• Journal of Korea Water Resources Association
• /
• v.51 no.11
• /
• pp.1031-1041
• /
• 2018

ANFIS-based methodology for improving GloSea5 ensemble weather forecast is developed and evaluated in this study. The proposed method consists of two steps: pre & post processing. For ensemble prediction of GloSea5, weights are assigned to the ensemble members based on Optimal Weighting Method (OWM) in the pre-processing. Then, the bias of the results of pre-processed is corrected based on Model Output Statistics (MOS) method in the post-processing. The watershed of the Chungju multi-purpose dam in South Korea is selected as a study area. The results of evaluation indicated that the pre-processing step (CASE1), the post-processing step (CASE2), pre & post processing step (CASE3) results were significantly improved than the original GloSea5 bias correction (BC_GS5). Correction performance is better the order of CASE3, CASE1, CASE2. Also, the accuracy of pre-processing was improved during the season with high variability of precipitation. The post-processing step reduced the error that could not be smoothed by pre-processing step. It could be concluded that this methodology improved the ability of GloSea5 ensemble weather forecast by using ANFIS, especially, for the summer season with high variability of precipitation when applied both pre- and post-processing steps.

• Journal of Digital Convergence
• /
• v.18 no.12
• /
• pp.87-95
• /
• 2020

The Incheon airport is a gateway to and from the Republic of Korea and has a great influence on the image of the country. Therefore, it is necessary to predict the number of airport passengers in the long term in order to maintain the quality of service at the airport. In this study, we compared the predictive performance of various time series models to predict the air passenger demand at Incheon Airport. From 2002 to 2019, passenger data include trend and seasonality. We considered the naive method, decomposition method, exponential smoothing method, SARIMA, PROPHET. In order to compare the capacity and number of passengers at Incheon Airport in the future, the short-term, mid-term, and long-term was forecasted by time series models. For the short-term forecast, the exponential smoothing model, which weighted the recent data, was excellent, and the number of annual users in 2020 will be about 73.5 million. For the medium-term forecast, the SARIMA model considering stationarity was excellent, and the annual number of air passengers in 2022 will be around 79.8 million. The PROPHET model was excellent for long-term prediction and the annual number of passengers is expected to be about 99.0 million in 2024.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.67 no.1
• /
• pp.61-66
• /
• 2022

Sesamin and sesamolin are major lignan components with a wide range of potential biological activities of sesame seeds. Near infrared reflectance spectroscopy (NIRS) is a rapid and non-destructive analysis method widely used for the quantitative determination of major components in many agricultural products. This study was conducted to develop a screening method to determine the lignan contents for sesame breeding. Sesamin and sesamolin contents of 482 sesame samples ranged from 0.03-14.40 mg/g and 0.10-3.79 mg/g with an average of 4.93 mg/g and 1.74 mg/g, respectively. Each sample was scanned using NIRS and calculated for the calibration and validation equations. The optimal performance calibration model was obtained from the original spectra using partial least squares (PLS). The coefficient of determination in calibration (R²) and standard error of calibration (SEC) were 0.963 and 0.861 for sesamin and 0.875 and 0.292 for sesamolin, respectively. Cross-validation results of the NIRS equation showed an R² of 0.889 in the prediction for sesamin and 0.781 for sesamolin and a standard error of cross-validation (SECV) of 1.163 for sesamin and 0.417 for sesamolin. The results showed that the NIRS equation for sesamin and sesamolin could be effective in selecting high lignan sesame lines in early generations of sesame breeding.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.4
• /
• pp.244-255
• /
• 2022

This study estimated and evaluated the high resolution (1km) gridded mountain meteorology data of daily mean, maximum and minimum temperature based on ASOS (Automated Surface Observing System), AWS (Automatic Weather Stations) and AMOS (Automatic Mountain Meteorology Observation System) in South Korea. The ASOS, AWS, and AMOS meteorology data which were located above 200m was classified as mountainous area. And the ASOS, AWS, and AMOS meteorology data which were located under 200m was classified as non-mountainous area. The bias-correction method was used for correct air temperature over complex mountainous area and the performance of enhanced daily coefficients based on the AMOS and mountainous area observing meteorology data was evaluated using the observed daily mean, maximum and minimum temperature. As a result, the evaluation results show that RMSE (Root Mean Square Error) of air temperature using the enhanced coefficients based on the mountainous area observed meteorology data is smaller as 30% (mean), 50% (minimum), and 37% (maximum) than that of using non-mountainous area observed meteorology data. It indicates that the enhanced weather coefficients based on the AMOS and mountain ASOS can estimate mean, maximum, and minimum temperature data reasonably and the temperature results can provide useful input data on several climatological and forest disaster prediction studies.

• The Korean Journal of Applied Statistics
• /
• v.36 no.5
• /
• pp.381-397
• /
• 2023

The most representative design used in clinical trials is randomization, which is used to accurately estimate the treatment effect. However, comparison between the treatment group and the control group in an observational study without randomization is biased due to various unadjusted differences, such as characteristics between patients. Propensity score weighting is a widely used method to address these problems and to minimize bias by adjusting those confounding and assess treatment effects. Inverse probability weighting, the most popular method, assigns weights that are proportional to the inverse of the conditional probability of receiving a specific treatment assignment, given observed covariates. However, this method is often suffered by extreme propensity scores, resulting in biased estimates and excessive variance. Several alternative methods including trimming, overlap weights, and matching weights have been proposed to mitigate these issues. In this paper, we conduct a simulation study to compare performance of various propensity score weighting methods under diverse situation, such as limited overlap, misspecified propensity score, and treatment contrary to prediction. From the simulation results overlap weights and matching weights consistently outperform inverse probability weighting and trimming in terms of bias, root mean squared error and coverage probability.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.63-83
• /
• 2019

Investors prefer to look for trading points based on the graph shown in the chart rather than complex analysis, such as corporate intrinsic value analysis and technical auxiliary index analysis. However, the pattern analysis technique is difficult and computerized less than the needs of users. In recent years, there have been many cases of studying stock price patterns using various machine learning techniques including neural networks in the field of artificial intelligence(AI). In particular, the development of IT technology has made it easier to analyze a huge number of chart data to find patterns that can predict stock prices. Although short-term forecasting power of prices has increased in terms of performance so far, long-term forecasting power is limited and is used in short-term trading rather than long-term investment. Other studies have focused on mechanically and accurately identifying patterns that were not recognized by past technology, but it can be vulnerable in practical areas because it is a separate matter whether the patterns found are suitable for trading. When they find a meaningful pattern, they find a point that matches the pattern. They then measure their performance after n days, assuming that they have bought at that point in time. Since this approach is to calculate virtual revenues, there can be many disparities with reality. The existing research method tries to find a pattern with stock price prediction power, but this study proposes to define the patterns first and to trade when the pattern with high success probability appears. The M & W wave pattern published by Merrill(1980) is simple because we can distinguish it by five turning points. Despite the report that some patterns have price predictability, there were no performance reports used in the actual market. The simplicity of a pattern consisting of five turning points has the advantage of reducing the cost of increasing pattern recognition accuracy. In this study, 16 patterns of up conversion and 16 patterns of down conversion are reclassified into ten groups so that they can be easily implemented by the system. Only one pattern with high success rate per group is selected for trading. Patterns that had a high probability of success in the past are likely to succeed in the future. So we trade when such a pattern occurs. It is a real situation because it is measured assuming that both the buy and sell have been executed. We tested three ways to calculate the turning point. The first method, the minimum change rate zig-zag method, removes price movements below a certain percentage and calculates the vertex. In the second method, high-low line zig-zag, the high price that meets the n-day high price line is calculated at the peak price, and the low price that meets the n-day low price line is calculated at the valley price. In the third method, the swing wave method, the high price in the center higher than n high prices on the left and right is calculated as the peak price. If the central low price is lower than the n low price on the left and right, it is calculated as valley price. The swing wave method was superior to the other methods in the test results. It is interpreted that the transaction after checking the completion of the pattern is more effective than the transaction in the unfinished state of the pattern. Genetic algorithms(GA) were the most suitable solution, although it was virtually impossible to find patterns with high success rates because the number of cases was too large in this simulation. We also performed the simulation using the Walk-forward Analysis(WFA) method, which tests the test section and the application section separately. So we were able to respond appropriately to market changes. In this study, we optimize the stock portfolio because there is a risk of over-optimized if we implement the variable optimality for each individual stock. Therefore, we selected the number of constituent stocks as 20 to increase the effect of diversified investment while avoiding optimization. We tested the KOSPI market by dividing it into six categories. In the results, the portfolio of small cap stock was the most successful and the high vol stock portfolio was the second best. This shows that patterns need to have some price volatility in order for patterns to be shaped, but volatility is not the best.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.5
• /
• pp.557-564
• /
• 2017

The purpose of the thermal imaging observation device mounted on the K's tank in the Republic of Korea military is to convert infrared rays into visual information to provide information about the environment under conditions of restricted visibility. Among the various performance indicators of thermal observation devices, such as the view, magnification, resolution, MTF, NETD, and Minimum Resolvable Temperature Difference (MRTD), the MRTD is the most important, because it can indicate both the spatial frequency and temperature resolvable. However, the standard method of measuring the MRTD in NATO contains many subjective factors. As the measurement result can vary depending on subjective factors such as the human eye, metal condition and measurement conditions, the MRTD obtained is not stable. In this study, these qualitative MRTD measurement systems are converted into quantitative indicators based on a gray scale using imaging processing. By converting the average of the gray scale differences of the black and white images into the MRTD, the mean values can be used to determine whether the performance requirements required by the defense specification are met. The (mean) value can also be used to discriminate between detection, recognition and identification and the detectable distance of the thermal equipment can be analyzed under various environmental conditions, such as altostratus, heavy rain and fog.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.2
• /
• pp.67-78
• /
• 2006

Local governments began to construct geographic information system to improve government productivity and performance. In support, central government organized a national commission for GIS. The master plan by NGIS has been the base for local government to participate in the construction of GIS at the local level in the under ground facilities management including water and sewers. The challenge faced by sewer facility managers includes controlling 'data accuracy'. The input for sewer data handling for efficient performance in local government requires accurate data. However data manipulation to get the 'good quality' data can be burdensome. Thus, the aim of this research is to provide the appropriate tool to guarantee the high quality of digital data in sewer facility management. It is helpful to pass the data examination by government as well as to insure confidence of decision and data analysis works in local government. In this research, error types of sewer data were classified and pointed the limitation of traditional examination methods. Thus this research suggested more improved method for finding and correcting errors in data input using sewer volume analysis and prediction model as immigrating sewer facility management work to Geographic Information System.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.4
• /
• pp.86-94
• /
• 2009

Currently, positioning methods for LBS(Location Based Service) are GPS and network-based positioning techniques that use mobile communication networks. In these methods, however, the accuracy of positioning decreases due to the propagation delay caused by the non-line-of-sight(NLOS) effect and the repeater. To address this disadvantage, the CDMA system uses Pattern Matching algorithm. The Pattern Matching algorithm constructs a database of the propagation characteristics of the RF signals measured during the GPS positioning along with the positioned locations, so that the location can be provided by comparing the propagation characteristics of the received signals and the database, upon a user's request. In the area where GPS signals are not received, however, a database cannot be constructed. There are problem that the accuracy of positioning decreases due to the area without a database Because Pattern Matching algorithm depend on database existence. Therefore, this paper proposed a pilot signal strength prediction algorithm to enable construction of databases for areas without databases, so as to improve the performance of the Pattern Matching algorithm. The database was constructed by predicting the pilot signals in the area without a database using the proposed algorithm, and the Pattern Matching algorithm analysed positioning performance.