• Korean Journal of Agricultural and Forest Meteorology
• /
• v.18 no.4
• /
• pp.199-207
• /
• 2016

This study was conducted to develop a forest fire occurrence model using meteorological characteristics for practical forecasting of forest fire danger rate by reflecting the climate change for the time period of 2000yrs. Forest fire in South Korea is highly influenced by humidity, wind speed, temperature, and precipitation. To effectively forecast forest fire occurrence, we developed a forest fire danger rating model using weather factors associated with forest fire in 2000yrs. Forest fire occurrence patterns were investigated statistically to develop a forest fire danger rating index using times series weather data sets collected from 76 meteorological observation centers. The data sets were used for 11 years from 2000 to 2010. Development of the national forest fire occurrence probability model used a logistic regression analysis with forest fire occurrence data and meteorological variables. Nine probability models for individual nine provinces including Jeju Island have been developed. The results of the statistical analysis show that the logistic models (p<0.05) strongly depends on the effective and relative humidity, temperature, wind speed, and rainfall. The results of verification showed that the probability of randomly selected fires ranges from 0.687 to 0.981, which represent a relatively high accuracy of the developed model. These findings may be beneficial to the policy makers in South Korea for the prevention of forest fires.

• Journal of Korean Society of Transportation
• /
• v.24 no.5 s.91
• /
• pp.89-108
• /
• 2006

Korea has been entering the ageing society as the population of age over 65 shared over 7% since the year 2000. The ageing society needs to have transportation facility considering elderly people's travel behavior. This study aims to understand the elderly people's travel behavior using recent data in Korea. The activity schedule approach begins with travel outcomes are part of an activitv scheduling decision. For tho?e approach. used discrete choice models (especially. Nested Logit Model) to address the basic modeling problem capturing decision interaction among the many choice dimensions of the immense activity schedule choice set The day activity schedule is viewed as a sot of tours and at-home activity episodes tied togather with overarching day activity pattern using the Seoul Metropolitan Area Transportation Survey data, which was conducted in June, 2002. Decisions about a specific tour in the schedule are conditioned by the choice of day activity pattern. The day activity scheduling model estimated in this study consists of tours interrelated in a day activity pattern. The day activity pattern model represents the basic decision of activity participation and priorities and places each activity in a configuration of tours and at-home episodes. Each pattern alternative is defined by the primary activity of the day, whether the primary activity occurs at home or away, and the type of tour for the primary activity. In travel mode choice of the elderly and non-workers, especially, travel cost was found to be important in understanding interpersonal variations in mode choice behavior though, travel time was found to be less important factor in choosing travel mode. In addition, although, generally, the elderly was likely to choose transit mode, private mode was preferred for the elderly over 75 years old owing to weakened physical health for such things as going up and down of stairs. Therefore. as entering the ageing society, transit mode should be invested heavily in transportation facility Planning tor improving elderly transportation service. Although the model has not yet been validated in before-and-after prediction studies. this study gives strong evidence of its behavioral soundness, current practicality. and potential for improving reliability of transportation Projects superior to those of the best existing systems in Korea.

• The Journal of Engineering Geology
• /
• v.32 no.4
• /
• pp.697-723
• /
• 2022

Data-driven models to predict groundwater levels 30 days in advance were developed for 12 groundwater monitoring stations in the middle-Jeju watershed, Jeju Island. Stacked long short-term memory (stacked-LSTM), a deep learning technique suitable for time series forecasting, was used for model development. Daily time series data from 2001 to 2022 for precipitation, groundwater usage amount, and groundwater level were considered. Various models were proposed that used different combinations of the input data types and varying lengths of previous time series data for each input variable. A general procedure for deep-learning-based model development is suggested based on consideration of the comparative validation results of the tested models. A model using precipitation, groundwater usage amount, and previous groundwater level data as input variables outperformed any model neglecting one or more of these data categories. Using extended sequences of these past data improved the predictions, possibly owing to the long delay time between precipitation and groundwater recharge, which results from the deep groundwater level in Jeju Island. However, limiting the range of considered groundwater usage data that significantly affected the groundwater level fluctuation (rather than using all the groundwater usage data) improved the performance of the predictive model. The developed models can predict the future groundwater level based on the current amount of precipitation and groundwater use. Therefore, the models provide information on the soundness of the aquifer system, which will help to prepare management plans to maintain appropriate groundwater quantities.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.111-126
• /
• 2020

Most industries have recently become aware of the importance of customer lifetime value as they are exposed to a competitive environment. As a result, preventing customers from churn is becoming a more important business issue than securing new customers. This is because maintaining churn customers is far more economical than securing new customers, and in fact, the acquisition cost of new customers is known to be five to six times higher than the maintenance cost of churn customers. Also, Companies that effectively prevent customer churn and improve customer retention rates are known to have a positive effect on not only increasing the company's profitability but also improving its brand image by improving customer satisfaction. Predicting customer churn, which had been conducted as a sub-research area for CRM, has recently become more important as a big data-based performance marketing theme due to the development of business machine learning technology. Until now, research on customer churn prediction has been carried out actively in such sectors as the mobile telecommunication industry, the financial industry, the distribution industry, and the game industry, which are highly competitive and urgent to manage churn. In addition, These churn prediction studies were focused on improving the performance of the churn prediction model itself, such as simply comparing the performance of various models, exploring features that are effective in forecasting departures, or developing new ensemble techniques, and were limited in terms of practical utilization because most studies considered the entire customer group as a group and developed a predictive model. As such, the main purpose of the existing related research was to improve the performance of the predictive model itself, and there was a relatively lack of research to improve the overall customer churn prediction process. In fact, customers in the business have different behavior characteristics due to heterogeneous transaction patterns, and the resulting churn rate is different, so it is unreasonable to assume the entire customer as a single customer group. Therefore, it is desirable to segment customers according to customer classification criteria, such as loyalty, and to operate an appropriate churn prediction model individually, in order to carry out effective customer churn predictions in heterogeneous industries. Of course, in some studies, there are studies in which customers are subdivided using clustering techniques and applied a churn prediction model for individual customer groups. Although this process of predicting churn can produce better predictions than a single predict model for the entire customer population, there is still room for improvement in that clustering is a mechanical, exploratory grouping technique that calculates distances based on inputs and does not reflect the strategic intent of an entity such as loyalties. This study proposes a segment-based customer departure prediction process (CCP/2DL: Customer Churn Prediction based on Two-Dimensional Loyalty segmentation) based on two-dimensional customer loyalty, assuming that successful customer churn management can be better done through improvements in the overall process than through the performance of the model itself. CCP/2DL is a series of churn prediction processes that segment two-way, quantitative and qualitative loyalty-based customer, conduct secondary grouping of customer segments according to churn patterns, and then independently apply heterogeneous churn prediction models for each churn pattern group. Performance comparisons were performed with the most commonly applied the General churn prediction process and the Clustering-based churn prediction process to assess the relative excellence of the proposed churn prediction process. The General churn prediction process used in this study refers to the process of predicting a single group of customers simply intended to be predicted as a machine learning model, using the most commonly used churn predicting method. And the Clustering-based churn prediction process is a method of first using clustering techniques to segment customers and implement a churn prediction model for each individual group. In cooperation with a global NGO, the proposed CCP/2DL performance showed better performance than other methodologies for predicting churn. This churn prediction process is not only effective in predicting churn, but can also be a strategic basis for obtaining a variety of customer observations and carrying out other related performance marketing activities.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.187-201
• /
• 2011

KOSPI200 index is the Korean stock price index consisting of actively traded 200 stocks in the Korean stock market. Its base value of 100 was set on January 3, 1990. The Korea Exchange (KRX) developed derivatives markets on the KOSPI200 index. KOSPI200 index futures market, introduced in 1996, has become one of the most actively traded indexes markets in the world. Traders can make profit by entering a long position on the KOSPI200 index futures contract if the KOSPI200 index will rise in the future. Likewise, they can make profit by entering a short position if the KOSPI200 index will decline in the future. Basically, KOSPI200 index futures trading is a short-term zero-sum game and therefore most futures traders are using technical indicators. Advanced traders make stable profits by using system trading technique, also known as algorithm trading. Algorithm trading uses computer programs for receiving real-time stock market data, analyzing stock price movements with various technical indicators and automatically entering trading orders such as timing, price or quantity of the order without any human intervention. Recent studies have shown the usefulness of artificial intelligent systems in forecasting stock prices or investment risk. KOSPI200 index data is numerical time-series data which is a sequence of data points measured at successive uniform time intervals such as minute, day, week or month. KOSPI200 index futures traders use technical analysis to find out some patterns on the time-series chart. Although there are many technical indicators, their results indicate the market states among bull, bear and flat. Most strategies based on technical analysis are divided into trend following strategy and non-trend following strategy. Both strategies decide the market states based on the patterns of the KOSPI200 index time-series data. This goes well with Markov model (MM). Everybody knows that the next price is upper or lower than the last price or similar to the last price, and knows that the next price is influenced by the last price. However, nobody knows the exact status of the next price whether it goes up or down or flat. So, hidden Markov model (HMM) is better fitted than MM. HMM is divided into discrete HMM (DHMM) and continuous HMM (CHMM). The only difference between DHMM and CHMM is in their representation of state probabilities. DHMM uses discrete probability density function and CHMM uses continuous probability density function such as Gaussian Mixture Model. KOSPI200 index values are real number and these follow a continuous probability density function, so CHMM is proper than DHMM for the KOSPI200 index. In this paper, we present an artificial intelligent trading system based on CHMM for the KOSPI200 index futures system traders. Traders have experienced on technical trading for the KOSPI200 index futures market ever since the introduction of the KOSPI200 index futures market. They have applied many strategies to make profit in trading the KOSPI200 index futures. Some strategies are based on technical indicators such as moving averages or stochastics, and others are based on candlestick patterns such as three outside up, three outside down, harami or doji star. We show a trading system of moving average cross strategy based on CHMM, and we compare it to a traditional algorithmic trading system. We set the parameter values of moving averages at common values used by market practitioners. Empirical results are presented to compare the simulation performance with the traditional algorithmic trading system using long-term daily KOSPI200 index data of more than 20 years. Our suggested trading system shows higher trading performance than naive system trading.

• Korean Journal of Agricultural Science
• /
• v.14 no.2
• /
• pp.263-271
• /
• 1987

The cyclical trend and seasonal variations of chestnut prices have been analyzed to find out the chestnut price fluctuation in Korea during 1966-1985. The optimum prices, production, and plantation area for the next twenty five years (1986-2010) have been forcasted by the derived equation models. The results of study can be summarized as follows: 1. The chestnut prices were increased by 14.67 percent per annum during 1966-1972, an d decreased by 9.24 percent during 1973-1985, due to the excessive production of chestnut. 2. The chestnut prices showed the lowest price during the harvesting season, especially in October (89.1), and highest in July (109.1). Seasonal fluctuation of chestnut prices were 0.0837 (C.V value) during 1966-1975, and 0.0706 during 1976-1985. Such a seasonal fluctuation of chestnut prices tends to be even with the passage of time. 3. The equation model of predicted chestnut prices was derived as follows : PR=117788.088 - 7.60 TC/Pop + 6.585 GNP/Pop The chestnut prices will be the lowest in 1988, but increased rapidly thereafter. 4. The equation model of optimum chestnut production was derived as follows : $${\ell}n\;PD/Pop=-8.5147-0.8267{\ell}n\;PR+3.3063{\ell}n\;GNP/Pop$$ To maintain optimum chestnut prices according to this model, chestnut production should be 133,000 ton for 1988, and 1,899,000 ton for 2010. 5. Optimum chestnut plantation area will be 4,000 ha in 1988, and thereafter total plantation area will be up to 57,400 ha in 2010.

• Korean journal of applied entomology
• /
• v.55 no.1
• /
• pp.35-43
• /
• 2016

The temperature-dependent development of Metcalfa pruinosa overwintering eggs was investigated at ten constant temperatures (12.5, 15, 17.5, 20, 22.5, 25, 27.5, 30, 32.5, and $35{\pm}1^{\circ}C$, Relative Humidity 20~30%). All individuals collected before April 13, 2012 failed to develop into first instar larvae. In contrast, some individuals that were collected on April 11, 2013 successfully developed when reared under $20{\sim}32.5^{\circ}C$ temperature regimes. The developmental duration was shortest at $30^{\circ}C$ (13.3 days) and longest at $15^{\circ}C$ (49.6 days) in the fourth collected colony (April 26 2013). Developmental duration decreased with increasing temperature up to $30^{\circ}C$ and development was retarded at high-temperature regimes ($32.5^{\circ}C$). The lower developmental threshold was $10.1^{\circ}C$ and the thermal constant required to complete egg overwintering was 252DD. The Lactin 2 model provided the best statistical description of the relationship between temperature and the developmental rate of M. pruinosa overwintering eggs ($r^2=0.99$). The distribution of the developmental completion of overwintering eggs was well described by the 2-parameter Weibull function ($r^2=0.92$) based on the standardized development duration. However, the estimated cumulative 50% spring emergence dates of overwintering eggs were best predicted by poikilotherm rate model combined with the 2-parameter Weibull model (average difference of 1.7days between observed and estimated dates).

• Journal of Korea Water Resources Association
• /
• v.49 no.7
• /
• pp.589-597
• /
• 2016

In this study, we investigated the use of satellite-derived flow (SDF) signals and a data-based model for the estimation of outflow for the river reach where in situ measurements are either completely unavailable or are difficult to access for hydraulic and hydrology analysis such as the upper basin of Imjin River. It has been demonstrated by many studies that the SDF signals can be used as the river width estimates and the correlation between SDF signals and river width is related to the shape of cross sections. To extract the nonlinear relationship between SDF signals and river outflow, Artificial Neural Network (ANN) model with SDF signals as its inputs were applied for the computation of flow discharge at Imjin Bridge located in Imjin River. 15 pixels were considered to extract SDF signals and Partial Mutual Information (PMI) algorithm was applied to identify the most relevant input variables among 150 candidate SDF signals (including 0~10 day lagged observations). The estimated discharges by ANN model were compared with the measured ones at Imjin Bridge gauging station and correlation coefficients of the training and validation were 0.86 and 0.72, respectively. It was found that if the 1 day previous discharge at Imjin bridge is considered as an input variable for ANN model, the correlation coefficients were improved to 0.90 and 0.83, respectively. Based on the results in this study, SDF signals along with some local measured data can play an useful role in river flow estimation and especially in flood forecasting for data-scarce regions as it can simulate the peak discharge and peak time of flood events with satisfactory accuracy.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.12 no.1
• /
• pp.11-22
• /
• 2010

According to IPCC 4th Assessment Report, concentration of carbon dioxide has been increasing by 30% since Industrial Revolution. Most of IPCC $CO_2$ emission scenarios estimate that the concentration will reach up to double of its present level within 100-year if the current tendency continues. The global warming has resulted in the agro-climate change over the Korean Peninsula as well. Accordingly, it is necessary to understand the future agro-climate induced by the increase of greenhouse gases in terms of the agro-climatic indices in the Korean peninsula. In this study, the future climate is simulated by an atmosphere/ocean/land surface/sea ice coupled general circulation climate model, Pusan National University Coupled General Circulation Model(hereafter, PNU CGCM), and by a regional weather prediction model, Weather Research and Forecasting Model(hereafter, WRF) for the purpose of a dynamical downscaling. The changes of the vegetable period and the crop growth period, defined as the total number of days of a year exceeding daily mean temperature of 5 and 10, respectively, have been analyzed. Our results estimate that the beginning date of vegetable and crop growth periods get earlier by 3.7 and 17 days, respectively, in spring under the $CO_2$-doubled climate. In most of the Korean peninsula, the predicted frost days in spring decrease by 10 days. Climatic production index (CPI), which closely represent the productivity of rice, tends to increase in the double $CO_2$ climate. Thus, it is suggested that the future $CO_2$ doubled climate might be favorable for crops due to the decrease of frost days in spring, and increased temperature and insolation during the heading date as we expect from the increased CPI.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.11 no.4
• /
• pp.192-205
• /
• 2009

The unexpected wind over the Mt. Hwawang on 9 February 2009 was deadly when many spectators were watching a traditional event to burn dried grasses and the fire went out of control due to the wind. We analyzed the fatal wind based on wind flow simulations over a digitized complex terrain of the mountain with a localized heating area using a three dimensional computational fluid dynamics model, CFD_NIMR_SNU (Computational Fluid Dynamics_National Institute of Meteorological Research_Seoul National University). Three levels of fire intensity were simulated: no fire, $300^{\circ}C$ and $600^{\circ}C$ of surface temperature at the site on fire. The surface heat accelerated vertical wind speed by as much as $0.7\;m\;s^{-1}$ (for $300^{\circ}C$) and $1.1\;m\;s^{-1}$ (for $600^{\circ}C$) at the center of the fire. Turbulent kinetic energy was increased by the heat itself and by the increased mechanical force, which in turn was generated by the thermal convection. The heating together with the complex terrain and strong boundary wind induced the unexpected high wind conditions with turbulence at the mountain. The CFD_NIMR_SNU model provided valuable analysis data to understand the consequences of the fatal mountain fire. It is suggested that the place of fire was calm at the time of the fire setting due to the elevated terrain of the windward side. The suppression of wind was easily reversed when there was fire, which caused updraft of hot air by the fire and the strong boundary wind. The strong boundary wind in conjunction with the fire event caused the strong turbulence, resulting in many fire casualties. The model can be utilized in turbulence forecasting over a small area due to surface fire in conjunction with a mesoscale weather model to help fire prevention at the field.