• 대한의용생체공학회:의공학회지
• /
• 제32권2호
• /
• pp.134-143
• /
• 2011

The selection of meaningful clinical tests and its reference values from a high-dimensional clinical data with imbalanced class distribution, one class is represented by a large number of examples while the other is represented by only a few, is an important issue for differential diagnosis between similar diseases, but difficult. For this purpose, this study introduces methods based on the concepts of both discernibility matrix and function in rough set theory (RST) with two discretization approaches, equal width and frequency discretization. Here these discretization approaches are used to define the reference values for clinical tests, and the discernibility matrix and function are used to extract a subset of significant clinical tests from the translated nominal attribute values. To show its applicability in the differential diagnosis problem, we have applied it to extract the significant clinical tests and its reference values between normal (N = 351) and abnormal group (N = 101) with either cholecystitis or cholelithiasis disease. In addition, we investigated not only the selected significant clinical tests and the variations of its reference values, but also the average predictive accuracies on four evaluation criteria, i.e., accuracy, sensitivity, specificity, and geometric mean, during l0-fold cross validation. From the experimental results, we confirmed that two discretization approaches based rough set approximation methods with relative frequency give better results than those with absolute frequency, in the evaluation criteria (i.e., average geometric mean). Thus it shows that the prediction model using relative frequency can be used effectively in classification and prediction problems of the clinical data with imbalanced class distribution.

• Journal of Chest Surgery
• /
• 제29권11호
• /
• pp.1202-1206
• /
• 1996

Ebstein기형은 삼첨판, 우심실 및 우심방의 특징적인 변형를 보이는 희귀한 선천성 심질환으로, 삼첨판의 후판막첨과 중격판막첨이 우심실로 나선형의 변형을 보이는 것이 특징적이다. 본 교실에서는 1988년 1월 1일부터 1995년 12월 31일까지 7년간 11명의 환자를 경험하였으며 평균연령은 29.6$\pm$11.1세, 성비는 남자 5명 여자 6명이었고, 주증상으로는 운동시 호흡곤란이었다. 모든례에서 삼첨판의 전형적인 변형을 보였으며 동반된 심기형으로는 개방성 난원창, 심방중격결손, 심실중격결손이 있었다. 9명은 Danielson씨 삼첨판성형술과 주름성형술을 시행하고 2명은 삼첨판막치환술과 주름성형술을 시행하였으며 동반된 심기형을 교정하였다. 수술후 5명의 환자에서 저심박출증, 부정맥, 창상감염 등의 합병증이 발생하였으며 수술사망례는 없었다. 술후 평균 33.3개월의 추적관찰 결과 모든 환자에서 술전보다 양호한 심기능을 보였다.

• 한국컴퓨터정보학회논문지
• /
• 제18권11호
• /
• pp.159-165
• /
• 2013

본 논문은 NP-완전 문제인 간선 색칠과 그래프 부류 결정 문제를 동시에 해결하는 O(E)의 다항시간 알고리즘을 제안하였다. 제안된 알고리즘은 최대차수-최소차수 정점 쌍 간선을 단순히 선택하는 방법으로 간선 채색수 ${\chi}^{\prime}(G)$를 결정하였다. 결정된 ${\chi}^{\prime}(G)$는 ${\Delta}(G)$ 또는 ${\Delta}(G)+1$을 얻는다. 결국, 알고리즘 수행 결과 얻은 ${\chi}^{\prime}(G)$로부터 ${\chi}^{\prime}(G)={\Delta}(G)$이면 부류 1, ${\chi}^{\prime}(G)={\Delta}(G)+1$이면 부류 2로 분류할 수 있다. 또한, 미해결 문제로 알려진 "최대차수가 6인 단순, 평면 그래프는 부류 1이다."라는 Vizing의 평면 그래프 추정도 증명하였다.

• 환경영향평가
• /
• 제22권1호
• /
• pp.65-78
• /
• 2013

Since pursuing the pleasant life for people, there is an increase of desire to appreciate outstanding scenery with the difference in certain level for perception and understanding of human on landscaping, However, the quality of landscaping has become artificial with the pleasance to be declining due to the urbanization. This study was applied at the site around High One Resort area in Gohan-eup, Jeongseon-gun Gangwon-do for analyzing the areas sensitive to the landscaping change as well as degree of requirement for landscape management for forest landscape management with the focus on presenting the zoning method and the management class classification method. Even if the forest is the same, the function of it is different depending on land use or what resource is placed that the forestry function is found out to present the management plan for each forestry function in the subject site and the result of the management grade classification is analyzed in overlapping to the forestry function level. As a result, from the landscaping management requirement and visual absorption analysis, the result formulated for upper, middle and lower zones to classify the final forestry landscape management degree into 1-4 grades and the management plan is presented on the respective 1-4 grade area for each forestry function. By applying the technique to set the management grade, it was possible to formulate the result to provide the means for integrated management in consideration of the forestry function and management of forestry landscape and resources.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• 제31권3호
• /
• pp.255-259
• /
• 2005

We observed 469 cases (male 217 cases, female 252 cases) with dento-facial deformity for 10 years from Jan 1994 to Dec 2003. The ratio of male to female was 1:1.2 and the mean age was 23.3 years (male 24.0 years, female 22.6 years) ranged from 11 to 43 years. The most dominant group was related to mandibular prognathism (80.4%). A rate of 83.8% demonstrated mandibular protrusion according to Slavicek's classification (n=160), and 85.4% were classified as skeletal Class III type according to Sugawara's classification (n=151). Surgical method were divided into 355 cases of one jaw surgery (single method), 26 cases of one jaw surgery (combined method), and 77 cases of two jaw surgery. Sagittal split osteotomy were performed on 316 cases (69.0%). The average operation time and blood loss in SSRO were $4.1{\pm}2.2$ hrs. and $138.8{\pm}222.6$ ml (n=152).

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제67차 동계학술대회논문집 31권1호
• /
• pp.39-42
• /
• 2023

최근 온라인 게임 산업이 급속도로 확장됨과 더불어 Gamebot과 같은 비정상적인 프로그램으로 인한 게임 서비스 피해사례가 급격하게 증가하고 있다. 특히, 대표적인 게임 장르 중 하나인 FPS(First-Person Shooter)에서 Aimbot의 사용은 정상적인 이용자들에게 재미 요소를 잃어버리게 하고 상대적 박탈감을 일으켜 게임의 수명을 줄이는 원인이 된다. 비정상 게임 이용자의 근절을 위해서 메모리 변조 및 불법 변조 프로그램 접근 차단 기법과 불법 프로그램 사용의 패턴 모니터링과 같은 기법들이 제안되었지만, 우회 프로그램 및 새로운 패턴을 이용한 비정상적인 프로그램의 개발에는 취약하다는 단점이 있다. 따라서, 본 논문에서는 정상적인 게임 이용자의 패턴만 학습함으로써 비정상 이용자 검출을 가능하게 하는 딥러닝 기반 단일 클래스 분류 기법을 제안하며, 가장 빈번하게 발생하는 치트(Cheat) 유형인 FPS 게임 내 Aimbot 사용 감지에 초점을 두었다. 제안된 비정상 게임 이용자 감지 시스템은 정상적인 사용자의 마우스 좌표를 데카르트 좌표계(Cartesian coordinates)와 극좌표계(Polar coordinates)의 형태로 패턴을 추출하는 과정과 정상적인 마우스 동작 기록으로 부터 학습된 LSTM 기반 Autoencoder의 복원 에러에 따른 검출 과정으로 구성된다. 실험에서 제안된 모델은 FPS 게임 내 마우스 동작을 기록한 공개 데이터셋인 CSGO 게임 데이터셋으로 부터 학습되었으며, 학습된 모델의 테스트 결과는 데카르트 좌표계로부터 훈련된 제안 모델이 비정상 게임 이용자를 분류하는데 적합함을 입증하였다.

• 대한치과교정학회지
• /
• 제9권1호
• /
• pp.39-65
• /
• 1979

The purpose of this study was to investigate the pattern of irregularities of teeth in various malocclusion groups. The subjects consist of 803 out-patients (355 males, and 448 females) in department of Orthodontics of S.N.U. Hospital, Yonsei University, and Kyunghi University Hospital. The results were as follows. 1. The proportions of subjects on the basis of Angle's Classification were 39.2% (42.2% male, and 57.8% fomale) in class I malocclusion, 29.0% (44.6% male, and 55.4% female) in class II. div. 1., 3.5%(46.4% male, and 53.6% female) in class II. div. 2., 28.3%(46.3% male, and 53.7% female) in class III. 2. Considering all the subjects, the percentage of teeth crowding was 67.8% (45.0% male, and 55.0% female). In class I malocclusion, the percentage of Crowding was 70.8%(43.5% male, and 56.5% female) with higher frequency in upper anterior teeth than in lower anterior. 3. The percentage of Maxillary anterior diastema was 25.6% (45.6% male, and 54.4% female) on the whole. In class II. div. 1. malocclusion, the percentage was 28.8% (46.3% male, and 53.7% female) and in class III, the percentage was 19.8% (46.7% male, and 53.3% female). Thus, frequency of maxillary anterior distema, was comparatively higher in class II. div. 1. than in class III. 4. The percentage of high canine was 25.1% (53.2% male, and 46.8% female) on the whole, and was 86.0% male and 76.6% female in right side, 73.0% male and 72.3% female in left side. In calss II. div. 2., the percentage was 53.6% (46.7% male, and 53.3% female ). In class II. div. 1., the percentage was 16.7% (46.2% male, and 53.8%) with higher frequency in class II. div.2. 5. The percentage of deep overbite was 23.0% (43. 2% male, and 56.8% female) on the whole. Ia class 11. div. 2., and in clas sll. div. 1., its were 89.3%(48.0% male and 52.0% female), 54.5% (40.9% male, and 59.1% female) respectively. This result can be considered as one of the characterics of Angle's class 11 malocclusion group. 6. The percentage of spacing was 23.0% (36.8% male, and 63.2% female) on the whole, In class II. div. 1., and in class II. div. 2., its were 26.1% (44.3% male, and 55. 7% female), 7.1% (50.0% male, and 50.0% female) respectively. 7. The percentage of open bite was 14.3% (42.6% male, and 57.4% female) on the whole with higher rate on the anterior part. It rated 17.6%(50. 0% male, and 50.0% female) in class III, but none in class II. div. 2. 8. The percentage of crossbite was 22.5% (55.8% male, and 44.2% female) on the whole, with higher frequency on the anterior part than on the posterior part. In Angle's class III, it rated as much as 55.1% (57.6% male, and 42.4% female). 9. The percentage of edge-to-edge bite was 20.4% (47.6% male, and 52.4% female) with higher frequency on anterior part than on posterior part. 10. The percentage of irregularities of teeth in various malocclusion groups, was 21.5% (24.8% maxillary, and 18.1% mandible) in crowding, 20.8% (23.5% maxillary, and 18.0% mandible) in rotation, 10.7% (10.6% maxillary, and 10.8% mandible) in cross bite, 9.5% (11.8% maxillary, and 7.3% mandible) in spacing, 8.5% (8.5% maxillary, and 8.5% mandible) in edge-to-edge bite, 8.1% (8.3% maxillary, 7.8% mandible) in open bite. Crowding teeth, spacing teeth, and rotating teeh were more prevalent in anterior part than in posterior part. Cross bite teeth and edge-to-edge bite teeth were more prevalent in class III malocclusion than in another.

• 한국의류학회지
• /
• 제29권3_4호
• /
• pp.569-575
• /
• 2005

The objective of this study is to consider the concept of postmodernism and the characteristics concerning the stage of the development, and to investigate the effect of the postmodernism on the clothing. Postmodernism is the result of the late capitalism and its characteristics are the narrative, mixture and deconstruction. First, since it is impossible to express the social culture of various society through one theoretical disclosure, the novel value on the narrative is provided and its characteristics arise. Hence, the society becomes afford to accept the other and provides the novel value to the absolute sub-concept. Second, the recognization and emphasis of the narrative in the post modem society bring about the repulsion as to the strict classification between the high culture and low one established from modernism and the closure between each genre of the art, and this causes to raise the composed characteristics which borrow or mix the style and image of different age and culture. Third, the deconstructive feature arises which eliminates the boundary between the high and low class, the past and future and the destruction and construction. This means not only anther recomposition but also skeptical attitude about it.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2853-2873
• /
• 2013

Over the last few years, one of the most common purposes of smart homes is to provide human centric services in the domain of u-healthcare by analyzing inhabitants' daily living. Currently, the major challenges in activity recognition include the reliability of prediction of each classifier as they differ according to smart homes characteristics. Smart homes indicate variation in terms of performed activities, deployed sensors, environment settings, and inhabitants' characteristics. It is not possible that one classifier always performs better than all the other classifiers for every possible situation. This observation has motivated towards combining multiple classifiers to take advantage of their complementary performance for high accuracy. Therefore, in this paper, a method for activity recognition is proposed by optimizing the output of multiple classifiers with Genetic Algorithm (GA). Our proposed method combines the measurement level output of different classifiers for each activity class to make up the ensemble. For the evaluation of the proposed method, experiments are performed on three real datasets from CASAS smart home. The results show that our method systematically outperforms single classifier and traditional multiclass models. The significant improvement is achieved from 0.82 to 0.90 in the F-measures of recognized activities as compare to existing methods.

• 한국컴퓨터산업학회논문지
• /
• 제2권2호
• /
• pp.151-156
• /
• 2001

우리는 개념 학습에 있어서 전통적으로 사용되어 온 연역 트리 구성법이나 규칙 학습법과 다른 새로운 개념 표현 기법을 소개하고자 한다. 우리의 PROLEARN 알고리즘은 각 클래스로부터 주어진 예제를 가장 잘 설명할 수 있는 가상 예제, 즉, 프로토타입을 하나 이상 학습하고 이것을 마치 주어진 예제처럼 취급하여 일반적인 개체 중심 학습법처럼 분류하도록 한다. 우리의 프로토타입 개념은 인지 심리학에서 사용한 같은 용어와는 하나의 개념이 하나 이상의 프로토타입을 가질 수 있도록 한 점에서 다르며 학습된 프로토타입은 근본적으로 ‘가상 예제’라는 점에서 다른 개체 중심 학습법과 다르다. 실험 결과 이 알고리즘은 정확도에서 다른 알고리즘에 뒤지지 않으며 실제 학습 문제에서 자주 발생하는 불안정성 문제, 즉 훈련 예제 집합이 바뀌면 알고리즘의 정확도도 영향 받는 부분도 해소하였다.