• Journal of the Korean Society of Radiology
• /
• v.16 no.5
• /
• pp.661-672
• /
• 2022

After the outbreak of the SARS-CoV2 virus that causes COVID-19, it spreads around the world with the number of infections and deaths rising rapidly caused a shortage of medical resources. As a way to solve this problem, chest X-ray diagnosis using Artificial Intelligence(AI) received attention as a primary diagnostic method. The purpose of this study is to comprehensively analyze the detection of COVID-19 via AI. To achieve this purpose, 292 studies were collected through a series of Classification methods. Based on these data, performance measurement information including Accuracy, Precision, Area Under Cover(AUC), Sensitivity, Specificity, F1-score, Recall, K-fold, Architecture and Class were analyzed. As a result, the average Accuracy, Precision, AUC, Sensitivity and Specificity were achieved as 95.2%, 94.81%, 94.01%, 93.5%, and 93.92%, respectively. Although the performance measurement information on a year-on-year basis gradually increased, furthermore, we conducted a study on the rate of change according to the number of Class and image data, the ratio of use of Architecture and about the K-fold. Currently, diagnosis of COVID-19 using AI has several problems to be used independently, however, it is expected that it will be sufficient to be used as a doctor's assistant.

• The Korean Journal of Applied Statistics
• /
• v.37 no.4
• /
• pp.395-410
• /
• 2024

Text data is usually made up of a wide variety of unique words. Even in standard text data, it is common to find tens of thousands of different words. In text data analysis, usually, each unique word is treated as a variable. Thus, text data can be regarded as a dataset with a large number of variables. On the other hand, in text data classification, we often encounter class label imbalance problems. In the cases of substantial imbalances, the performance of conventional classification models can be severely degraded. To improve the classification performance of support vector machines (SVM) for imbalanced data, algorithms such as the Synthetic Minority Over-sampling Technique (SMOTE) can be used. The SMOTE algorithm synthetically generates new observations for the minority class based on the k-Nearest Neighbors (kNN) algorithm. However, in datasets with a large number of variables, such as text data, errors may accumulate. This can potentially impact the performance of the kNN algorithm. In this study, we propose a method for enhancing prediction performance for the minority class of imbalanced text data. Our approach involves employing variable selection to generate new synthetic observations in a reduced space, thereby improving the overall classification performance of SVM.

• Journal of Environmental Impact Assessment
• /
• v.15 no.6
• /
• pp.395-406
• /
• 2006

This study was carried out to offer the systematical and scientific method of regional environment conservation by deciding the rank using fuzzy theory, and try to find the methodology to accurately accomplished the regional environment assessment for sound land conservation. The results were as follows. To transform the Likert's scale granted to assessment indicators into the type of triangular fuzzy number (a, b, c), there was conversion to each minimum (a), median (b), and maximum (c) in applying membership function. We used the center of gravity and eigenvalue leading to the rank. In the sequential analysis of rank-based test of assessment indicators by triangular fuzzy number, the result proclaimed that ranking of the indicators was, in the biotic field, in the order of 'dominance', 'sociality', 'coverage' and in the abiotic one, 'soil pH', 'T-N', 'soil property', and in the qualitative one, 'impact rating class', 'hemeroby degree', 'land use pattern', and in the functional one, 'protection of water resource', 'offer of recreation', 'protection of soil erosion'. Therefore, there was a difference between subjective rank from human and the rank from triangular fuzzy number. In other words, the scientific rank decision would be not so much being subjective and biased as dealing with human thoughts mathematically by triangular fuzzy number.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2005.11a
• /
• pp.353-357
• /
• 2005

LOx post damage occurs from the development process of the full-scale gas generator which is necessary to 30 tonf class engine development was described. The cause and analysis for damage was described. The combustion test result of 4 injector, the full-scale gas generator and redesigned injector was described. Combustion instability, purge, the low momentum of LOx spray, small recess number, the low flow of LOx, and the high spray angle is main reason the possibility of knowing. The redesign for the injector in the direction of increase of recess number, increase of LOx and fuel spray angle, decrease of gap interval between the LOx post outer wall and fuel screen and increase of LOx post wall thick became accomplished.

• Journal of Auto-vehicle Safety Association
• /
• v.11 no.2
• /
• pp.6-10
• /
• 2019

This paper describes effectiveness of accident reduction on vehicles equipped with AEB using accident data occurring in Korea. During the statistical period, we used the number of vehicles which are covered by auto insurance and the number of accidents. To maximize the reduction effect of accidents caused by the driver's carelessness, the analysis was limited to Physical Damage Coverage that covers the cost of repairing or replacing the damaged vehicle caused by the driver's fault. Due to Personal Information Protection Law, it was not capable of comparing the same vehicle using Vehicle Identification Number in this study. Instead of that, we used it as a similar vehicle, so there are limits to the comparison and analysis results. As a result of this study, we have found that the effect of reducing accidents was different depending on the vehicle class, but it was generally concluded that the number of accidents decreased when the vehicle was equipped with an AEB system. Domestic research on the AEB effect of reducing accidents is not active yet. Therefore, it is absolutely essential to analyze the effects according to various conditions such as driver's age, occupation and gender as well as expanding the study models in the future.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.45-68
• /
• 2023

The purpose of this study is to longitudinally analyze impact factors on library use. One of library use indicators, the number of circulated books was statistically analyzed with latent growth model and growth mixture model. Library data from 2014 to 2019 were collected from the National Library Statistics System, and 846 public libraries were analyzed. As results, the number of circulated books were decreased, but it was tempered. Next, with controlling the factor affecting the dependent variable, the size of collection and the number of participants in reading programs provided by public libraries were statistically significant. Lastly, 5 classes were identified by applying the growth mixture model, and the number of librarians was significantly associated with trajectory class membership.

• Journal of Chest Surgery
• /
• v.30 no.4
• /
• pp.383-389
• /
• 1997

From March, 1992 to March, 1996, a total of 279 patients underwent coronary bypass surgery at the Sejong General Hospital, Puchon. We selected 22 patients with severe left ventricular(LV) dysfunction from them. The criteria were the presence of global or segmental abnormalities of left ventricular contraction and LV ejection fraction(EF) less than 35% based on biplane LV angiography by planimetry method. The mean age of 17 male and 5 female patients was 60$\pm$5.6years(range:47~73 years). All had the anginas, which were Canadian class II in 6, class 111 in 12 and class IV in 4. All patients except one had the history of previous myocardial infarction more than once. Seven of them had the symptoms and signs of congestive heart failure, such as dyspnea on excertion and increased pulmonary vascular markings. Their mean LVEF was 29.4$\pm$4 5%(range : 18~35%) and mean LV end-diastolic pressure was 18.7 $\pm$8. 2mmHg(range:10~42mmHg). 21 patients had 3 vessel-disease and 1 had 2 vessel-disease. Complete revascularization was tried with the use of 16 internal mammary arteries and 60 sapheuous veins and 3 radial arteries grafts. The mean number of distal anastomosis was 3.5$\pm$ 1.1. Concomitantly, one mitral valvuloplasty and annuloplasty was performed in the patient with moderate mitral regurtigation. The hospital mortality was 4.5%. During the follow-up, there were 3 late deaths. Of 18 survivors, 2 patients were lost in follow-up 24 and 27 month respectively after operation and the remaining 16 patients have bcen followed up with an average of 30.4 $\pm$ 13.4 months.15 patients had improvement with respect to angina but 8 patients still have the continuing or progressing heart failure. The 1-year, 2-year and 3-year actuarial survival rate was 85.2, 69.1, 46.1%, respectively. This study indicates that coronary artery bypass sur ery can be performed in the patients with severe LV dysfunction at acceptable risk but does not greatly contribute to the improvement of congestive heart failure.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.8 no.2
• /
• pp.86-96
• /
• 2006

Ecoclimap-1, a new complete surface parameter global database at a 1-km resolution, was previously presented. It is intended to be used to initialize the soil-vegetation- atmosphere transfer schemes in meteorological and climate models. Surface parameters in the Ecoclimap-1 database are provided in the form of a per-class value by an ecoclimatic base map from a simple merging of land cover and climate maps. The principal objective of this ecoclimatic map is to consider intra-class variability of life cycle that the usual land cover map cannot describe. Although the ecoclimatic map considering land cover and climate is used, the intra-class variability was still too high inside some classes. In this study, a new strategy is defined; the idea is to use the information contained in S10 NDVI SPOT/VEGETATION profiles to split a land cover into more homogeneous sub-classes. This utilizes an intra-class unsupervised sub-clustering methodology instead of simple merging. This study was performed to provide a new ecolimatic map over Northeast Asia in the framework of Ecoclimap-2 global database construction for surface parameters. We used the University of Maryland's 1km Global Land Cover Database (UMD) and a climate map to determine the initial number of clusters for intra-class sub-clustering. An unsupervised classification process using six years of NDVI profiles allows the discrimination of different behavior for each land cover class. We checked the spatial coherence of the classes and, if necessary, carried out an aggregation step of the clusters having a similar NDVI time series profile. From the mapping system, 29 ecosystems resulted for the study area. In terms of climate-related studies, this new ecosystem map may be useful as a base map to construct an Ecoclimap-2 database and to improve the surface climatology quality in the climate model.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.20 no.3
• /
• pp.1-10
• /
• 2021

Before long the number of Elementary School students per class will be 20 in Korea, but the current Area and Module of Elementary School are planned for 30 students. Therefore, necessary Area and Module for less than 20 students should be prepared. The purpose of this research is to find out necessary Area and Module for less than 20 students in Elementary School Classroom. I researched 60 Classrooms of 10 Elementary Schools before 2 researches of mine, and researched the sizes of every path in the classrooms. With the Plans for 20 students, I found the conclusion as follows: First, the one-way class requires a minimum of 5.4m×8.1m (43.74m²), a maximum of 5.4m×8.7m (48.6m²). Second, the 3-row alignment class requires a minimum of 7.2m×7.2m (51.84m²), a maximum of 7.5m×7.5m (56.25m²). Third, the group study class requires a minimum of 6.0m×8.7m (52.2m²), a maximum of 6.3m×9.3m (58.59m²). Fourth, the group study class requires a minimum of 2.34m², a maximum of 14.85m² more than the one-way class. Fifth, the suitable module which fits both 2-row alignment class and group study class except the 3-row alignment class is 6.0m×8.7m (52.2m²).

• Trans-
• /
• v.12
• /
• pp.51-79
• /
• 2022

This study investigates the methods for deriving colors which can serve as a reference to users such as designers and or contents creators who search for online images from the web portal sites using specific words for color planning and more. Two experiments were conducted in order to accomplish this. Digital scenery photos within the geographic scope of Korea were downloaded from web portal sites, and those photos were studied to find out what colors were used to describe daytime and nighttime. Machine learning was used as the study methodology to classify colors in daytime and nighttime, and KSCA was used to derive the color frequency of daytime and nighttime photos and to compare and analyze the two results. The results of classifying the colors of daytime and nighttime photos using machine learning show that, when classifying the colors by 51~100%, the area of daytime colors was approximately 2.45 times greater than that of nighttime colors. The colors of the daytime class were distributed by brightness with white as its center, while that of the nighttime class was distributed with black as its center. Colors that accounted for over 70% of the daytime class were 647, those over 70% of the nighttime class were 252, and the rest (31-69%) were 101. The number of colors in the middle area was low, while other colors were classified relatively clearly into day and night. The resulting color distributions in the daytime and nighttime classes were able to provide the borderline color values of the two classes that are classified by brightness. As a result of analyzing the frequency of digital photos using KSCA, colors around yellow were expressed in generally bright daytime photos, while colors around blue value were expressed in dark night photos. For frequency of daytime photos, colors on the upper 40% had low chroma, almost being achromatic. Also, colors that are close to white and black showed the highest frequency, indicating a large difference in brightness. Meanwhile, for colors with frequency from top 5 to 10, yellow green was expressed darkly, and navy blue was expressed brightly, partially composing a complex harmony. When examining the color band, various colors, brightness, and chroma including light blue, achromatic colors, and warm colors were shown, failing to compose a generally harmonious arrangement of colors. For the frequency of nighttime photos, colors in approximately the upper 50% are dark colors with a brightness value of 2 (Munsell signal). In comparison, the brightness of middle frequency (50-80%) is relatively higher (brightness values of 3-4), and the brightness difference of various colors was large in the lower 20%. Colors that are not cool colors could be found intermittently in the lower 8% of frequency. When examining the color band, there was a general harmonious arrangement of colors centered on navy blue. As the results of conducting the experiment using two methods in this study, machine learning could classify colors into two or more classes, and could evaluate how close an image was with certain colors to a certain class. This method cannot be used if an image cannot be classified into a certain class. The result of such color distribution would serve as a reference when determining how close a certain color is to one of the two classes when the color is used as a dominant color in the base or background color of a certain design. Also, when dividing the analyzed images into several classes, even colors that have not been used in the analyzed image can be determined to find out how close they are to a certain class according to the color distribution properties of each class. Nevertheless, the results cannot be used to find out whether a specific color was used in the class and by how much it was used. To investigate such an issue, frequency analysis was conducted using KSCA. The color frequency could be measured within the range of images used in the experiment. The resulting values of color distribution and frequency from this study would serve as references for color planning of digital design regarding natural scenery in the geographic scope of Korea. Also, the two experiments are meaningful attempts for searching the methods for deriving colors that can be a useful reference among numerous images for content creator users of the relevant field.