의사결정나무 분석을 사용한 고가의료장비의 다빈도 사용 특성 분석

최윤정,곽민정,윤민,Choi, Yoon Jung,Kwak, Minjung,Yoon, Min 한국데이터정보과학회 2015 한국데이터정보과학회지 Vol.26 No.1

최근 고가의료장비의 도입으로 진단기술이 빠르게 발전하고 있으나 이에 따른 건강보험 재정의 부담이 크게 늘어 이에 대한 적절한 관리와 효율적 운영에 대한 정책이 필요하다. 이에 따라 본 연구에서는 의사결정나무분석 모형을 사용하여 CT 의료장비의 검사빈도에 영향을 미치는 요인을 파악하여 효율적 운영에 대한 방안을 제시한다. The cost of advanced medical technologies is commonly considered to be a major factor in the overall escalation of expenditures on health. The use of computed tomography (CT) scanning has increased dramatically over the past decade. CT has been rapidly adopted, despite their high cost. The aim of this study is to analysis the increasing factor of the frequency of the CT, using the decision tree model. Finally, we propose the effective policy option of diagnostic imaging technology in Korea.

정보화시대를 대비한 화학공학 데이터베이스

최윤정,양대륙 ( Y . J . Choi,D . R . Yang ) 한국화학공학회 1996 화학공학의이론과응용 Vol.2 No.2

아파트 개조 전후의 휘발성유기화합물 농도변화 실태

최윤정,심현숙,신해철,Choi, Yoon-Jung,Shim, Hyun-Suk,Shin, Hae-Chul 한국주거학회 2007 한국주거학회 논문집 Vol.18 No.4

The purposes of this study were to make clear the present condition of the TVOC and HCHO concentration after renovation in apartment houses. The field measurements of TVOC and HCHO concentration according to the Korea Test Method Standard for Indoor Air Quality were carried out in 4 subject apartment houses. The results are as follows; the TVOC concentration after renovation in apartment houses ranged from mean 0.35ppm to mean 5.08ppm and increased of $0.35{\sim}5.08ppm$. The TVOC concentration of 3 subjects exceeded the Indoor Air Quality Management standard for the newly-built apartment houses (0.58ppm). The HCHO concentration after renovation ranged from mean 0.13ppm to mean 0.43ppm and increased of $0.06{\sim}0.26ppm$. The HCHO concentration of 2 subjects exceeded the Standard (0.17ppm). As results of analysis on the relation of concentrated ascension and renovation elements, the amount and the types of finishing materials and adhesives affected concentrated ascension. Also, production method for installed or purchased furniture had certain effect on the TVOC and HCHO concentration ascension.

증식성 근막염의 세침흡인 세포학적 소견

최윤정,이상엽,양우익,정순희,이광길,Choi, Yoon-Jung,Yi, Sang-Yeop,Yang, Woo-Ick,Jung, Soon-Hee,Lee, Kwang-Gil 대한세포병리학회 1993 대한세포병리학회지 Vol.4 No.1

Proliferative fasciitis is a benign pseudosarcomatous mesenchymal lesion occurring in the subcutis. The lesion occurs clinically as a tumorous mass that develops within a rather short time in elderly patients. We recently experiecened a case of fine needle aspiration cytology of proliferative fasciitis in the left anterior chest wall of a 72 year-old male patient. The smear revealed two types of cells. One was the large and mostly oval cell with one or two nuclei lying at the periphery of the cell body and abundant basophilic cytoplasm like the ganglion cell. The nuclei were round to oval, had vesicular chromatin and contained prominent nucleoli. The other was the spindle shaped fibroblast with an oval nucleus. The differential diagnosis includes a true tumor such as ganglioneuroma, rhabdomyosarcoma, and liposarcoma and therefore fine needle aspiration cytology is very much indicated in order to exclude these possibilities.

경계범주 자동탐색에 의한 확장된 학습체계 구성방법

최윤정,지정규,박승수,Choi, Yun-Jeong,Jee, Jeong-Gyu,Park, Seung-Soo 한국정보처리학회 2009 정보처리학회논문지B Vol.16 No.6

본 논문은 기존의 목표항목만을 위주로 한 학습체계에서 발생하는 오분류 문제의 해결을 위해 기존의 학습체계에 경계항목을 자동으로 탐 색하여 포함시켜 확대시키는 방법을 제안하고 있다. 여러 주제에 걸쳐 다양한 내용을 다루는 복잡한 문서들은 확실히 어느 범주로 분류해야 할 지 판가름하기 어려운 성질인 모호성이 강하다. 이러한 경우 모든 경우들을 정확히 구분할 수 있는 최적의 경계를 찾는 일은 더욱 어려운 일이 다. 복잡하고 불확실성이 높은 데이터들의 특징은 대부분 분류 경계영역에 위치하므로 이러한 분류경계의 데이터들을 새로운 학습 항목으로 인 식시키도록 하는 것이 필요하다. 본 연구에서는 주어진 목표항목 사이의 경계항목을 자동으로 탐색하여 학습체계에 추가하는 학습 체계 확장 알고리즘을 제시하고, 의도적인 학습오류를 발생시킨 후 기존방법과의 비교실험을 수행함으로써 제안방법의 정확성과 안정성을 비교하였다. 실 험결과 경계범주를 포함하여 학습 체계를 확장시켰을 때의 예측력은 기존 0.70에서 0.86으로 약 24% 향상 되었고, 오류를 포함시켰을 때의 예 측력은 기존 0.52에서 0.79로 약 49% 향상되었다. This paper shows a reinforced construction scheme of training data for improvement of text classification by automatic search of boundary category. The documents laid on boundary area are usually misclassified as they are including multiple topics and features. which is the main factor that we focus on. In this paper, we propose an automated exploring methodology of optimal boundary category based on previous research. We consider the boundary area among target categories to new category to be required training, which are then added to the target category sementically. In experiments, we applied our method to complex documents by intentionally making errors in training process. The experimental results show that our system has high accuracy and reliability in noisy environment.

대학교 신축 기숙사의 휘발성유기화합물 농도 및 새집증후군 반응

최윤정,오예슬,장윤정,김정재,Choi, Yoon-Jung,Oh, Ye-Seul,Jang, Yoon-Jeong,Kim, Jung-Jae 한국주거학회 2009 한국주거학회 논문집 Vol.20 No.6

The purposes of this study were to determine the actual state of the indoor air quality by measuring TVOC Concentration and surveying residents' responses in a newly built university dormitory and to analyze the influencing factors of IAQ. Field measurements on the concentrations of TVOC and HCHO were carried out three times at 4 week intervals in 3 rooms of a dormitory. A questionnaire survey was conducted on residents which inquired into the resident's lifestyle, their consciousness of IAQ, and the responses to SHS. According to the results, TVOC concentrations were 0.14~18.5 ppm and HCHO concentrations were 0.23~6.89 ppm during the 3 months following the completion of construction, showing a serious state in which standard levels are exceeded, though these levels seemed to decrease over time. The factors influencing the differences in the levels of TVOC and HCHO were the ventilation volume including infiltration, the heating temperature, relative humidity, or the use of living matter that include chemical ingredients. However, the residents rarely felt the symptoms of SHS and were not conscious of the importance of ventilation.

아파트의 겨울철 실내온열환경 실태와 생활요인 분석

최윤정,정연홍,Choi, Yoon-Jung,Jeong, Youn-Hong 한국주거학회 2008 한국주거학회 논문집 Vol.19 No.4

The purposes of this study were to determine the actual state of the indoor thermal environment in apartment units and to analyze the relationship between the living factors and indoor thermal elements. The field surveys consisted of measurements of physical elements and observations of living factors. In addition, the residents of 20 apartment units were interviewed to survey their subjective response. Field surveys were carried out from January to March 2007. Measuring elements were air temperature, globe temperature, and relative humidity. The results showed that the average of indoor temperature for the houses was $21.2{\sim}27.2^{\circ}C$, while 4 houses exceeded the comfort zone. The average of globe temperature for the houses was $21.3{\sim}27.5^{\circ}C$, while 6 houses exceeded the comfort zone. The mean relative humidity was $19.5{\sim}58.8%$, which is a relatively dry condition. The residents' average clothing value was $0.39{\sim}0.89$ clo(average 0.68 clo). The average thermal sensation vote on each room was $4.2{\sim}4.8$, which is 'neutral' to 'slightly warm'. Living factors had significant effect on indoor temperature in regression analysis were ventilation time(outdoor air exchange), opening time of door through balcony, and gas cooker use time.

농촌지역 독거노인주택의 겨울철 실내환경 실태

최윤정,김윤희,김란희,Choi, Yoon-Jung,Kim, Yun-Hee,Kim, Lan-Hee 한국주거학회 2010 한국주거학회 논문집 Vol.21 No.3

The purposes of this study were to determine the actual state of indoor environments of solitary elderly houses in the rural district during winter and to analyze the relationship between the influencing factors and indoor physical elements. Field surveys consisted of measurements of physical elements, observations of living factors, and resident's responses in interviews. Field surveys were carried out in 4 houses from $28^{th}$ of February to $2^{nd}$ of March 2008. The elements measured were air temperature, relative humidity, floor temperature, seating-place temperature, CO2 concentration, CO concentration, and illumination. The results showed that the average indoor temperature for houses was $13.5{\sim}22.5^{\circ}C$, relative humidity was 30.6~55.4%, floor temperature was $13.9{\sim}24.0^{\circ}C$, temperature when seated was $27.6{\sim}51.1^{\circ}C$, $CO_2$ concentration was 1434.6~3305.5 ppm, CO concentration was 2.8~8.4 ppm, and illumination was 31.0~96.7 lux. The residents' clothing values were 1.10~1.78 clo. The environment was evaluated as being in an unsuitable state, and it was revealed that the main reason was the lack of heating and ventilation.

상향식 계층분류의 최적화 된 병합을 위한 후처리분석과 피드백 알고리즘

최윤정,박승수,Choi, Yun-Jeong,Park, Seung-Soo 한국정보처리학회 2010 정보처리학회논문지B Vol.17 No.2

본 논문은 자동화된 분류시스템의 성능향상을 위한 것으로 오분류율이 높은 불확실성이 강한 문서들의 범주결정방식을 개선하기 위한 후처리분석 방법과 피드백 알고리즘을 제안한다. 전통적인 분류시스템에서 분류의 정확성을 결정하는 요인으로 학습방법과 분류모델, 그리고 데이터의 특성을 들 수 있다. 특성들이 일부 공유되어 있거나 다의적인 특성들이 풍부한 문서들의 분류문제는 정형화된 데이터들에서 보다 심화된 분석과정이 요구된다. 특히 단순히 최상위 항목으로 지정하는 기존의 결정방법이 분류의 정확도를 저하시키는 직접적인 요인이 되므로 학습방법의 개선과 함께 분류모델을 적용한 이후의 결과 값인 순위정보 리스트의 관계를 분석하는 작업이 필요하다. 본 연구에서는 경계범주의 자동탐색기법으로 확장된 학습체계를 제안한 이전 연구의 후속작업으로써, 최종 범주를 결정하기까지의 후처리분석 방법과 이전의 학습단계로 피드백하여 신뢰성을 높일 수 있는 알고리즘을 제안하고 있다. 실험결과에서는 제안된 범주결정방식을 적용한 후 1회의 피드백을 수행하였을 때의 결과들을 단계적이고 종합적으로 분석함으로써 본 연구의 타당성과 정확성을 보인다. This paper shows a reinforcement post-processing method and feedback algorithm for improvement of assigning method in classification. Especially, we focused on complex documents that are generally considered to be hard to classify. A basis factors in traditional classification system are training methodology, classification models and features of documents. The classification problem of the documents containing shared features and multiple meanings, should be deeply mined or analyzed than general formatted data. To address the problems of these document, we proposed a method to expand classification scheme using decision boundary detected automatically in our previous studies. The assigning method that a document simply decides to the top ranked category, is a main factor that we focus on. In this paper, we propose a post-processing method and feedback algorithm to analyze the relevance of ranked list. In experiments, we applied our post-processing method and one time feedback algorithm to complex documents. The experimental results show that our system does not need to change the classification algorithm itself to improve the accuracy and flexibility.

학습방법개선과 후처리 분석을 이용한 자동문서분류의 성능향상 방법

최윤정,박승수,Choi, Yun-Jeong,Park, Seung-Soo 한국정보처리학회 2005 정보처리학회논문지B Vol.12 No.7

자동문서분류는 문서의 내용에 기반하여 미리 정의된 항목에 자동으로 할당하는 작업으로서 효율적인 정보관리 및 검색등에 필수적인 작업이다. 기존의 문서분류성능 향상을 위한 연구들은 대부분 분류모델 자체를 개선시키는 데 주력해왔으며 통계적인 방법으로 그 범위가 제한되어왔다. 본 연구에서는 자동문서분류의 성능향상을 위해 데이터마이닝 기법과 결함허용방법을 이용하는 개선된 학습알고리즘과 후처 리 방법에 의한 RTPost 시스템을 제안한다. RTPost 시스템은 학습문서 선택작업 이전에 분류항목 설정의 문제를 다루며, 분류함수의 성능보다는 지정방식의 문제점을 감안하여 학습과 분류 후처리 프로세스를 개선하려는 것이다. 이를 통해 분류결과에 중요한 영향을 미쳐왔던 학습문서의 수와 선택방법, 분류모델의 성능등에 의존하지 않는 안정적인 분류가 가능하였고, 이를 분류오류율이 높은 경계선 인접영역에 위치한 문서들에 적용한 결과 높은 정확율을 얻을 수 있었다. 뿐만 아니라, RTPost 프로세스를 진행하는 동안 능동학습방법의 장점을 수용하여 학습효과는 높이며 비용을 감소시킬 수 있는 자가학습방법(self learning)방법의 효과를 기대할 수 있다. Automated text categorization is to classify free text documents into predefined categories automatically and whose main goals is to reduce considerable manual process required to the task. The researches to improving the text categorization performance(efficiency) in recent years, focused on enhancing existing classification models and algorithms itself, but, whose range had been limited by feature based statistical methodology. In this paper, we propose RTPost system of different style from i.ny traditional method, which takes fault tolerant system approach and data mining strategy. The 2 important parts of RTPost system are reinforcement training and post-processing part. First, the main point of training method deals with the problem of defining category to be classified before selecting training sample documents. And post-processing method deals with the problem of assigning category, not performance of classification algorithms. In experiments, we applied our system to documents getting low classification accuracy which were laid on a decision boundary nearby. Through the experiments, we shows that our system has high accuracy and stability in actual conditions. It wholly did not depend on some variables which are important influence to classification power such as number of training documents, selection problem and performance of classification algorithms. In addition, we can expect self learning effect which decrease the training cost and increase the training power with employing active learning advantage.