• Journal of Korean Society for Geospatial Information Science
• /
• v.25 no.1
• /
• pp.19-27
• /
• 2017

This research was aimed to analyze landslide susceptibility and compare the prediction accuracy using ensemble frequency ratio (FR) and logistic regression at the Inje area, Korea. The landslide locations were identified with the before and after aerial photographs of landslide occurrence that were randomly selected for training (70%) and validation (30%). The total twelve landslide-related factors were elevation, slope, aspect, distance to drainage, topographic wetness index, stream power index, soil texture, soil sickness, timber age, timber diameter, timber density, and timber type. The spatial relationship between landslide occurrence and landslide-related factors was analyzed using FR and ensemble model. The produced LSI maps were validated and compared using relative operating characteristics (ROC) curve. The prediction accuracy of produced ensemble LSI map was about 2% higher than FR LSI map. The LSI map produced in this research could be used to establish land use planning and mitigate the damages caused by disaster.

• Journal of the Korean Society of Radiology
• /
• v.11 no.4
• /
• pp.205-212
• /
• 2017

Chronic diffuse hepatopathy is one of the important clinical tasks to reduce mortality and morbidity due to liver cirrhosis, liver failure, and liver cancer. The purpose of this study was to evaluate the criteria for predicting liver and chronic liver disease using Fibroscan based on ultrasound diagnosis. Serum and liver stiffness measurement(kPa) were analyzed in 280 patients and cut-off values of liver stiffness measurement for predicting fatty liver and chronic diffuse hepatopathy were determined using ROC curve analysis. Bilirubin and PT(prothrombin time) were not related to disease prediction(p=0.243, p=0.115). Serum glucose and triglyceride levels were significantly higher in the liver (p<0.05). The cut-off value for predicting chronic diffuse hepatopathy was determined as 10.3 kPa(AUC 0.98, sensitivity 94.94%, specificity 94.93%) in the order of control group, fatty liver and chronic diffuse hepatopathy. Therefore, it will be used as a primary tool for the diagnosis of chronic liver disease patients with quantitative evaluation.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.722-729
• /
• 2010

Prediction problems are widely used in medical domains. For example, computer aided diagnosis or prognosis is a key component in a CDSS (Clinical Decision Support System). SVMs with nonlinear kernels like RBF kernels, have shown superior accuracy in prediction problems. However, they are not preferred by physicians for medical prediction problems because nonlinear SVMs are difficult to visualize, thus it is hard to provide intuitive interpretation of prediction results to physicians. Nomogram was proposed to visualize SVM classification models. However, it cannot visualize nonlinear SVM models. Localized Radial Basis Function (LRBF) was proposed which shows comparable accuracy as the RBF kernel while the LRBF kernel is easier to interpret since it can be linearly decomposed. This paper presents a new tool named VRIFA, which integrates the nomogram and LRBF kernel to provide users with an interactive visualization of nonlinear SVM models, VRIFA visualizes the internal structure of nonlinear SVM models showing the effect of each feature, the magnitude of the effect, and the change at the prediction output. VRIFA also performs nomogram-based feature selection while training a model in order to remove noise or redundant features and improve the prediction accuracy. The area under the ROC curve (AUC) can be used to evaluate the prediction result when the data set is highly imbalanced. The tool can be used by biomedical researchers for computer-aided diagnosis and risk factor analysis for diseases.

• Journal of radiological science and technology
• /
• v.40 no.1
• /
• pp.35-40
• /
• 2017

The purpose of this study was to investigate the relationship between abdominal subcutaneous fat thickness(ASFT) and maternal gestational diabetes mellitus(GDM) measured by ultrasound at period of pregnancy. We compared maternal age, pre-pregnancy body mass index, and weight gain during pregnancy in 286 pregnant women who were diagnosed with early pregnancy ASFT and high GDM screening test(50 g OGTT) of more than 140 mg/dL. ROC curve analysis was used to determine the cut-off value of ASFT for GDM prediction. Maternal age and weight gain during pregnancy were not related to GDM in the mid-trimester and pre-pregnancy body mass index and earely pregnancy ASFT were significantly different between normal and GDM high risk groups. The cut-off value of ASFT for GDM prediction was 2.23 cm(AUC 0.913. Sensitivity 76.19%, Specificity 93.72%). ASFT measured by ultrasound in early pregnancy was useful as an important index for predicting mid-trimester GDM prediction. Therefore, ASFT can be used as an auxiliary diagnostic index for early recognition of GDM.

• Journal of radiological science and technology
• /
• v.39 no.3
• /
• pp.353-359
• /
• 2016

This study were to evaluate risk factors of GB polpy in Busan and Gyeongnam area. This study was performed with patients by abdominal ultrasonography among the patients who came to the P hospital from January to May 2016. Among them, risk factors were analyzed on 399 people at the same time when abdominal ultrasonography and hematological test. The statistical analysis of risk factors related to the GB ployp was performed by independent t-test and chi-square test. In consider of difference verification result for calculations odds ratio about independent variables, multiple logistic regression analysis to conduct verify adequacy by calculating forecasting model from variable. As a result, GB polyp risk factors have relevance to male, HBsAg positive, triglyceride. GB polyp risk factors confirmed to male, HBsAg positive, triglyceride were calculated forecasting model and forecasting probability value. Forecasting probability sensitivity 61.0%, specificity 76.8%, ROC area under curve 0.735 showed, it confirmed validity of forecasting model. When analyzing the GB polyps morphologically, among the GB polyp types observed from abdominal ultrasonography, the hyperechoic and homogeneous pattern with neck was the largest as shown from 27.5% and two GB polyps were shown most from 38%, sizes were shown most by maximum diameter, 5 to 10mm from 53%. As a disease accompany with GB polyp showed mild fatty liver(23%), diffuse hepatopathy(21%).

• Journal of the Korean Institute of Landscape Architecture
• /
• v.36 no.5
• /
• pp.64-72
• /
• 2008

The purpose of this study is to compare a habitat suitability grid unit included within a radius of 100m and $1km^2,\;2km^2,\;4km^2$ watershed units in order to predict suitable habitats for Chungcheong province's endangered leopard species(Prionailurus bengalensis). Other developed countries have carried out habitat assessment and established management policies for species conservation using such methods as HEP(Habitat Evaluation Procedures), HSI(Habitat Suitability Index) and GAP(Gap Analysis Program), etc. In accordance with these studies, many evaluation methods for habitat conservation have been proposed in Korea, but these studies are lacking in consideration of analytic units and general application of analysis results. This study predicted leopard habitat using a logistic regression analysis according to analytic units by data from 56 location and 8 sources of environmental data, including elevation, slope, forest area, land cover, roads, water, broadleaf trees, and human habitation. Moreover, the habitat suitability assessment unit was confirmed by a model comparison process encompassing model explanation. verification, and application on a regional scale. Results showed that assessment methods that took into consideration areas in and around the location points were beneficial in predicting habitat and that the assessment unit was appropriate for a 30m grid unit including areas within a radius of 100m and a $1km^2$ watershed unit in Chungcheong Province. This study suggests a method for regional habitat conservation to complement existing conservation area selection methods, and the results are expected to be used in conservation area selection and ecosystem management policies for endangered species.

• Journal of the Korean Society of Radiology
• /
• v.10 no.3
• /
• pp.187-193
• /
• 2016

In this study, we performed the carotid artery ultrasound targeting 140 subjects who have conducted to evaluate the changes in intima-media thickness(IMT) and plaque correlated with the presence or absence of a hematological test of the carotid artery. Considering that the IMT thickness more than 1mm is abnormal based on the carotid artery ultrasound to assess the presence or absence of plaque, and examined the correlation by classifying the blood lipid value and the fasting blood glucose level through the serum test. Consequently, the fasting blood glucose level is being analyzed as independent predictors of causing dental plaque(p=0.033), cut off value was determined as 126 mg/dL(sensitivity 56.25%, specificity 68.38%) in ROC curve analysis. Furthermore, the odds ratio appeared 1.01 times the value in the Logistic regression. Therefore, it seemed that the necessity to prospective studies in a number of subjects are considered, and also taking into account a number of blood test values along with the sonography of the carotid artery as a valuable part for effective primary prevention and follow-up observation of the cardiac and brain vascular disease is highly recommended.

• Journal of Korea Water Resources Association
• /
• v.54 no.12
• /
• pp.1305-1316
• /
• 2021

In this study, a new empirical formula for 2D transverse dispersion coefficient was developed using the results of previous tracer test studies, and the performance of the formula was evaluated. Since many tracer test studies have been conducted under the conditions where the width-to-depth ratio is less than 50, the existing empirical formulas developed using these imbalanced tracer test results have limitations in applying to rivers with a width-to-depth ratio greater than 50. Therefore, in order to develop an empirical formula for transverse dispersion coefficient using the imbalanced tracer test data, the Synthetic Minority Oversampling TEchnique (SMOTE) was used to oversample new data representing the properties of the existing tracer test data. The hydraulic data and the transverse dispersion coefficients in conditions of width-to-depth ratio greater than 50 were oversampled using the SMOTE. The reliability of the oversampled data was evaluated using the ROC (Receiver Operating Characteristic) curve. The empirical formula of transverse dispersion coefficient was developed including the oversampled data, and the performance of the results were compared with the empirical formulas suggested in previous studies using R². From the comparison results, the value of R² was 0.81 for the range of W/H < 50 and 0.92 for 50 < W/H, which were improved accuracy compared to the previous studies.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_1
• /
• pp.1367-1377
• /
• 2020

The purpose of this study is to assess the seismic vulnerability of buildings in Gyeongju city starting with the earthquake that occurred in the city on September 12, 2016, and produce a seismic vulnerability map. 11 influence factors related to geotechnical, physical, and structural indicators were selected to assess the seismic vulnerability, and these were applied as independent variables. For a dependent variable, location data of the buildings that were actually damaged in the 9.12 Gyeongju Earthquake was used. The assessment model was constructed based on random forest (RF) as a mechanic study method and support vector machine (SVM), and the training and test dataset were randomly selected with a ratio of 70:30. For accuracy verification, the receiver operating characteristic (ROC) curve was used to select an optimum model, and the accuracy of each model appeared to be 1.000 for RF and 0.998 for SVM, respectively. In addition, the prediction accuracy was shown as 0.947 and 0.926 for RF and SVM, respectively. The prediction values of the entire buildings in Gyeongju were derived on the basis of the RF model, and these were graded and used to produce the seismic vulnerability map. As a result of reviewing the distribution of building classes as an administrative unit, Hwangnam, Wolseong, Seondo, and Naenam turned out to be highly vulnerable regions, and Yangbuk, Gangdong, Yangnam, and Gampo turned out to be relatively safer regions.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.3
• /
• pp.397-411
• /
• 2023

The number of deteriorated bridges with a service period of more than 30 years has been rapidly increasing in Korea. Accordingly, the importance of advanced maintenance technologies through the predictions of age-induced deterioration degree, condition, and performance of bridges is more and more noticed. The prediction method of the safety grade of bridges was proposed in this study using the classification models of the Decision Tree and the Random Forest based on machine learning. As a result of analyzing these models for the 8,850 bridges located in national roads with various evaluation indexes such as confusion matrix, balanced accuracy, recall, ROC curve, and AUC, the Random Forest largely showed better predictive performance than that of the Decision Tree. In particular, random under-sampling in the Random Forest showed higher predictive performance than that of other sampling techniques for the C and D grade bridges, with the recall of 83.4%, which need more attention to maintenance because of the significant deterioration degree. The proposed model can be usefully applied to rapidly identify the safety grade and to establish an efficient and economical maintenance plan of bridges that have not recently been inspected.