• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.5
• /
• pp.535-546
• /
• 2020

Land cover maps are derived from satellite and aerial images by the Ministry of Environment for the entire Korea since 1998. Even with their wide application in many sectors, their usage in research community is limited. The main reason for this is the map compilation cycle varies too much over the different regions. The situation requires us a new and quicker methodology for generating land cover maps. This study was conducted to automatically generate land cover map using aerial ortho-images and Landsat 8 satellite images. The input aerial and Landsat 8 image data were trained by Residual U-Net, one of the deep learning-based segmentation techniques. Study was carried out by dividing three groups. First and second group include part of level-II (medium) categories and third uses group level-III (large) classification category defined in land cover map. In the first group, the results using all 7 classes showed 86.6 % of classification accuracy The other two groups, which include level-II class, showed 71 % of classification accuracy. Based on the results of the study, the deep learning-based research for generating automatic level-III classification was presented.

• Journal of Cadastre & Land InformatiX
• /
• v.50 no.1
• /
• pp.75-85
• /
• 2020

This study examines machine learning cross-validation to utilized create ROI for classification of land cover. The study area located in Sejong and one KOMPSAT-3A image was used in this analysis: procedure on October 28, 2019. We used four bands(Red, Green, Blue, Near infra-red) for learning cross validation process. In this study, we used K-fold method in cross validation and used SVM kernel type with cross validation result. In addition, we used 4 kernels of SVM(Linear, Polynomial, RBF, Sigmoid) for supervised classification land cover map using extracted ROI. During the cross validation process, 1,813 data extracted from 3,500 data, and the most of the building, road and grass class data were removed about 60% during cross validation process. Based on this, the supervised SVM linear technique showed the highest classification accuracy of 91.77% compared to other kernel methods. The grass' producer accuracy showed 79.43% and identified a large mis-classification in forests. Depending on the results of the study, extraction ROI using cross validation may be effective in forest, water and agriculture areas, but it is deemed necessary to improve the distinction of built-up, grass and bare-soil area.

• Advances in pediatric surgery
• /
• v.1 no.2
• /
• pp.140-148
• /
• 1995

To study the clinical profiles and outcome of surgery in infants with esophageal atresia, we reviewed 96 esophageal atresia cases who were treated from April, 1978 to June, 1995. There were 51 male and 45 female infants, a ratio of 1.1:1. The low birth weight(<2500g) patients were 32%. Clinical findings at the time of diagnosis included drooling in 57%, choking in 50%, cyanosis in 38%, respiratory distress in 27% and swallowing difficulty in 20%. Gross classification included 6 cases of type A esophageal atresia(6%), 79 cases of type C(82%), 3 cases of type E (3%) and 8 cases of type F(8%). Associated anomalies occurred in 34 infants(35%). Among them, cardiac anomalies were most common(60%). A primary repair of the defect was carried out in 76 patients with type A or C. A staged operation comprising a repair or gastric tube interposition after gastrostomy was performed in 8 patients. In all 3 infants with H-type, a division of fistula was performed. Esophageal resection and anastomosis was done in 8 infants with esophageal stenosis. In one infant, a gastrostomy was performed and he expired before staged operation. Anastomotic complications included leakage in 16 cases(17%), stricture in 37 cases(39%) and recurrent tracheoesopohageal fistula in 3 cases(3%). The mortality rate was 14% and the leading cause of death was pneumonia. The overall survival rate was 86%, and according to Waterston criteria, the survival rates were 93%, 85% and 58% in class A, Band C, respectively. 75 patients were followed up with median follow up 6.4 years. Among them, 93% were uneventful and 7% had frequent pneumonia.

• Journal of Acupuncture Research
• /
• v.32 no.4
• /
• pp.91-102
• /
• 2015

Objectives : The Oriental medical device industry is expected to continue to experience significant growth. It should increase its global market share rather than focusing on the domestic market. Countries around the world self-regulate their domestic market, so this study aims to aid in the development of a particular overseas market by introducing the U.S.(the largest market) medical device registration and approval process. Methods : For an understanding of the US medical device licensing process, we researched the relevant regulatory organization (FDA), the history, definition and classification of medical devices, the approval and 510(k) submission process related to substantial equivalence, IEC 60601-1 Edition 3, usability tests, and so on. Results : Medical devices in the United States are assigned to one of three regulatory classes: Class I, Class II and Class III, based on the level of control necessary to assure the safety and effectiveness of the device. If a company's device is classified as Class II and if it is not exempt, a 510k will be required for marketing. 1) A 510(k) is a premarket submission made to the FDA to demonstrate that the new device to be marketed is "substantially equivalent" to a legally marketed device (predicate device) 2) The IEC 60601-1 Edition 3 preparation process, which contains information related to usability, is expensive and time-consuming but a critical requirement. Conclusions : Although the U.S. market has high barriers to entry, access to this, large overseas market will encourage development of the Oriental medical device industry and commercial value enhancement is expected.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.11 no.5
• /
• pp.38-59
• /
• 2008

This research has a meaning to provide basic data for eco-friendly way of district unit plans and ecological landscape planning by evaluation of biotope preservation value at the level of district unit and designating land development of the site, the whole area of Sinseo-dong (Dong-gu, Daegu metropolitan city) for research site. The summary of analysis result is as follows. As a result of classification of biotope types on the research site, it is divided into 11 biotope groups such as a residential biotope group and 51 specific biotope types which is subordinate to the groups. As a result of the first value assessment on classified biotope types, there are 16 types of natural rivers which is full of vegetation as a I class. Also it is analysed as 9 types of IIclass, 14 of IIIclass, 8 of IVclass, and 4 of Vclass. In particular, in light of a wildlife habitat, EB, in case of broad-leaved tree of mixed forest assessed as a II class, was classified into Iclass which is one-step upgraded as a final class with the analysis as there is a structural characteristic (more than 71% of low density, 50 years of age-class). As a result of second assessment, it is analysed that there are 17 special sites (1a,1b) and 33 special sites (2a, 2b, 2c) respectively for preservation of species and biotope. Particularly, in case of the No. 27 space, it was assessed that it has the value of about medium (IIIclass) level, but its value was upgraded with the on-spot detailed investigation that most of Aristolochia contorta, designated as a rare plant by Ministry of Environment, is growing. It is regarded that the above-mentioned research result on evaluation of biotope preservation value is expected to provide very important basic materials for future district unit plans and smooth integration with landscape ecology plans and eco-friendly space development.

• Journal of Environmental Science International
• /
• v.17 no.6
• /
• pp.679-687
• /
• 2008

In this study, we implemented landslide distribution of Jeju Island using ANN and GIS, respectively. To do this, we first get the counter line from 1:2,5000 digital map and use this counter line to make the DEM. for the evaluate the land slide susceptibility. Next, we abstracted slop map and aspect map from the DEM and get the land use map using ISODATA classification method from Landsat 7 images. In the computation processes of landslide analysis, we make the class to the soil map, tree diameter map, Isohyet map, geological map and so on. Finally, we applied the ANN method to the landslide one and calculated its weighted values. GIS results can be calculated by using Acrview program and produced Jeju landslide susceptibility map by usign Weighted Overlay method. Based on our results, we found the relatively weak points of landslide ware concentrated to the top of Halla mountains.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.663-667
• /
• 2004

This paper presents new pruning and learning methods for the fuzzy rule-based classifier. The structure of the proposed classifier is framed from the fuzzy sets in the premise part of the rule and the Bayesian classifier in the consequent part. For the simplicity of the model structure, the unnecessary features for each fuzzy rule are eliminated through the iterative pruning algorithm. The quality of the feature is measured by the proposed correctness method, which is defined as the ratio of the fuzzy values for a set of the feature values on the decision region to one for all feature values. For the improvement of the classification performance, the parameters of the proposed classifier are finely adjusted by using the gradient descent method so that the misclassified feature vectors are correctly re-categorized. The cost function is determined as the squared-error between the classifier output for the correct class and the sum of the maximum output for the rest and a positive scalar. Then, the learning rules are derived from forming the gradient. Finally, the fuzzy rule-based classifier is tested on two data sets and is found to demonstrate an excellent performance.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.15 no.4
• /
• pp.485-494
• /
• 2008

Purpose: In this study, relationships between symptom experience and quality of life in a cross-sectional sample of patients with Atrial Fibrillation (AF) were investigated. Methods: This descriptive study involved a convenience sample of AF patients from S university hospital, C city. One hundred and two AF patients completed psychometric validated measures of AF related symptoms and quality of life. Descriptive statistics and Pearson correlation coefficients with SPSS WIN 14.0 were used for data analysis. Results: Of 16 atrial arrhythmia-related symptoms, the patients reported 'tiredness' as the most frequent and 'shortness of breath' as the most severe. The level of overall quality of life for patients with AF was 53.92. There were significant differences in symptom frequency according to religion, New York Heart Association (NYHA) classification and left ventricular ejection fraction ; symptom severity according to monthly income and stroke ; quality of life according to age, job, alcohol intake, NYHA class and stroke. Quality of life for these patients was positively correlated with symptom frequency and symptom severity. Conclusions: This study demonstrated that patients with more frequent and severe symptoms perceive poorer quality of life than patients with less frequent and less severe symptoms. Symptom experience should be assessed early to improve quality of life for patients.

• Research in Community and Public Health Nursing
• /
• v.28 no.4
• /
• pp.386-396
• /
• 2017

Purpose: The purpose of this study was to investigate the influence of social support, self - esteem, hope, and health conservation of the vulnerable elderly people with diabetes. Methods: Participants were 100 vulnerable elderly people with diabetes living in D or K cities. Data collection was done through interviews from February to March, 2016. Social support was measured with the MOS-SSS (Medical Outcomes Study Social Support Survey), self-esteem with Self-Esteem Scale, hope with the Nowotny Hope Scale, and health conservation with the Sung's Health Conservation Scale. IBM SPSS 20.0 was used to analyze descriptive statistics, one-way ANOVA, independent t-test, Pearson correlation, and stepwise multiple regression. Results: Factors affecting the health conservation of the vulnerable elderly people were social support, hope, education level and subjective health status. These factors explained 64.9% of the health conservation. Conclusion: It is necessary to construct a comprehensive nursing classification system for elderly people with diabetes in vulnerable class and to develop integrated health conservation program and nursing care as a new social support resource.

• Journal of Oral Medicine and Pain
• /
• v.14 no.1
• /
• pp.19-24
• /
• 1989

The purpose of this study was to investigate the reliability of electromyographic examination in a day and detect the objective measurement timing of electromyography. 18 normal students who were in dental collage of C national university were selected for this study. They had no symptoms on temporomandibular joint area, no restorations and missing tooth on dentition. Their molar relationship was normal or class I of Angle's classification. Electromyography had been taken every one hour from 9:00 A.M. to 5:00 P.M. in the state of clenching and rest by using Bioelectric processor EM2 interfaced with mandibular kinesiograph K-6 diagnostic system. We compared and analyzed the variances of electromyography values of each subjects. The obtained results were as follows : There were no significant differences on variability of electromyography values in each state clenching and rest. In the aspect of this circumstances, the use of electromyography could be a good objective procedure to diagnose the temporomandibular disorders and to detect the effect to the treatment of temporomandibular disorders at any time in a day from 9:00 A.M. to 5:00 P.M.