• Spatial Information Research
• /
• v.4 no.1
• /
• pp.21-42
• /
• 1996

The Anyang-cheon is one of the Han River tributaries in Seoul Metropolitan area. It is 35.1km long, has a basin area of 287km2 and touches seven cities of Kyounggi Province and part of Seoul. The purpose of this study were 1) to reconstruct the ancient stream network and to investigate the change of landuse in Anyang-cheon watershed between 1957 and 1991,2) to measure the change of the hydrologic ¬acteristics with urbanization, 3) to suggest the institutional solutions to reduce natural hazard as the area has urbanizedThe main results are as follows: 1.Anyang-cheon river basin has experienced the rapid urbanization and industrialization since 1957. Anyang-cheon stream network was oversimplified in the watershed. The total stream length decreased atributaries in the upper part of river basin have eliminated or buried undergrolmd in pipes. 2.Urbanization impacted to all of the area of Anyang-cht'On watershed. Urbanization in Anyang-cheon watershed corresponds to the large portion of flat area, especially flood - prone zone of river side, and the small portion of Greenbelt to constrain urban expantion in cities. 3.The urbanization of Anyang-cheon watershed produces fundamental changes in watershed hydrology. As infiltration is reduced by the creation of extensive pavement, concrete surface, and sewer pipe, runoff moves more quickly from upland to stream. As a result, runoff from the watershed is flashier, increasing flood hazardAs urban area continue to grow we will need to better utilize stream by protecting and enhancing stream systems.otecting and enhancing stream systems.tems.

• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.

• Korean Journal of Soil Science and Fertilizer
• /
• v.34 no.5
• /
• pp.316-325
• /
• 2001

To develope a technique for efficiently managing fertilizer for cucumber, a quick test method to quantify nitrate content in soil solution and leaf petiole juice using a simple instrument was investigated. Among the nitrate analyzing instruments such as compact ion meter, nitrate ion meter, and test strip with reflectometer, the paper test-strip used in conjunction with a hand-held reflectometer was most closely correlated with ion chromatography method in nitrate content, and then it would be suggested with a tool that a farmer can use rapidly, conveniently and accurately for nitrate analysis in a field. Nitrate content in soil solution collected by porous cup was very variable on the lapsed time after drip irrigation and the sampling positions such as soil depth and the distance from dripper. As a result, a significant correlation between nitrate contents of soil solutions and 2M KCl soil extract was not found. However, nitrate content in soil solution extracted with a volume basis (soil:water=1:2) showed the highly significant correlation with that in 2M KCl extract. Nitrate contents of cucumber leaf petiole juices was greatly different between upper and lower leaves. Eleven to sixteen positioned-leaf would be a proper sampling position to determine nitrate content in leaf petiole for evaluating nutrient state by plant tissue analysis. From the secondary regression equations between nitrate contents of soil and petiole juice and the yield of cucumber, nitrate levels for real time diagnosis were estimated as $400mg\;l^{-1}$ soil solution by porous cup. $300mg\;l^{-1}$ in a soil volume extraction, and $1400mg\;l^{-1}$ in petiole juice from spring to summer season. In addition, the maximum yield of cucumber fruit in pot test was obtained in nitrate $1500mg\;l^{-1}$ level of petiole juice, which was similar to nitrate $1400mg\;l^{-1}$ in greenhouse trial.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.27 no.3
• /
• pp.183-192
• /
• 1982

The variability of rice productivity during last 2 decades (1961-1980) of ten years before and after the introduction of"Tongil" was reviewed from the epochal, regional and varietal points of view. During that period the cultivated area of paddy rice have remained almost unchanged, while the total rice production have got elevated from 3, 463 million metric tons in 1961 to 6.006 million metric tons in 1977, recording 73.4% increase. This remarkable increase in rice production is considered to be attributable much to the development and release of new high yielding variety, "Tongil", coupled with the amelioration of cultural techniques. However, in 1978 Tongil type varieties experienced the epidemic outbreak of blast disease due to the shifted race population of blast fungus and in 1980 recorded poor rice production as low as in 1960's due to the unfavorable weather stress throughout the rice growing season, giving rise to many problems awaiting solutions for securing the stabilized high production of rice. The rice yield has continued the gradual increase during last two decades but its difference between farmer and research organization have got wider from 79kg/10a during 1960 to 1971 to 101kg/l0a during 1972 to 1980, and also the inter-regional differences have been increased from 50-60kg/10a to 80kg/10a during those periods. Therefore, this proves that we have raised the upper boundary of rice yield by increasing the yield potential of rice variety but have not changed those absolute deviations. Estimates indicate that the increased rice production during that period was indebted 40 percent to the varietal improvement and 13 percent to the ameliorated agro-technologies, and the rest, 47 percent, could be ascribed to the other factors besides varieties and cultural technologies such as the improved agricultural environments, etc. Of course, even though it cannot be expected to unify the cultural environments and the cultural technologies, provided that much efforts are to be endeavored to minimize the yield difference of 20 percent between farmer and research organizations and the inter-regional yield difference of 20 percent, much increased rice production can be expected to be achieved with the current level of cultural technology and the yielding potential of the present rice varieties. In order to expedite the above effects on rice production the followings are to be put into practices consitently and steadfastly. 1. Reinforcement of breeding for varieties with high yielding potential and less susceptible to climatic-stress and pests, and of basic physicoecological studies of rice plant for improving the cultural technologies. 2. Continuous endeavor to secure the stabilized cultural environments by improving the soil fertility and increasing the drainage and irrigation facilities. 3. Political back-up to encourage the farmers' incentives for production 4. Precise surveys for agricultural statistics to facilitate the long-term planninge long-term planning.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.431-438
• /
• 2020

In this paper, the method to extract lip contour by multiple threshold is proposed. Spyridonos et. el. proposed a method to extract lip contour. First step is get Q image from transform of RGB into YIQ. Second step is to find lip corner points by change point detection and split Q image into upper and lower part by corner points. The candidate lip contour can be obtained by apply threshold to Q image. From the candidate contour, feature variance is calculated and the contour with maximum variance is adopted as final contour. The feature variance 'D' is based on the absolute difference near the contour points. The conventional method has 3 problems. The first one is related to lip corner point. Calculation of variance depends on much skin pixels and therefore the accuracy decreases and have effect on the split for Q image. Second, there is no analysis for color systems except YIQ. YIQ is a good however, other color systems such as HVS, CIELUV, YCrCb would be considered. Final problem is related to selection of optimal contour. In selection process, they used maximum of average feature variance for the pixels near the contour points. The maximum of variance causes reduction of extracted contour compared to ground contours. To solve the first problem, the proposed method excludes some of skin pixels and got 30% performance increase. For the second problem, HSV, CIELUV, YCrCb coordinate systems are tested and found there is no relation between the conventional method and dependency to color systems. For the final problem, maximum of total sum for the feature variance is adopted rather than the maximum of average feature variance and got 46% performance increase. By combine all the solutions, the proposed method gives 2 times in accuracy and stability than conventional method.

• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.29-45
• /
• 2012

Bond rating is regarded as an important event for measuring financial risk of companies and for determining the investment returns of investors. As a result, it has been a popular research topic for researchers to predict companies' credit ratings by applying statistical and machine learning techniques. The statistical techniques, including multiple regression, multiple discriminant analysis (MDA), logistic models (LOGIT), and probit analysis, have been traditionally used in bond rating. However, one major drawback is that it should be based on strict assumptions. Such strict assumptions include linearity, normality, independence among predictor variables and pre-existing functional forms relating the criterion variablesand the predictor variables. Those strict assumptions of traditional statistics have limited their application to the real world. Machine learning techniques also used in bond rating prediction models include decision trees (DT), neural networks (NN), and Support Vector Machine (SVM). Especially, SVM is recognized as a new and promising classification and regression analysis method. SVM learns a separating hyperplane that can maximize the margin between two categories. SVM is simple enough to be analyzed mathematical, and leads to high performance in practical applications. SVM implements the structuralrisk minimization principle and searches to minimize an upper bound of the generalization error. In addition, the solution of SVM may be a global optimum and thus, overfitting is unlikely to occur with SVM. In addition, SVM does not require too many data sample for training since it builds prediction models by only using some representative sample near the boundaries called support vectors. A number of experimental researches have indicated that SVM has been successfully applied in a variety of pattern recognition fields. However, there are three major drawbacks that can be potential causes for degrading SVM's performance. First, SVM is originally proposed for solving binary-class classification problems. Methods for combining SVMs for multi-class classification such as One-Against-One, One-Against-All have been proposed, but they do not improve the performance in multi-class classification problem as much as SVM for binary-class classification. Second, approximation algorithms (e.g. decomposition methods, sequential minimal optimization algorithm) could be used for effective multi-class computation to reduce computation time, but it could deteriorate classification performance. Third, the difficulty in multi-class prediction problems is in data imbalance problem that can occur when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. SVM ensemble learning is one of machine learning methods to cope with the above drawbacks. Ensemble learning is a method for improving the performance of classification and prediction algorithms. AdaBoost is one of the widely used ensemble learning techniques. It constructs a composite classifier by sequentially training classifiers while increasing weight on the misclassified observations through iterations. The observations that are incorrectly predicted by previous classifiers are chosen more often than examples that are correctly predicted. Thus Boosting attempts to produce new classifiers that are better able to predict examples for which the current ensemble's performance is poor. In this way, it can reinforce the training of the misclassified observations of the minority class. This paper proposes a multiclass Geometric Mean-based Boosting (MGM-Boost) to resolve multiclass prediction problem. Since MGM-Boost introduces the notion of geometric mean into AdaBoost, it can perform learning process considering the geometric mean-based accuracy and errors of multiclass. This study applies MGM-Boost to the real-world bond rating case for Korean companies to examine the feasibility of MGM-Boost. 10-fold cross validations for threetimes with different random seeds are performed in order to ensure that the comparison among three different classifiers does not happen by chance. For each of 10-fold cross validation, the entire data set is first partitioned into tenequal-sized sets, and then each set is in turn used as the test set while the classifier trains on the other nine sets. That is, cross-validated folds have been tested independently of each algorithm. Through these steps, we have obtained the results for classifiers on each of the 30 experiments. In the comparison of arithmetic mean-based prediction accuracy between individual classifiers, MGM-Boost (52.95%) shows higher prediction accuracy than both AdaBoost (51.69%) and SVM (49.47%). MGM-Boost (28.12%) also shows the higher prediction accuracy than AdaBoost (24.65%) and SVM (15.42%)in terms of geometric mean-based prediction accuracy. T-test is used to examine whether the performance of each classifiers for 30 folds is significantly different. The results indicate that performance of MGM-Boost is significantly different from AdaBoost and SVM classifiers at 1% level. These results mean that MGM-Boost can provide robust and stable solutions to multi-classproblems such as bond rating.