http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
한방병원에 내원한 특발성 폐섬유화증 환자 82명에 대한 임상적 특징 분석; 후향적 차트 리뷰
홍성은,강성우,박지원,장권준,박수현,김관일,부영민,정희재,이범준,Hong, Sung-eun,Kang, Sung-woo,Park, Ji-won,Jang, Kwon-jun,Park, Su-hyeon,Kim, Kwan-il,Bu, Yung-min,Jung, Hee-jae,Lee, Beom-joon 대한한방내과학회 2021 大韓韓方內科學會誌 Vol.42 No.3
Objective: This study was designed to analyze the clinical features of idiopathic pulmonary fibrosis patients who attended a Korean medicine hospital and the treatment effects through retrospective chart reviews. Methods: The medical records of 82 outpatients who had been diagnosed with idiopathic pulmonary fibrosis and visited the Allergy, Immune, and Respiratory System Department of Kyung Hee Korean Medicine Hospital from 8 January 2015 to 8 January 2021 were retrospectively reviewed. To assess the treatment outcomes, we used the FVC (Forced Vital Capacity), DLCO (Diffusing capacity of the Lung for CO), 6-minute walk test, and HRCT (High Resolution Computed Tomography). Results: The study group consisted of 28 females and 54 males. The median age of the patients was 67.98±11.44 years. The chief complaints were cough (n=51) and dyspnea (n=49). Other frequent symptoms were general weakness (n=8), weight loss (n=4), and a fever (n=2). A total of 77 (93.90%) patients were prescribed Korean herbal medicine, and 52 (63.41%) patients were treated with acupuncture, moxibustion, cupping therapy, ICT, or pharmacopuncture. After treatments, FVC, DLCO, the 6-minute walk test, and HRCT were maintained or worsened slightly. Conclusions: This study presented the characteristics of idiopathic pulmonary fibrosis patients treated by Korean medical therapies, and further studies of Korean medical treatments for idiopathic pulmonary fibrosis patients would be valuable.
영상 내 차량의 위치 및 촬영 각도에 강인한 차량 번호판 인식 시스템
홍성은,황성수,김성대,Hong, Sungeun,Hwang, Sungsoo,Kim, Seongdae 대한전자공학회 2012 전자공학회논문지 Vol.50 No.8
최근 지능형 교통 시스템을 다양한 상황 및 환경에 적용하려는 시도가 증가함에 따라, 다수의 지능형 교통 시스템에서 사용되고 있는 차량 번호판 인식 과정이 입력영상 내 차량의 위치 및 촬영 각도와 관계없이 정확하게 이루어질 필요성이 있다. 본 논문에서는 현행 번호판의 규격정보를 활용하여 오검출된 번호판 후보 영역의 제거 및 번호판 내 글자추출을 수행하고, 한글 특성을 고려한 글자인식을 수행하는 차량 번호판 인식 시스템을 제안한다. 제안하는 시스템은 입력영상에서 검출한 번호판 후보 영역들에 대해서 기울기 보정을 수행한 후, 후보 영역 내 글자로 판명되는 객체의 위치 및 형태 정보를 번호판 규격정보와 비교 검증하는 과정을 거쳐 오검출된 번호판 영역을 제거한다. 또한 글자추출 단계에서는 영역 내 밝기 변화를 고려한 이진화를 수행한 뒤, 번호판 규격정보 및 번호판 영역의 종횡비, 배경색, 투영정보 등을 종합적으로 활용하여 번호판 영역 내 글자를 정확하게 추출한다. 그리고 번호판 영역 내 글자들 중 오인식률이 높은 한글의 인식에 있어서, 형태적 유사성으로 그룹을 나눈 뒤, 주요 특징점들을 토대로 계층을 좁혀 나가는 super-class 개념을 적용하여 한글 인식을 수행한다. 성능 검증을 위해 다양한 배경에서 촬영된 영상에 대해서 실험을 수행한 결과 제안하는 번호판 인식 시스템이 영상 내 차량의 위치 및 촬영 각도의 변화에 강인한 것을 확인할 수 있었다. Recently, various attempts have been made to apply Intelligent Transportation System under various environments and conditions. Consequently, an accurate license plate recognition regardless of vehicle location and viewing angle is required. In this paper, we propose a novel license plate recognition system which exploits a) the format of license plates to remove false candidates of license plates and to extract characters in license plates and b) the characteristics of Hangul for accurate character recognition. In order to eliminate false candidates of license plates, the proposed method first aligns the candidates of license plates horizontally, and compares the position and the shape of objects in each candidate with the prior information of license plates provided by Korean Ministry of Construction & Transportation. The prior information such as aspect ratio, background color, projection image is also used to extract characters in license plates accurately applying an improved local binarization considering luminance variation of license plates. In case of recognizing Hangul in license plates, they are initially grouped according to their shape similarity. Then a super-class method, a hierarchical analysis based on key feature points is applied to recognize Hangul accurately. The proposed method was verified with high recognition rate regardless of background image, which eventually proves that the proposed LPR system has high performance regardless of the vehicle location or viewing angle.
공공데이터를 활용한 교통사고 상해 심각도 예측 모델 연구
홍성은(Seong-Eun Hong),이구연(Goo-Yeon Lee),김화종(Hwa-Jong Kim) 한국정보기술학회 2015 한국정보기술학회논문지 Vol.13 No.5
When a car accident occurs, there are two types of damages from the accident; human damage and material damage. Prediction model of human damage according to accident types may be helpful to find out severity of accident type or estimating compensation cost for the insurance company. It may also be used to decide compensation outlier. In the paper, we propose a severity prediction model of car accidents. We use a hybrid model of random forest algorithm and CART decision tree with up-sampling based one-vs-all scheme. We use open data of car accidents from Korean government according to the open data policy. The proposed severity prediction model of car accidents shows more accurate estimation comparing to the previous research, and is expected to be effectively used in car accident damage analysis.