• Journal of KIISE:Information Networking
• /
• v.36 no.3
• /
• pp.173-183
• /
• 2009

We present a real-time monitoring system for detecting anomalous network events using the entropy. The entropy accounts for the effects of disorder in the system. When an abnormal factor arises to agitate the current system the entropy must show an abrupt change. In this paper we deliberately model the Internet to measure the entropy. Packets flowing between these two networks may incur to sustain the current value. In the proposed system we keep track of the value of entropy in time to pinpoint the sudden changes in the value. The time-series data of entropy are transformed into the two-dimensional domains to help visually inspect the activities on the network. We examine the system using network traffic traces containing notorious worms and DoS attacks on the testbed. Furthermore, we compare our proposed system of time series forecasting method, such as EWMA, holt-winters, and PCA in terms of sensitive. The result suggests that our approach be able to detect anomalies with the fairly high accuracy. Our contributions are two folds: (1) highly sensitive detection of anomalies and (2) visualization of network activities to alert anomalies.

• Journal of Korean Society of Transportation
• /
• v.34 no.1
• /
• pp.1-14
• /
• 2016

In the recent years, the internet has become accessible without limitation of time and location to anyone with smartphones. It resulted in more convenient travel information access both on the pre-trip and en-route phase. The main objective of this study is to conduct a stationary test for traffic information web/mobile application access indexes from TCS (Toll Collection System); and analyzing the relationship between the web/mobile application access indexes and actual traffic volume on expressways, in order to analyze searching behavior of expressway related travel information. The key findings of this study are as follows: first, the results of ADF-test and PP-test confirm that the web/mobile application access indexes by time periods satisfy stationary conditions even without log or differential transformation. Second, the Pearson correlation test showed that there is a strong and positive correlation between the web/mobile application access indexes and expressway entry and exit traffic volume. In contrast, truck entry traffic volume from TCS has no significant correlation with the web/mobile application access indexes. Third, the time gap relationship between time-series variables (i.e., concurrent, leading and lagging) was analyzed by cross-correlation tests. The results indicated that the mobile application access leads web access, and the number of mobile application execution is concurrent with all web access indexes. Lastly, there was no web/mobile application access indexes leading expressway entry traffic volumes on expressways, and the highest correlation was observed between webpage view/visitor/new visitor/repeat visitor/application execution counts and expressway entry volume with a lag of one hour. It is expected that specific individual travel behavior can be predicted such as route conversion time and ratio if the data are subdivided by time periods and areas and utilizing traffic information users' location.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.19-43
• /
• 2016

This study examines the causes of the Asian exchange rate crisis and compares it to the European Monetary System crisis. In 1997, emerging countries in Asia experienced financial crises. Previously in 1992, currencies in the European Monetary System had undergone the same experience. This was followed by Mexico in 1994. The objective of this paper lies in the generation of useful insights from these crises. This research presents a comparison of South Korea, United Kingdom and Mexico, and then compares three different models for prediction. Previous studies of economic crisis focused largely on the manual construction of causal models using linear techniques. However, the weakness of such models stems from the prevalence of nonlinear factors in reality. This paper uses a structural equation model to analyze the causes, followed by a neural network model to circumvent the linear model's weaknesses. The models are examined in the context of predicting exchange rates In this paper, data were quarterly ones, and Consumer Price Index, Gross Domestic Product, Interest Rate, Stock Index, Current Account, Foreign Reserves were independent variables for the prediction. However, time periods of each country's data are different. Lisrel is an emerging method and as such requires a fresh approach to financial crisis prediction model design, along with the flexibility to accommodate unexpected change. This paper indicates the neural network model has the greater prediction performance in Korea, Mexico, and United Kingdom. However, in Korea, the multiple regression shows the better performance. In Mexico, the multiple regression is almost indifferent to the Lisrel. Although Lisrel doesn't show the significant performance, the refined model is expected to show the better result. The structural model in this paper should contain the psychological factor and other invisible areas in the future work. The reason of the low hit ratio is that the alternative model in this paper uses only the financial market data. Thus, we cannot consider the other important part. Korea's hit ratio is lower than that of United Kingdom. So, there must be the other construct that affects the financial market. So does Mexico. However, the United Kingdom's financial market is more influenced and explained by the financial factors than Korea and Mexico.

• The Journal of Engineering Geology
• /
• v.33 no.1
• /
• pp.189-200
• /
• 2023

As urbanization and industrialization increase development in downtown areas, damage due to ground settlement continues to occur. Building collapse in urban has a high risk of leading to large-scale damage to life and property. However, there has rarely been studied on measurement data analysis methods when uneven loads are applied to the excavated ground and no prior knowledge of the ground. Accordingly, it was attempted to analyze the relative settlement behavior and correlation by processing the time-series surface settlement of construction sites in the urban. In this paper, the average index of difference in settlement and average of relative difference in settlement are defined and calculated, then plotted in the coordinate system to analyze the relative settlement behavior over time. In addition, since there was no prior knowledge of the ground, a standard to classify the clusters was needed, and the observation points were classified into using k-means clustering and Dunn Index. As a result of the analysis, it was confirmed that all the clusters moved to the stable region as the settlement amount converges. The clusters were segmented. Based on the analysis results, it was possible to distinguish between the independent displacement area and same behavior area by analyzing the correlation between measurement points. If possible to analyze the relative settlement behavior between the stations and classify the behavior areas, it can be helpful in settlement and stability management, such as uplift of the surrounding area, prediction of ground failure area, and prevention of activity failure.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.394-394
• /
• 2015

급격히 변화하고 있는 산업화와 도시화로 지구 온난화 현상으로 기상이변의 발생빈도가 높아졌고 기후가 불안정하여 예전보다 많은 집중호우가 발생하면서, 홍수로 인한 제내지 침수가 발생되기도 한다. 기후변화로 인한 수재해에 대응하기 위하여 하천 호소 수리 예측 모형의 개선이 필요한 실정이다. 하지만, 자연하천 유역의 강우-유출 상관관계와 지표면 유출현상 및 하도 수리 특성을 자연현상의 복잡성, 강우발생의 시간적 공간적인 발생과정의 임의성, 정확한 해석방법 및 확률 분석에 따르는 불확실성 들을 토대로 단순한 이론과 제한적인 경험공식 등에 의해서 해석, 재현 및 평가를 한다는 것은 매우 어려운 문제이다. 최근 IT 기술의 발전과 더불어, 많은 연구자, 엔지니어들이 기존 수리 수문학적 지식과 IT기술을 융합하여 복잡 다단한 수자원 환경 문제를 해결하고자 한다. 이와 같은 최근 연구 동향에 의거하여, 본 연구에서는 HEC-RAS, TELEMAC-2D 1, 2차원 수리 모형을 연계하여 하천 흐름 분석 및 홍수 범람 해석에 적용하였다. 본 연구에서는 HEC-RAS, TELEMAC 모형을 적용하여 2012년 태풍 '산바(SANBA)'로 인해 홍수 피해를 입은 고령군에 위치한 낙동강 본류 회천 유역(상류 회천교 ~ 하류 도진교)의 하도 내 흐름 분석과 하천 인근 제내지 홍수범람을 예측하였다. 범람해석에 필요한 지형자료를 기초로 하여 각 지형의 조건에 맞게 수치자료를 이용하여 작성하였고, 수자원 정보를 이용하여 유랑, 수위 등 시계열자료를 지류 및 상 하류의 경계조건으로 설정하고, 조도계수 등 하천 기본정보들을 입력하였다. HEC-RAS 모형은 회천교부터 도진교까지 전구간에 대한 종단면과 횡단면별 홍수침수범위 및 홍수위 크기 등 거시적인 1차원 수리해석에 적용하였고, TELEMAC 모형은 HEC-RAS 시뮬레이션 결과를 바탕으로 HEC-RAS에서 나타내기 힘든 2차원 흐름특성, 침수현상 등 일부 범람 구간에 대해 수리해석에 적용하였다. HEC-RAS 시스템은 수공구조물들의 영향과 하천의 영향을 종 횡단면으로 다양한 홍수침수 범위를 1차원으로 나타 낼 수 있으며, TELEMAC 시스템 수리 모의를 통해 얻어진 결과는 유속, 유량, 수심, 하상고 높이 등 2차원으로 나타낼 수 있다. TELEMAC 시스템을 활용한 2차원 분석은 실측자료와 비교적 유사하고 시각, 공간적으로 이해하기 쉽게 표현되므로, 모형 적용성이 우수한 것으로 판단된다. 향후 유역 해석을 위한 수치데이터, 수위, 유량자료를 확보하여 HEC-RAS, TELEMAC 1, 2차원 연계 모형을 적용 한다면, 하천 준설, 하천 구조물 설치, 홍수피해 등 전반적인 하천관리 계획에 활용할 수 있을 것이라 판단된다.

• 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 The Korean Society of Agricultural Engineers
• /
• v.61 no.6
• /
• pp.111-121
• /
• 2019

Evapotranspiration (ET) of vegetation is one of the major components of the hydrologic cycle, and its accurate estimation is important for hydrologic water balance, irrigation management, crop yield simulation, and water resources planning and management. For agricultural crops, ET is often calculated in terms of a short or tall crop reference, such as well-watered, clipped grass (reference crop evapotranspiration, $ET_o$). The Penman-Monteith equation recommended by FAO (FAO 56-PM) has been accepted by researchers and practitioners, as the sole $ET_o$ method. However, its accuracy is contingent on high quality measurements of four meteorological variables, and its use has been limited by incomplete and/or inaccurate input data. Therefore, this study evaluated the applicability of Backpropagation Neural Network (BPNN) model for estimating $ET_o$ from less meteorological data than required by the FAO 56-PM. A total of six meteorological inputs, minimum temperature, average temperature, maximum temperature, relative humidity, wind speed and solar radiation, were divided into a series of input groups (a combination of one, two, three, four, five and six variables) and each combination of different meteorological dataset was evaluated for its level of accuracy in estimating $ET_o$. The overall findings of this study indicated that $ET_o$ could be reasonably estimated using less than all six meteorological data using BPNN. In addition, it was shown that the proper choice of neural network architecture could not only minimize the computational error, but also maximize the relationship between dependent and independent variables. The findings of this study would be of use in instances where data availability and/or accuracy are limited.

• Journal of Korea Water Resources Association
• /
• v.41 no.9
• /
• pp.959-967
• /
• 2008

Disaggregation techniques are widely used to transform observed daily rainfall values into hourly ones, which serve as important inputs for flood forecasting purposes. However, an important limitation with most of the existing disaggregation techniques is that they treat the rainfall process as a realization of a stochastic process, thus raising questions on the lack of connection between the structure of the models on one hand and the underlying physics of the rainfall process on the other. The present study introduces a nonlinear deterministic (and specifically chaotic) framework to study the dynamic characteristics of rainfall distributions across different temporal scales (i.e. weights between scales), and thus the possibility of rainfall disaggregation. Rainfall data from the Seoul station (recorded by the Korea Meteorological Administration) are considered for the present investigation, and weights between only successively doubled resolutions (i.e., 24-hr to 12-hr, 12-hr to 6-hr, 6-hr to 3-hr) are analyzed. The correlation dimension method is employed to investigate the presence of chaotic behavior in the time series of weights, and a local approximation technique is employed for rainfall disaggregation. The results indicate the presence of chaotic behavior in the dynamics of weights between the successively doubled scales studied. The modeled (disaggregated) rainfall values are found to be in good agreement with the observed ones in their overall matching (e.g. correlation coefficient and low mean square error). While the general trend (rainfall amount and time of occurrence) is clearly captured, an underestimation of the maximum values are found.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.79-96
• /
• 2012

As the pace of competition dramatically accelerates and the complexity of change grows, a variety of research have been conducted to improve firms' short-term performance and to enhance firms' long-term survival. In particular, researchers and practitioners have paid their attention to identify promising technologies that lead competitive advantage to a firm. Discovery of promising technology depends on how a firm evaluates the value of technologies, thus many evaluating methods have been proposed. Experts' opinion based approaches have been widely accepted to predict the value of technologies. Whereas this approach provides in-depth analysis and ensures validity of analysis results, it is usually cost-and time-ineffective and is limited to qualitative evaluation. Considerable studies attempt to forecast the value of technology by using patent information to overcome the limitation of experts' opinion based approach. Patent based technology evaluation has served as a valuable assessment approach of the technological forecasting because it contains a full and practical description of technology with uniform structure. Furthermore, it provides information that is not divulged in any other sources. Although patent information based approach has contributed to our understanding of prediction of promising technologies, it has some limitations because prediction has been made based on the past patent information, and the interpretations of patent analyses are not consistent. In order to fill this gap, this study proposes a technology forecasting methodology by integrating patent information approach and artificial intelligence method. The methodology consists of three modules : evaluation of technologies promising, implementation of technologies value prediction model, and recommendation of promising technologies. In the first module, technologies promising is evaluated from three different and complementary dimensions; impact, fusion, and diffusion perspectives. The impact of technologies refers to their influence on future technologies development and improvement, and is also clearly associated with their monetary value. The fusion of technologies denotes the extent to which a technology fuses different technologies, and represents the breadth of search underlying the technology. The fusion of technologies can be calculated based on technology or patent, thus this study measures two types of fusion index; fusion index per technology and fusion index per patent. Finally, the diffusion of technologies denotes their degree of applicability across scientific and technological fields. In the same vein, diffusion index per technology and diffusion index per patent are considered respectively. In the second module, technologies value prediction model is implemented using artificial intelligence method. This studies use the values of five indexes (i.e., impact index, fusion index per technology, fusion index per patent, diffusion index per technology and diffusion index per patent) at different time (e.g., t-n, t-n-1, t-n-2, ${\cdots}$) as input variables. The out variables are values of five indexes at time t, which is used for learning. The learning method adopted in this study is backpropagation algorithm. In the third module, this study recommends final promising technologies based on analytic hierarchy process. AHP provides relative importance of each index, leading to final promising index for technology. Applicability of the proposed methodology is tested by using U.S. patents in international patent class G06F (i.e., electronic digital data processing) from 2000 to 2008. The results show that mean absolute error value for prediction produced by the proposed methodology is lower than the value produced by multiple regression analysis in cases of fusion indexes. However, mean absolute error value of the proposed methodology is slightly higher than the value of multiple regression analysis. These unexpected results may be explained, in part, by small number of patents. Since this study only uses patent data in class G06F, number of sample patent data is relatively small, leading to incomplete learning to satisfy complex artificial intelligence structure. In addition, fusion index per technology and impact index are found to be important criteria to predict promising technology. This study attempts to extend the existing knowledge by proposing a new methodology for prediction technology value by integrating patent information analysis and artificial intelligence network. It helps managers who want to technology develop planning and policy maker who want to implement technology policy by providing quantitative prediction methodology. In addition, this study could help other researchers by proving a deeper understanding of the complex technological forecasting field.