http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
노인암 생존자의 삶의 질 관련요인 분석 : 2006-2016 고령화패널 조사 자료 활용
장혜경,박양춘,박소정,Jang, Hye-Kyoung,Park, Yang Chun,Park, So Jung 대한예방한의학회 2019 대한예방한의학회지 Vol.23 No.2
Objectives : The purpose of this study was to explore factors related quality of life among cancer survivor in order to identify strategies for cancer survivors to go back to normal life and carry on stable and high quality life. Methods : This study used the $1^{st}$ to $6^{th}$ data of Korean Longitudinal Study of Aging(KLoSA). The sample of this study consisted of 118 cancer survivors, all of whom were diagnosed with cancer for more than 10 years later in 2016. Results : Regression analysis of major factors related to the quality of life of elderly cancer survivors showed that the results of 2006 and 2016 were different. In 2006, factors related to cancer were highly correlated with quality of life, but in 2016, it was associated with pain and depression. Conclusions : The results of this study confirm that the factors related to quality of life in cancer survivors change with survival period. Therefore, this study suggests comprehensive care strategies based on the stage of survivorship.
실시간 얼굴인식 시스템을 위한 새로운 LINF 알고리즘의 제안
장혜경,강대성,Jang Hye-Kyoung,Kang Dae-Seong 대한전자공학회 2005 電子工學會論文誌-SP (Signal processing) Vol.42 No.4
본 논문에서는 실시간 얼굴인식 시스템을 위한 새로운 LINF(Linear Independent Non-negative Factorization) 알고리즘을 제안한다. 시스템은 크게 얼굴추출 부분과 얼굴인식 부분으로 구성 되어 있으며, 얼굴추출 부분에는 차영상, 눈과 입의 영역 검출 그리고 정규화 방법을 사용하였고, 얼굴인식 부분에는 추출된 얼굴 후보 영역 영상에 LINF 를 적용하였다. 기존의 PCA(Principal Component Analysis)만을 사용한 인식시스템은 낮은 인식률을 보였으며, LDA(Linear Discriminants Analysis)만을 사용한 인식시스템에서는 학습데이터의 수에 비하여 영상의 화소 개수가 많은 경우 LDA를 그대로 적용하기 곤란하였다. 이러한 단점을 극복하기 위하여, 본 논문에서 제안하는 시스템은 기존의 고유얼굴과 달리 비음수 값을 갖는 행렬로 차원을 축소하여 LDA를 적용하였다. 제안한 시스템의 성능을 평가하기 위하여 자체 제작한 DAUface 데이터베이스와 영국 Cambridge 에 있는 AT&T 연구소에서 제공하는 ORL 데이터베이스를 가지고 실험을 하였다. 실험 결과, 제안된 방법이 PCA 방법과 LDA 방법, ICA(Independent Component Analysis) 방법, 그리고 PLMA(PCA-based LDA mixture algorithm)에 비해 인식률이 상당히 우수함을 알 수 있었다. In this paper, we propose a new LINF(Linear Independent Non-negative Factorization) algorithm for real-time face recognition systea This system greatly consists of the two parts: 1) face extraction part; 2) face recognition part. In the face extraction Part we applied subtraction image, the detection of eye and mouth region , and normalization method, and then in the face recognition Part we used LINF in extracted face candidate region images. The existing recognition system using only PCA(Principal Component Analysis) showed low recognition rates, and it was hard in the recognition system using only LDA(Linear Discriminants Analysis) to apply LDA directly when the training set is small. To overcome these shortcomings, we reduced dimension as the matrix that had non-negative value to be different from former eigenfaces and then applied LDA to the matrix in the proposed system We have experimented using self-organized DAIJFace database and ORL database offered by AT(')T laboratory in Cambridge, U.K. to evaluate the performance of the proposed system. The experimental results showed that the proposed method outperformed PCA, LDA, ICA(Independent Component Analysis) and PLMA(PCA-based LDA mixture algorithm) method within the framework of recognition accuracy.
관심영역(ROI)을 이용한 정교한 얼굴인식 알고리즘 연구
박준규(Jun-gyu Park),장혜경(Hye-Kyoung Jang),강대성(Dae-Seong Kang) 한국정보기술학회 2014 Proceedings of KIIT Conference Vol.2014 No.5
본 논문은 보다 더 정교한 얼굴인식 알고리즘을 만들기 위해서 Haar와 관심영역을 이용한다. 먼저 많은 양의 positive 얼굴 샘플과 negative 얼굴 샘플을 1:2의 비율로 수집하고 학습시켜 XML 파일을 생성한다 그 후 Haar를 이용하여 얼굴 특징을 찾은 후에 그 좌표값을 받아와 관심영역 (ROI)을 지정한다. 관심영역을 지정한 후에도 얼굴 특징과 비슷한 다른 물체를 인식할 수도 있다. 그래서 보다 더 정확한 얼굴 인식을 위해 관심영역 내에서 눈 코 입 샘플이 학습된 XML 파일을 이용하여 Haar를 실행한다 그 후 관심영역 (ROI) 내의 좌표의 값을 얻고 이 좌표 값으로 위치에 따라 눈 코 입을 추출한다. 그리하여 얼굴이 아닌 다른 물체는 걸러 내게 되고 더욱더 정교한 얼굴인식을 할 수 있게 된다. In this paper, I proposed using Haar and the area of interest to make more sophisticated face recognition algorithm. First, a large of amount of positive face samples and negative face samples collect ratio of 1:2 and after learn to make the XML file. After find facial feature which using the Harr, get the coordinates. and the great value region of interest (ROI) is designated. After designate the area of interest , It can recognize other object which is similar facial feature. So, for more exact face detection, region of interest (ROI) is performed using XML file which learned the eyes, nose, and mouth, After obtain the coordinate in a region of interest (ROI), used this coordinate to extracted the location of the eyes, nose, and mouth. Thus, Filter out the objects except the face. and then face recognition is more sophisticated can be obtained.
동적 GTM와 BMA을 이용한 움직이는 객체의 얼굴 검출
장혜경,홍종선,강대성 동아대학교 정보기술연구소 2003 情報技術硏究所論文誌 Vol.11 No.1
This paper estimates dynamic object information in video stream and proposes face detection technique using dynamic GTM(genetic tree-map) algorithm. The existing general object estimate methods divided image information through cluster process, and estimated as reconstructing the moving object of the separate information. On the other hand, proposed method obtains object information that is moving in video stream as taking advantage of BMA(b1ock matching algorithm) and employs PCA(principal component analysis) as cluster algorithm. PCA algorithm searches for principal components utilizing statistical properties for input data, and then divides data making use of region division algorithm. Only face region is detected in specific object abstracted using separate object information, according to dynamic GTM map information generated about feature of face region using dynamic GTM.
이지은,장혜경,오지영,유윤경,김현지,임숙인,연숙희,강진숙,최귀령 한국병원약사회 2003 병원약사회지 Vol.20 No.1
In an aging society, there is an increasing possibility of the duplication of the drugs given to patients because they take many kinds of drugs. Among the prescriptions given to the patients who was treated at multiple ambulatory clinics in St. Mary's hospital for one month of September, 2002, in which drugs that has identical or similar effects are prescribed, we analysed and evaluated them by patients' characteristics, kinds of medication, severity of side effects on a case by case basis. More, we assessed the potential additional costs. As a result of this study, the duplication rate turned out to be 6.69% and it was shown that the proportion of the elderly patients over 60 was high. The gastro-intestinal medications took up a large part and most of the cases showed that the danger caused by double taking of medicine was slight, but there were some examples in which the serious side effects were predicted. Expected additional costs were the average 11.349 won and it ranges from the minimum of 56 won to the maximum of 135,720 won. In conclusion, the management of drug histories of the patients who need the plural treatments is very important and the necessity of the individual and professional guidance of taking medicines for the elderly patients is emerged, too.