a binary classification algorithm about snowfall damage information by using media articles text mining. We collected news articles during 2009 to 2021 which containing 'heavy snow' in its body context and labelled whether each article correspond to specific damage fields such as car accident. To develop a classifier, we proposed a probability-based classifier based on the ratio of the two conditional probabilities, which is defined as I/O Ratio in this study. During the construction process, we also adopted the n-gram approach to consider contextual meaning of each keyword. The accuracy of the classifier was 75%, supporting the possibility of application of news big data to the impact-based forecasting. We expect the performance of the classifier will be improve in the further research as the various training data is accumulated. The result of this study can be readily expanded by applying the same methodology to other disasters in the future. Furthermore, the result of this study can reduce social and economic damage of high impact weather by supporting the establishment of an integrated meteorological decision support system.

• Journal of the Korean Society of Safety
• /
• v.32 no.3
• /
• pp.83-89
• /
• 2017

A new technology has provided the nation, industry, society, and people with innovative and useful functions. National economy and society has been improved through this technology innovation. Despite the benefit of technology innovation, however, since technology society was sufficiently mature, the unintended side effect and negative impact of new technology on society and human beings has been highlighted. Thus, it is important to investigate a risk of new technology for the future society. Recently, the risks of the new technology are being suggested through a large amount of social data such as news articles and report contents. These data can be used as effective sources for quantitatively and systematically forecasting social risks of new technology. In this respect, this paper aims to propose a data-driven process for forecasting and assessing social risks of future new technology using the text mining, 4M(Man, Machine, Media, and Management) framework, and analytic hierarchy process (AHP). First, social risk factors are forecasted based on social risk keywords extracted by the text mining of documents containing social risk information of new technology. Second, the social risk keywords are classified into the 4M causes to identify the degree of risk causes. Finally, the AHP is applied to assess impact of social risk factors and 4M causes based on social risk keywords. The proposed approach is helpful for technology engineers, safety managers, and policy makers to consider social risks of new technology and their impact.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.4
• /
• pp.59-66
• /
• 2020

In this study, we consider the problem of forecasting the number of inbound foreigners visiting Korea. Forecasting tourism demand is an essential decision to plan related facilities and staffs, thus many studies have been carried out, mainly focusing on the number of inbound or outbound tourists. In order to forecast tourism demand, we use a seasonal ARIMA (SARIMA) model, as well as a SARIMAX model which additionally comprises an exogenous variable affecting the dependent variable, i.e., tourism demand. For constructing the forecasting model, we use a search procedure that can be used to determine the values of the orders of the SARIMA and SARIMAX. For the exogenous variable, we introduce factors that could cause the tourism demand reduction, such as the 9/11 attack, the SARS and MERS epidemic, and the deployment of THAAD. In this study, we propose a procedure, called Measuring Impact on Demand (MID), where the impact of each factor on tourism demand is measured and the value of the exogenous variable corresponding to the factor is determined based on the measurement. To show the performance of the proposed forecasting method, an empirical analysis was conducted where the monthly number of foreign visitors in 2019 were forecasted. It was shown that the proposed method can find more accurate forecasts than other benchmarks in terms of the mean absolute percentage error (MAPE).

• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.1
• /
• pp.11-25
• /
• 2021

The objective of this study was to analyze the impact of activation functions on flood forecasting model based on Artificial neural networks (ANNs). The traditional activation functions, the sigmoid and tanh functions, were compared with the functions which have been recently recommended for deep neural networks; the ReLU, leaky ReLU, and ELU functions. The flood forecasting model based on ANNs was designed to predict real-time runoff for 1 to 6-h lead time using the rainfall and runoff data of the past nine hours. The statistical measures such as R2, Nash-Sutcliffe Efficiency (NSE), Root Mean Squared Error (RMSE), the error of peak time (ETp), and the error of peak discharge (EQp) were used to evaluate the model accuracy. The tanh and ELU functions were most accurate with R2=0.97 and RMSE=30.1 (㎥/s) for 1-h lead time and R2=0.56 and RMSE=124.6~124.8 (㎥/s) for 6-h lead time. We also evaluated the learning speed by using the number of epochs that minimizes errors. The sigmoid function had the slowest learning speed due to the 'vanishing gradient problem' and the limited direction of weight update. The learning speed of the ELU function was 1.2 times faster than the tanh function. As a result, the ELU function most effectively improved the accuracy and speed of the ANNs model, so it was determined to be the best activation function for ANNs-based flood forecasting.

• Journal of Environmental Science International
• /
• v.32 no.8
• /
• pp.543-553
• /
• 2023

Weather forecasts and advisories provided by the national organizations in Korea that are used to identify and prevent disaster associated damage are often ineffective in reducing disasters as they only focus on predicting weather events (World Meteorological Organization(WMO ), 2015). In particular, typhoons are not a single weather disaster, but a complex weather disaster that requires advance preparation and assessment, and the WMO has established guidelines for the impact forecasting and recommends typhoon impact forecasting. In this study, we introduced the Typhoon-Ready System, which is a system that produces pre-disaster prevention information(risk level) of typhoon-related disasters across Korea and in detail for each region in advance, to be used for reducing and preventingtyphoon-related damage in Korea.

• Journal of Navigation and Port Research
• /
• v.26 no.2
• /
• pp.183-188
• /
• 2002

The forecast of a container traffic has been very important for port and development. Generally, Statistic methods, such as moving average method, exponential smoothing, and regression analysis have been much used for traffic forecasting. But, considering various factors related to the port affect the forecasting of container volume, neural network of parallel processing system can be effective to forecast container volume based on various factors. This study discusses the forecasting of volume by using the neural, network with back propagation learning algorithm. Affected factors are selected based on impact vector on neural network, and these selected factors are used to forecast container volume. The proposed the forecasting algorithm using neural network was compared to the statistic methods.

• International journal of advanced smart convergence
• /
• v.10 no.4
• /
• pp.59-65
• /
• 2021

Electricity contributes to the development of the economy. Therefore, forecasting electricity demand plays an important role in the development of the electricity industry in particular and the economy in general. This study aims to provide a precise model for long-term electricity demand forecast in the residential sector by using three independent variables include: Population, Electricity price, Average annual income per capita; and the dependent variable is yearly electricity consumption. Based on the support of Multiple variable regression, the proposed method established a model with variables that relate to the forecast by ignoring variables that do not affect lead to forecasting errors. The proposed forecasting model was validated using historical data from Vietnam in the period 2013 and 2020. To illustrate the application of the proposed methodology, we presents a five-year demand forecast for the residential sector in Vietnam. When demand forecasts are performed using the predicted variables, the R square value measures model fit is up to 99.6% and overall accuracy (MAPE) of around 0.92% is obtained over the period 2018-2020. The proposed model indicates the population's impact on total national electricity demand.

• Journal of Environmental Impact Assessment
• /
• v.14 no.2
• /
• pp.55-62
• /
• 2005

This study applied the Neural Network and Fuzzy theory to show water-purity control and preventive measure in water quality forecasting of the future river. This study picked out NAJU and HAMPYUNG as the subject of investigation and used monthly the water quality and the outflow data of KWANGJU2, NAJU, YOUNGSANNPO and HAMPYUNG from 1995 to 1999 to forecast BOD, COD, T-N, T-P water density. The datum from 1995 to 1999 are used for study and that of 2000 are used for verification. To develop model of water quality forecasting, firstly, this research formed Neural Network model and divided Neural Network model into two case - the case of considering lag and not considering. And this study selected optimal Neural Network model through changing the number of hidden layer based on input layer(n) from n to 3n. Through forecasting result, the case without considering lag showed more precise simulated result. Accordingly, this study intended to compare, analyse that Fuzzy model using the method without considering lag with Neural Network model. As a result, this study found that the model without considering lag in Neural Network Network shows the most excellent outcome. Thus this study examined a forecasting accuracy, analyzed result and verified propriety through appling the method of water quality forecasting using Neural Network and Fuzzy Algorithms to the actual case.

• Atmosphere
• /
• v.27 no.2
• /
• pp.189-197
• /
• 2017

Progressing from weather forecasts and warnings to multi-hazard impact-based forecast and warning services represents a paradigm shift in service delivery. Urban flooding is a typical meteorological disaster. This study proposes support plan for urban flooding impact-based forecast by providing inundation risk matrix. To achieve this goal, we first configured storm sewer management model (SWMM) to analyze 1D pipe networks and then grid based inundation analysis model (GIAM) to analyze 2D inundation depth over the Gangnam drainage area with $7.4km^2$. The accuracy of the simulated inundation results for heavy rainfall in 2010 and 2011 are 0.61 and 0.57 in POD index, respectively. 20 inundation scenarios responding on rainfall scenarios with 10~200 mm interval are produced for 60 and 120 minutes of rainfall duration. When the inundation damage thresholds are defined as pre-occurrence stage, occurrence stage to $0.01km^2$, 0.01 to $0.1km^2$, and $0.1km^2$ or more in area with a depth of 0.5 m or more, rainfall thresholds responding on each inundation damage threshold results in: 0 to 20 mm, 20 to 50 mm, 50 to 80 mm, and 80 mm or more in the rainfall duration 60 minutes and 0 to 30 mm, 30 to 70 mm, 70 to 110 mm, and 110 mm or more in the rainfall duration 120 minutes. Rainfall thresholds as a trigger of urban inundation damage can be used to form an inundation risk matrix. It is expected to be used for urban flood impact forecasting.

• Asian Journal of Innovation and Policy
• /
• v.9 no.2
• /
• pp.187-206
• /
• 2020

Under the on-going evolution of the COVID-19 pandemic, estimating the economic impact of the pandemic is highly uncertain and challenging. This situation makes it difficult for policymakers, governors, and economic entities to formulate appropriate responses and decision makings. To provide useful information about the effect of the COVID-19 pandemic on the Korean economy, this study examined macroeconomic impact analysis stemming from the pandemic shocks with different scenarios for the Korean economy. Based on three scenarios using the growth rate of 2020 GDP and consumer expenditure patterns, the 2021 GDP by industry sector was forecast with two new approaches. First, the recovering process of the Korean economy from the shock was analyzed by applying a Flex-IO method. Second, a new forecasting approach combined with an IO coefficient matrix was applied to forecast the future GDP changes. The findings of this study are summarized as follows: First, the total GDP growth rate under the Pessimistic Scenario demonstrates less rebound from the shock than that of the Base Scenario. Second, agriculture, culture, and tourism-related sectors that are suffering from the severe losses of COVID-19 showed lower resilience than other different industries. Third, information and communications technology (ICT) industry maintains a stable growth trend and is expected to take the leading role for the Korean economy in the post-COVID-19 and the Industry 4.0 eras. The findings deliver that it needs to analyze how government expenditure responding the shock into the forecasting model, which can be more useful and reliable to simulate the resilience from the pandemic.