• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.221-232
• /
• 2021

This study analyzed co-registration results according to the geometric processing level of reference image, which are Level 1R and Level 1G provided from KOMPSAT-3 and KOMPSAT-3A images. We performed co-registration using each Level 1R and Level 1G image as a reference image, and Level 1R image as a sensed image. For constructing the experimental dataset, seven Level 1R and 1G images of KOMPSAT-3 and KOMPSAT-3A acquired from Daejeon, South Korea, were used. To coarsely align the geometric position of the two images, SURF (Speeded-Up Robust Feature) and PC (Phase Correlation) methods were combined and then repeatedly applied to the overlapping region of the images. Then, we extracted tie-points using the SURF method from coarsely aligned images and performed fine co-registration through affine transformation and piecewise Linear transformation, respectively, constructed with the tie-points. As a result of the experiment, when Level 1G image was used as a reference image, a relatively large number of tie-points were extracted than Level 1R image. Also, in the case where the reference image is Level 1G image, the root mean square error of co-registration was 5 pixels less than the case of Level 1R image on average. We have shown from the experimental results that the co-registration performance can be affected by the geometric processing level related to the initial geometric relationship between the two images. Moreover, we confirmed that the better geometric quality of the reference image achieved the more stable co-registration performance.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1691-1707
• /
• 2022

Cheonji Lake, the caldera of Baekdu Mountain, located on the border of the Korean Peninsula and China, alternates between melting and freezing seasonally. There is a magma chamber beneath Cheonji, and variations in the magma chamber cause volcanic antecedents such as changes in the temperature and water pressure of hot spring water. Consequently, there is an abnormal region in Cheonji where ice melts quicker than in other areas, freezes late even during the freezing period, and has a high-temperature water surface. The abnormal area is a discharge region for hot spring water, and its ice gradient may be used to monitor volcanic activity. However, due to geographical, political and spatial issues, periodic observation of abnormal regions of Cheonji is limited. In this study, the degree of ice change in the optimal region was quantified using a Landsat -5/-7/-8 optical satellite image and a Modified U-Net regression model. From January 22, 1985 to December 8, 2020, the Visible and Near Infrared (VNIR) band of 83 Landsat images including anomalous regions was utilized. Using the relative spectral reflectance of water and ice in the VNIR band, unique data were generated for quantitative ice variability monitoring. To preserve as much information as possible from the visible and near-infrared bands, ice gradient was noticed by applying it to U-Net with two encoders, achieving good prediction accuracy with a Root Mean Square Error (RMSE) of 140 and a correlation value of 0.9968. Since the ice change value can be seen with high precision from Landsat images using Modified U-Net in the future may be utilized as one of the methods to monitor Baekdu Mountain's volcanic activity, and a more specific volcano monitoring system can be built.

• Journal of Korea Water Resources Association
• /
• v.57 no.5
• /
• pp.333-346
• /
• 2024

High-resolution medium-range streamflow prediction is crucial for sustainable water quality and aquatic ecosystem management. For reliable medium-range streamflow predictions, it is necessary to understand the characteristics of forcings and to effectively utilize weather forecast data with low spatio-temporal resolutions. In this study, we presented a comparative analysis of medium-range streamflow predictions using the distributed hydrological model, WRF-Hydro, and the numerical weather forecast Global Data Assimilation and Prediction System (GDAPS) in the Geumho River basin, Korea. Multiple forcings, ground observations (AWS&ASOS), numerical weather forecast (GDAPS), and Global Land Data Assimilation System (GLDAS), were ingested to investigate the performance of streamflow predictions with highresolution WRF-Hydro configuration. In terms of the mean areal accumulated rainfall, GDAPS was overestimated by 36% to 234%, and GLDAS reanalysis data were overestimated by 80% to 153% compared to AWS&ASOS. The performance of streamflow predictions using AWS&ASOS resulted in KGE and NSE values of 0.6 or higher at the Kangchang station. Meanwhile, GDAPS-based streamflow predictions showed high variability, with KGE values ranging from 0.871 to -0.131 depending on the rainfall events. Although the peak flow error of GDAPS was larger or similar to that of GLDAS, the peak flow timing error of GDAPS was smaller than that of GLDAS. The average timing errors of AWS&ASOS, GDAPS, and GLDAS were 3.7 hours, 8.4 hours, and 70.1 hours, respectively. Medium-range streamflow predictions using GDAPS and high-resolution WRF-Hydro may provide useful information for water resources management especially in terms of occurrence and timing of peak flow albeit high uncertainty in flood magnitude.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.185-202
• /
• 2012

.Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.83-102
• /
• 2021

The government recently announced various policies for developing big-data and artificial intelligence fields to provide a great opportunity to the public with respect to disclosure of high-quality data within public institutions. KSURE(Korea Trade Insurance Corporation) is a major public institution for financial policy in Korea, and thus the company is strongly committed to backing export companies with various systems. Nevertheless, there are still fewer cases of realized business model based on big-data analyses. In this situation, this paper aims to develop a new business model which can be applied to an ex-ante prediction for the likelihood of the insurance accident of credit guarantee. We utilize internal data from KSURE which supports export companies in Korea and apply machine learning models. Then, we conduct performance comparison among the predictive models including Logistic Regression, Random Forest, XGBoost, LightGBM, and DNN(Deep Neural Network). For decades, many researchers have tried to find better models which can help to predict bankruptcy since the ex-ante prediction is crucial for corporate managers, investors, creditors, and other stakeholders. The development of the prediction for financial distress or bankruptcy was originated from Smith(1930), Fitzpatrick(1932), or Merwin(1942). One of the most famous models is the Altman's Z-score model(Altman, 1968) which was based on the multiple discriminant analysis. This model is widely used in both research and practice by this time. The author suggests the score model that utilizes five key financial ratios to predict the probability of bankruptcy in the next two years. Ohlson(1980) introduces logit model to complement some limitations of previous models. Furthermore, Elmer and Borowski(1988) develop and examine a rule-based, automated system which conducts the financial analysis of savings and loans. Since the 1980s, researchers in Korea have started to examine analyses on the prediction of financial distress or bankruptcy. Kim(1987) analyzes financial ratios and develops the prediction model. Also, Han et al.(1995, 1996, 1997, 2003, 2005, 2006) construct the prediction model using various techniques including artificial neural network. Yang(1996) introduces multiple discriminant analysis and logit model. Besides, Kim and Kim(2001) utilize artificial neural network techniques for ex-ante prediction of insolvent enterprises. After that, many scholars have been trying to predict financial distress or bankruptcy more precisely based on diverse models such as Random Forest or SVM. One major distinction of our research from the previous research is that we focus on examining the predicted probability of default for each sample case, not only on investigating the classification accuracy of each model for the entire sample. Most predictive models in this paper show that the level of the accuracy of classification is about 70% based on the entire sample. To be specific, LightGBM model shows the highest accuracy of 71.1% and Logit model indicates the lowest accuracy of 69%. However, we confirm that there are open to multiple interpretations. In the context of the business, we have to put more emphasis on efforts to minimize type 2 error which causes more harmful operating losses for the guaranty company. Thus, we also compare the classification accuracy by splitting predicted probability of the default into ten equal intervals. When we examine the classification accuracy for each interval, Logit model has the highest accuracy of 100% for 0~10% of the predicted probability of the default, however, Logit model has a relatively lower accuracy of 61.5% for 90~100% of the predicted probability of the default. On the other hand, Random Forest, XGBoost, LightGBM, and DNN indicate more desirable results since they indicate a higher level of accuracy for both 0~10% and 90~100% of the predicted probability of the default but have a lower level of accuracy around 50% of the predicted probability of the default. When it comes to the distribution of samples for each predicted probability of the default, both LightGBM and XGBoost models have a relatively large number of samples for both 0~10% and 90~100% of the predicted probability of the default. Although Random Forest model has an advantage with regard to the perspective of classification accuracy with small number of cases, LightGBM or XGBoost could become a more desirable model since they classify large number of cases into the two extreme intervals of the predicted probability of the default, even allowing for their relatively low classification accuracy. Considering the importance of type 2 error and total prediction accuracy, XGBoost and DNN show superior performance. Next, Random Forest and LightGBM show good results, but logistic regression shows the worst performance. However, each predictive model has a comparative advantage in terms of various evaluation standards. For instance, Random Forest model shows almost 100% accuracy for samples which are expected to have a high level of the probability of default. Collectively, we can construct more comprehensive ensemble models which contain multiple classification machine learning models and conduct majority voting for maximizing its overall performance.

• Journal of Korean Society of Environmental Engineers
• /
• v.36 no.8
• /
• pp.534-541
• /
• 2014

This study investigated a method to determine an efficient operating condition for the $UV/H_2O_2$ process. The OH radical scavenging factor is the most important factor to predict the removal efficiency of the target compound and determine the operating condition of the $UV/H_2O_2$ process. To rapidly and simply measure the scavenging factor, Rhodamine B (RhB) was selected as a probe compound. Its reliability was verified by comparing it with a typical probe compound (para-chlorobenzoic acid, pCBA); the difference between RhB and pCBA was only 1.1%. In a prediction test for the removal of Ibuprofen, the RhB method also shows a high reliability with an error rate of about 5% between the experimental result and the model prediction using the measured scavenging factor. In the monitoring result, the scavenging factor in the influent water of the $UV/H_2O_2$ pilot plant was changed up to 200% for about 8 months, suggesting that the required UV dose could be increased about 1.7 times to achieve 90% caffeine removal. These results show the importance of the scavenging factor measurement in the $UV/H_2O_2$ process, and the operating condition could simply be determined from the scavenging factor, absorbance, and information pertaining to the target compound.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.26 no.5
• /
• pp.278-284
• /
• 2014

Water temperature due to climate change can be estimated using the air temperature because the air and water temperatures are closely related and the water temperatures have been widely used as the indicators of the environmental and ecological changes. It is highly necessary to estimate the frequency distribution of the air and water temperatures, for the climate change derives the change of the coastal water temperatures. In this study, the distribution function of the air temperatures is estimated by using the long-term coastal air temperature data sets in Korea. The candidate distribution function is the bi-modal distribution function used in the previous studies, such as Cho et al.(2003) on tidal elevation data and Jeong et al.(2013) on the coastal water temperature data. The parameters of the function are optimally estimated based on the least square method. It shows that the optimal parameters are highly correlated to the basic statistical informations, such as mean, standard deviation, and skewness coefficient. The RMS error of the parameter estimation using statistical information ranges is about 5 %. In addition, the bimodal distribution fits good to the overall frequency pattern of the air temperature. However, it can be regarded as the limitations that the distribution shows some mismatch with the rapid decreasing pattern in the high-temperature region and the some small peaks.

• Geophysics and Geophysical Exploration
• /
• v.11 no.3
• /
• pp.221-229
• /
• 2008

The three dimensional model method is widely applied in resource development for feasibility study, mine design, excavation planning and process management by constructing the database of various data in 3 dimensional space. Most of geophysical surveys for the purpose of engineering and resource development are performed in 2 dimensional line survey due to the restriction of the field situation, technical or economical situation and so on. The acquired geophysical data are used as the input for the 2 dimensional inversion under the 2 dimensional assumption. But the geophysical data are affected by 3 dimensional space. Therefore in order to reduce the error caused by 2 dimensional assumption, the 2 dimensional inversion result must be interpreted considering the additional information such as 3 dimensional topography, geological structure, borehole survey etc. The applicability and usability of 3 dimensional modeling method are studied by reviewing the case study to the geophysical data acquired in field of engineering and resource development.

• Journal of Astronomy and Space Sciences
• /
• v.25 no.2
• /
• pp.227-238
• /
• 2008

GNSS (Global Navigation Satellite System) Ground Station monitors navigation satellite signal, analyzes navigation result, and uploads correction information to satellite. GNSS Ground Station is considered as a main object for constructing GNSS infra-structure and applied in various fields. ETRI (Electronics and Telecommunications Research Institute) is developing Monitoring and Control subsystem, which is subsystem of GNSS Ground Station. Monitoring and Control subsystem acquires GPS and Galileo satellite signal and provides signal monitoring data to GNSS control center. In this paper, the configurations of GNSS Ground Station and Monitoring and Control subsystem are introduced and the preliminary design of Monitoring and Control subsystem is performed. Monitoring and Control subsystem consists of data acquisition module, data formatting and archiving module, data error correction module, navigation solution determination module, independent quality monitoring module, and system operation and maintenance module. The design process uses UML (Unified Modeling Language) method which is a standard for developing software and consists of use-case modeling, domain design, software structure design, and user interface structure design. The preliminary design of Monitoring and Control subsystem enhances operation capability of GNSS Ground Station and is used as basic material for detail design of Monitoring and Control subsystem.

• Journal of KIISE:Software and Applications
• /
• v.33 no.1
• /
• pp.69-83
• /
• 2006

This paper describes an image disparity estimation method using a segmented-region based stereo matching. Segmented-region based disparity estimation yields a disparity map as the unit of segmented region. However, there is a problem that it estimates disparity imprecisely. The reason is that because it not only have matching errors but also apply an identical way to disparity estimation, which is not considered each type of matched regions. To solve this problem, we proposes a disparity estimation method which is considered the type of matched regions. That is, the proposed method classifies whole matched regions into similar-matched region, dissimilar-matched region, false-matched region and miss-matched region by analyzing the type of matched regions. We then performs proper disparity estimation for each type of matched regions. This method minimizes the error in estimating disparity which is caused by inaccurate matching and also improves the accuracy of disparity of the well-matched regions. For the purpose of performance evaluations, we perform tests on a variety of scenes for synthetic, indoor and outdoor images. As a result of tests, we can obtain a dense disparity map which has the improved accuracy. The remarkable result is that the accuracy of disparity is also improved considerably for complex outdoor images which are barely treatable in the previous methods.