• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.167-167
• /
• 2018

토양수분은 토양에 포함된 평균 수분량을 나타내며 수문 순환 관점에서 매우 중요한 수문변량 중 하나이다. 본 연구에서는 대표적인 기계학습 방법인 Support Vector Machine (SVM)을 이용한 토양 함수 예측 기법을 개발하고자 하며, 예측인자로서 원격 탐측 기반의 토양함수자료, 강수량, 온도 등을 활용하고자 한다. SVM은 Kernel 함수를 이용하여 복잡한 비선형 관계를 선형 가정을 통해서 해석하는 기계학습 방법으로서 전역모델(global model)로서 다양한 수문기상분야에 적용이 이루어지고 있다. SVM의 장점은 일정 부분의 오차를 허용함으로서 모형의 일반화 측면에서 기존 인공신경망(artificial neural network, ANN)에 비해 우수한 성능을 나타내며, 특히 예측모형으로서 적용성이 매우 크다. 본 연구에서는 과거 토양 함수 자료와 강수, 온도, 위성 관측 기반 정보 등을 이용하여 모형을 적합시키고 이를 미계측 유역으로 확장하는데 연구의 목적이 있으며, 본 연구를 통해 제안된 모형은 용담댐 시험유역을 대상으로 적용되며 기존 ANN 모형 및 다중회귀분석 결과와 비교를 통해 모형의 적합성을 평가하고자한다.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.2
• /
• pp.327-335
• /
• 2016

The People's Republic of China has vigorously been pursuing the internationalization of the Chinese Yuan or Renminbi after the financial crisis of 2008. In this view, an abrupt increase of use of the Chinese Yuan in the onshore and offshore markets are important milestones to be one of important currencies. One of the most frequently used methods to forecast volatility is GARCH model. Since a prediction error of the GARCH model has been reported quite high, a lot of efforts have been made to improve forecasting capability of the GARCH model. In this paper, we have proposed MLP-GARCH and a DL-GARCH by employing Artificial Neural Network to the GARCH. In an application to forecasting Chinese Yuan volatility, we have successfully shown their overall outperformance in forecasting over the GARCH.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.435-447
• /
• 2019

In order to prevent unnecessary re-admission, it is necessary to intensively manage the groups with high probability of re-admission. For this, it is necessary to develop a re-admission prediction model. Two - year discharge summary data of one university hospital were collected from 2016 to 2017 to develop a predictive model of re-admission. In this case, the re-admitted patients were defined as those who were discharged more than once during the study period. We conducted descriptive statistics and crosstab analysis to identify the characteristics of rehospitalized patients. The re-admission prediction model was developed using logistic regression, neural network, and decision tree. AUC (Area Under Curve) was used for model evaluation. The logistic regression model was selected as the final re-admission predictive model because the AUC was the best at 0.81. The main variables affecting the selected rehospitalization in the logistic regression model were Residental regions, Age, CCS, Charlson Index Score, Discharge Dept., Via ER, LOS, Operation, Sex, Total payment, and Insurance. The model developed in this study was limited to generalization because it was two years data of one hospital. It is necessary to develop a model that can collect and generalize long-term data from various hospitals in the future. Furthermore, it is necessary to develop a model that can predict the re-admission that was not planned.

• Journal of Korea Water Resources Association
• /
• v.40 no.1 s.174
• /
• pp.73-88
• /
• 2007

The goal of this research is to develop and apply the generalized regression neural networks model(GRNNM) embedding genetic algorithm(GA) for the estimation and calculation of the pan evaporation(PE), which is missed or ungaged and of the alfalfa reference evapotranspiration ($ET_r$), which is not measured in South Korea. Since the observed data of the alfalfa 37. using Iysimeter have not been measured for a long time in South Korea, the Penman-Monteith(PM) method is used to estimate the observed alfalfa $ET_r$. In this research, we develop the COMBINE-GRNNM-GA(Type-1) model for the calculation of the optimal PE and the alfalfa $ET_r$. The suggested COMBINE-GRNNM-GA(Type-1) model is evaluated through training, testing, and reproduction processes. The COMBINE-GRNNM-GA(Type-1) model can evaluate the suggested climatic variables and also construct the reliable data for the PE and the alfalfa $ET_r$. We think that the constructive data could be used as the reference data for irrigation and drainage networks system in South Korea.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.207-221
• /
• 2023

This study suggests deep neural network models for estimating air temperature with Level 1B (L1B) datasets of GEO-KOMPSAT-2A (GK-2A). The temperature at 1.5 m above the ground impact not only daily life but also weather warnings such as cold and heat waves. There are many studies to assume the air temperature from the land surface temperature (LST) retrieved from satellites because the air temperature has a strong relationship with the LST. However, an algorithm of the LST, Level 2 output of GK-2A, works only clear sky pixels. To overcome the cloud effects, we apply a deep neural network (DNN) model to assume the air temperature with L1B calibrated for radiometric and geometrics from raw satellite data and compare the model with a linear regression model between LST and air temperature. The root mean square errors (RMSE) of the air temperature for model outputs are used to evaluate the model. The number of 95 in-situ air temperature data was 2,496,634 and the ratio of datasets paired with LST and L1B show 42.1% and 98.4%. The training years are 2020 and 2021 and 2022 is used to validate. The DNN model is designed with an input layer taking 16 channels and four hidden fully connected layers to assume an air temperature. As a result of the model using 16 bands of L1B, the DNN with RMSE 2.22℃ showed great performance than the baseline model with RMSE 3.55℃ on clear sky conditions and the total RMSE including overcast samples was 3.33℃. It is suggested that the DNN is able to overcome cloud effects. However, it showed different characteristics in seasonal and hourly analysis and needed to append solar information as inputs to make a general DNN model because the summer and winter seasons showed a low coefficient of determinations with high standard deviations.

• Journal of Intelligence and Information Systems
• /
• v.11 no.3
• /
• pp.69-81
• /
• 2005

As the competition in business becomes severe, companies are focusing their capacity on customer relationship management (CRM) for survival. One of the important issues in CRM is to build a purchase prediction model, which classifies customers into either purchasing or non-purchasing groups. Until now, various techniques for building purchase prediction models have been proposed. However, they have been criticized because their performances are generally low, or it requires much effort to build and maintain them. Thus, in this study, we propose the support vector machine (SVM) a tool for building a purchase prediction model. The SVM is known as the technique that not only produces accurate prediction results but also enables training with the small sample size. To validate the usefulness of SVM, we apply it and some of other comparative techniques to a real-world purchase prediction case. Experimental results show that SVM outperforms all the comparative models including logistic regression and artificial neural networks.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.157-173
• /
• 2011

As the Internet use explodes recently, the malicious attacks and hacking for a system connected to network occur frequently. This means the fatal damage can be caused by these intrusions in the government agency, public office, and company operating various systems. For such reasons, there are growing interests and demand about the intrusion detection systems (IDS)-the security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. The intrusion detection models that have been applied in conventional IDS are generally designed by modeling the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. These kinds of intrusion detection models perform well under the normal situations. However, they show poor performance when they meet a new or unknown pattern of the network attacks. For this reason, several recent studies try to adopt various artificial intelligence techniques, which can proactively respond to the unknown threats. Especially, artificial neural networks (ANNs) have popularly been applied in the prior studies because of its superior prediction accuracy. However, ANNs have some intrinsic limitations such as the risk of overfitting, the requirement of the large sample size, and the lack of understanding the prediction process (i.e. black box theory). As a result, the most recent studies on IDS have started to adopt support vector machine (SVM), the classification technique that is more stable and powerful compared to ANNs. SVM is known as a relatively high predictive power and generalization capability. Under this background, this study proposes a novel intelligent intrusion detection model that uses SVM as the classification model in order to improve the predictive ability of IDS. Also, our model is designed to consider the asymmetric error cost by optimizing the classification threshold. Generally, there are two common forms of errors in intrusion detection. The first error type is the False-Positive Error (FPE). In the case of FPE, the wrong judgment on it may result in the unnecessary fixation. The second error type is the False-Negative Error (FNE) that mainly misjudges the malware of the program as normal. Compared to FPE, FNE is more fatal. Thus, when considering total cost of misclassification in IDS, it is more reasonable to assign heavier weights on FNE rather than FPE. Therefore, we designed our proposed intrusion detection model to optimize the classification threshold in order to minimize the total misclassification cost. In this case, conventional SVM cannot be applied because it is designed to generate discrete output (i.e. a class). To resolve this problem, we used the revised SVM technique proposed by Platt(2000), which is able to generate the probability estimate. To validate the practical applicability of our model, we applied it to the real-world dataset for network intrusion detection. The experimental dataset was collected from the IDS sensor of an official institution in Korea from January to June 2010. We collected 15,000 log data in total, and selected 1,000 samples from them by using random sampling method. In addition, the SVM model was compared with the logistic regression (LOGIT), decision trees (DT), and ANN to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell 4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on SVM outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that our model reduced the total misclassification cost compared to the ANN-based intrusion detection model. As a result, it is expected that the intrusion detection model proposed in this paper would not only enhance the performance of IDS, but also lead to better management of FNE.