• 융합정보논문지
• /
• 제11권6호
• /
• pp.49-54
• /
• 2021

최근 스마트 헬스케어 기술의 발전에 따라 일상적인 질환에 대한 관심이 증가하고 있다. 이에 따라 헬스케어 데이터를 통해 예측 모델로 질병을 분석하거나 예측하는 연구들이 증가하고 있다. 그러나 헬스케어 데이터에는 양성 데이터와 음성 데이터의 불균형이 존재한다. 이는 특정 질환을 가진 환자에 비하여 상대적으로 환자가 아닌 사람이 많아 데이터 수집에 어려움이 있어 발생하는 현상이다. 데이터 불균형은 질병 예측 및 탐지 시 진행하는 모델의 성능에 영향을 끼치기 때문에 이를 제거할 필요가 있다. 따라서 본 연구에서는 오버샘플링과 결측값 대치를 통해서 데이터 불균형을 해소한다. AutoML을 기반으로 여러 모델의 성능을 파악하고 모델 중 상위 3개의 모델을 앙상블한다.

• 한국인터넷방송통신학회논문지
• /
• 제19권6호
• /
• pp.227-233
• /
• 2019

최근 딥러닝 기술의 발달과 함께 신경 네트워크는 컴퓨터 비전에서도 성공을 거두고 있다. 컨볼루션 신경망은 단순한 영상 분류 작업뿐만 아니라 객체 분할 및 검출 등 난이도가 높은 작업에서도 탁월한 성능을 보였다. 그러나 그러한 많은 심층 학습 모델은 지도학습에 기초하고 있으며, 이는 이미지 라벨보다 주석 라벨이 더 많이 필요하다. 특히 semantic segmentation 모델은 훈련을 위해 픽셀 수준의 주석을 필요로 하는데, 이는 매우 중요하다. 이 논문은 이러한 문제를 해결하기 위한 네트워크 훈련을 위해 영상 수준 라벨만 필요한 약지도 semantic segmentation 방법을 제안한다. 기존의 약지도학습 방법은 대상의 특정 영역만 탐지하는 데 한계가 있다. 반면에, 본 논문에서는 우리의 모델이 사물의 더 다른 부분을 인식하도 multi-classifier 심층 학습 아키텍처를 사용한다. 제안된 방법은 VOC 2012 검증 데이터 세트를 사용하여 평가한다.

• 정보처리학회논문지D
• /
• 제16D권5호
• /
• pp.643-650
• /
• 2009

생명정보 대량 획득기술의 하나인 마이크로어레이(microarray)는 DNA와 각종 유전자 연구에 사용되는 도구로 확립되면서, 생명정보학(Bioinformatics)분야의 발전에 크게 기여하였다. 그러나 마이크로어레이는 생명정보학분야의 핵심기술 중 하나로 발전하였음에도 불구하고 실험으로 생성되는 데이터는 형태가 다양하고 매우 복잡한 형태를 갖기 때문에 데이터의 공유나 저장에서 많은 어려움을 겪고 있다. 본 논문에서는 마이크로어레이 데이터의 관리를 원활하게 하기위한 XML 기반의 표준 포맷인 MAGE-ML스키마에서 구조적으로 유사한 엘리먼트가 반복적으로 나타나는 특징과 대다수의 엘리먼트들이 특정 엘리먼트의 자식으로만 온다는 구조적 특징을 이용하여, MAGE-ML의 스키마를 단순화 하고 저장구조를 효율적으로 설계하는 방법을 제안한다. 이 방법에서 인라인 기법(Inlining Technique)을 이용한 스키마의 단순화와 새롭게 제시하는 엘리먼트의 구조적 형태를 기준으로 분류하는 기법을 이용한다. 이를 통하여 데이터베이스 스키마는 간략화 되며 테이블조인의 횟수가 줄어들고 성능은 향상된다.

• 지능정보연구
• /
• 제27권3호
• /
• pp.139-156
• /
• 2021

이미지 분류에서 딥러닝 모형을 사용하는 가장 큰 이유는 이미지의 전체적인 정보에서 각 지역 특징을 추출하여 서로의 관계를 고려할 수 있기 때문이다. 하지만 이미지의 지역 특징이 없는 감정 이미지 데이터는 CNN 모델이 적합하지 않을 수 있다. 이러한 감정 이미지 분류의 어려움을 해결하기 위하여 매년 많은 연구자들이 감정 이미지에 적합한 CNN기반 아키텍처를 제시하고 있다. 색깔과 사람 감정간의 관계에 대한 연구들도 수행되었으며, 색깔에 따라 다른 감정이 유도된다는 결과들이 도출되었다. 딥러닝을 활용한 연구에서도 색깔정보를 활용하여 이미지 감성분류에 적용하는 연구들이 있어왔으며, 이미지만을 가지고 분류 모형을 학습한 경우보다 이미지의 색깔 정보를 추가로 활용한 경우가 이미지 감성 분류 정확도를 더 높일 수 있었다. 본 연구는 사람이 이미지의 감정을 분류하는 기준 중 많은 부분을 차지하는 색감을 이용하여 이미지 감성 분류 정확도를 향상시키는 방안을 제안한다. 이미지의 RGB 값에 K 평균 군집화 방안을 적용하여 이미지를 대표하는 색을 추출하여, 각 감성 클래스 별 해당 색깔이 나올 확률을 가중치 식으로 변형 후 CNN 모델의 최종 Layer에 적용하는 이-단계 학습방안을 구현하였다. 이미지 데이터는 6가지 감정으로 분류되는 Emotion6와 8가지 감정으로 분류되는 Artphoto를 사용하였다. 학습에 사용한 CNN 모델은 Densenet169, Mnasnet, Resnet101, Resnet152, Vgg19를 사용하였으며, 성능 평가는 5겹 교차검증으로 CNN 모델에 이-단계 학습 방안을 적용하여 전후 성과를 비교하였다. CNN 아키텍처만을 활용한 경우보다 색 속성에서 추출한 정보를 함께 사용하였을 때 더 좋은 분류 정확도를 보였다.

• Asia pacific journal of information systems
• /
• 제19권2호
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.

• 지능정보연구
• /
• 제27권1호
• /
• pp.23-46
• /
• 2021

개인화 추천에서 많이 사용되는 협업 필터링은 고객들의 구매이력을 기반으로 유사고객을 찾아 상품을 추천할 수 있는 매우 유용한 기법으로 인식되고 있다. 그러나, 전통적인 협업 필터링 기법은 사용자 간에 직접적인 연결과 공통적인 특징을 기반으로 유사도를 계산하는 방식으로 인해 신규 고객 혹은 상품에 대해 유사도를 계산하기 힘들다는 문제가 제기되어 왔다. 이를 극복하기 위하여, 다른 기법을 함께 사용하는 하이브리드 기법이 고안되기도 하였다. 이런 노력의 하나로서, 사회연결망의 구조적 특성을 적용하여 이런 문제를 해결하려는 시도가 있었다. 이는, 직접적으로 유사성을 찾기 힘든 사용자 간에도 둘 사이에 놓인 유사한 사용자 또는 사용자들을 통해 유추해내는 방식으로 상호 간의 유사성을 계산하는 방식을 적용한 것이다. 즉, 구매 데이터를 기반으로 사용자의 네트워크를 생성하고 이 네트워크 내에서 두 사용자를 간접적으로 이어주는 네트워크의 특성을 기반으로 둘 사이의 유사도를 계산하는 것이다. 이렇게 얻은 유사도는 추천대상 고객이 상품의 추천에 대한 수락여부를 결정하는 척도로 활용될 수 있다. 서로 다른 중심성 척도는 추천성과에 미치는 영향이 서로 다를 수 있다는 점에서 중요한 의미를 갖는다 할 수 있다. 이런 유사도의 계산을 위해서 네트워크의 중심성을 활용할 수 있다. 본 연구에서는 여기서 더 나아가 이런 중심성이 추천성과에 미치는 영향이 추천 알고리즘에 따라서도 다를 수 있다는 데에서 주목하여 수행되었다. 또한, 이런 네트워크 분석을 활용한 추천기법은 신규 고객 혹은 상품뿐만 아니라 전체 고객 혹은 상품으로 그 대상을 넓히더라도 추천 성능을 높이는 데 기여할 것을 기대할 수 있을 것이다. 이런 관점에서 본 연구는 네트워크 모형에서 연결선이 생성되는 것을 이진 분류의 문제로 보고, 추천 모형에 적용할 분류 기법으로 의사결정나무, K-최근접이웃법, 로지스틱 회귀분석, 인공신경망, 서포트 벡터 머신을 선택하고, 온라인 쇼핑몰에서 4년2개월간 수집된 구매 데이터로 실험을 진행하였다. 사회연결망에서 측정된 중심성 척도를 각 분류 기법에 적용하여 생성한 모형을 비교 실험한 결과, 각 모형 별로 중심성 척도의 추천성공률이 서로 다르게 나타남을 확인할 수 있었다.

• 지역사회간호학회지
• /
• 제12권1호
• /
• pp.278-287
• /
• 2001

The purpose of this study is to provide with basic information on application of hand acupuncture as a complementary and alternative therapy by giving some recognition of efficiency and effectiveness of hand acupuncture. And so, answers for questionnaires of 290 respondents were used for this research and collected from June 5 through 13, 1999 from adults twenty and over who were participating in the hand acupuncture training program in Seoul and had some direct experiences with hand acupuncture therapy, whatever they had been treated and/or had treated. To secure reliability of measurement tool. Cronbach'a has been calculated and Factor Analysis was done as Validity Analysis of question classification. Demograprucal characteristics of hand acupuncture experienced people and factors related to hand acupuncture experiences are calculated based on the real number and percentage. The degree of recognition of efficiency and effectiveness of hand acupuncture is made as average and standard deviation, while the degree of recognition of efficiency and effectiveness based on general characteristics come from one-way ANOVA. 1. According to socio-demographical analysis. the questioned could be classified firstly as age (40-49 : 32.5%. 30-39 : 24.9%. 50-59 : 21.9%. 60-69 : 14.7%. 20-29 : 6.0%). secondly gender (male 36.6%. female 63.4%). thirdly occupation (housewife: 43.8%. self-employed: 15.5%. company-employee: 14.8%). fourthly education (high school graduate: 41.9%, college graduate: 37.9%), and lastly monthly-income (1 to 2 million: 51.4%. 2 to 3 million: 20,3%) 2, As for the general aspects related to hand acupuncture. 80,0% of the respondents answered almost zero for the monthly average number of visit to hospital and 15.5% responded 1 to 2 visits, 6,2% of the respondents is complaining of a disorder of digestive system. 19,0% circulatory disease, 10.7% bad nervous system. By utilizing hand acupuncture, 84% of the questioned have following experiences in curing diseases: digestive system 47.3%, circulatory system 9.3%, nervous system 8.3%, 54,1% are curing 1 to 2 and 10.3% 3 to 4 patients on a daily basis with hand acupuncture. Research on the demerits of giving medical treatment with hand acupuncture shows 23,8% are feeling economic burden. 16.6% difficulty of learning and 16.2% weak theoretical backgrounds. 3. Among the efficiency recognition, possibility of general application is average 4,29 and simple treatment is 4,19. economic merits 4.36. possibility of establishment with supplementary and alternative medicine 4.17, medical effectiveness 4.09. 4, As a result of demographical analysis on the efficiency and effectiveness of hand acupuncture therapy, it appears that the recognition of efficiency based on occupation and the recognition of effectiveness based on monthly income are most significant to be noticed. In an orderly fashion. government-employee, self-employed, company-employee. and then housewife have perceived hand acupuncture very efficiently, And those who recognize hand acupuncture to be most effective are people earn 1 million to 2 million won a month, 5. The efficiency(p = .003) and effectiveness (p= .049) of hand acupuncture therapy by number of visit to hospital were statiscally significant, and effectiveness of hand acupuncture therapy by disease exist was statiscally significant (p= .033).

• Journal of Nutrition and Health
• /
• 제41권4호
• /
• pp.307-316
• /
• 2008

The purpose of the study was to investigate nutritional status of chronic obstructive pulmonary disease (COPD) patients and to find out the differences according to the stages of disease. From March to October, 2006, 41 stable male patients of mild to severe COPD patients were recruited from Seoul National University hospital. The patients' of body weight and fat free mass were assessed by bioelectrical impedance analysis. The nutritional status of the patients was also assessed by 3-day recall, index of nutritional quality (INQ), dietary diversity score (DDS), dietary variety score (DVS), food group index pattern and dietary quality index (DQI). The total of 41 patients were classified into three groups, stage I, stage II and stage III groups according to the classification of Global Initiative for Chronic Obstructive Lung Disease (GOLD) standard. The mean age of the patients in each stage were 67.2-66.9 years showing no significant difference. The ratio of $FEV_1$/FVC were $57.5{\pm}7.3$, $46.9{\pm}7.6$ and $38.2{\pm}6.8%$, respectively showing significant differences according to the stages of disease. The fat free mass of the stage II ($48.2{\pm}4.7kg$) and III ($47.3{\pm}4.5kg$) was significantly lower than that of stage I ($53.1{\pm}6.9kg$) patients. There were significant correlation of fat free mass with $FEV_{1}$, and BMI (body mass index) with $FEV_{1}$/FVC ratio (p < 0.05). COPD patients showed the diet-related clinical symptoms of anorexia, dyspnea, dyspepsia, and chewing difficulty. Daily intakes of calorie, K, vitamin $B_2$ and folate of the patients were very low ($83.8{\pm}20.7%$, $58.9{\pm}14.4%$, $70.7{\pm}19.6%$ and $74.4{\pm}10.2%$, respectively) however, they did not significantly different according to the stages of disease. Daily intake of calcium was significantly lower in the stage III patients (p < 0.05). The mean scores of dietary variety score was significantly lower in the stage III patients (p < 0.001). Dietary quality index of the patients were not different among the stages of disease and the scores indicated poor quality of diet. As a summary, we found that body fat free mass, regularity of exercise, frequency of having snacks and dietary variety score were significantly associated with the severity of chronic obstructive pulmonary disease.

• 한국학교보건학회지
• /
• 제16권1호
• /
• pp.9-21
• /
• 2003

The present study was designed to evaluate the factors influential on stress and subjective fatigue symptoms based on school life environments and daily life styles among high school students. The self-administered questionnaires were delivered to 2,381 high school students of both sexes in Taejon Metropolitan city during the period from Mar. 1st to Jun. 30th, 2000. The analysis of study results revealed the following findings: 1. According to the magnitude of stress, the normal subjects were 3.1%, the groups with potential stress were 64.7%, and the groups at high risk for stress were 32.2%. Higher level of stress existed in the female than the male students, and in the third grader than the 1st and 2nd graders. According to the classification of typical constitutional symptoms of fatigue, category III (group with bodily projection of fatigue) was the most frequent and it was followed by category II (group with difficulty in concentration) and category I (group with dullness and sleepiness) in a decreasing order of frequency, which showed that the predominant pattern of fatigue arose from the body parts. 2. With regard to the school life characteristics and stress scores, the higher scores of stress were shown in the groups with the lower grades, with worse friend's relation and with the lower satisfaction with the school life. The scores for the subjective fatigue symptoms were higher in the male, in the low graders, in the better friend's relation, and in the satisfactory group than the respective counterparts. 3. Concerning home life characteristics, the higher scores of stress were associated with the students characterized by the recognized poor economic conditions, lower interests of parents, lack of satisfaction with the home life, the poor subjective health status. On the other hand, the scores for the subjective fatigue symptoms were higher in the student groups with good economic conditions, higher interests of parents, presence of satisfaction with the home life, and good subjective health status. 4. Concerning daily life styles, the higher scores of stress were in the students who had inappropriate sleep hours, skipped breakfasts, daily consumption of intermeal snacks, lack of exercise, daily smoking, normal indices of obesity, and lower indices of health habit. Conversely, the scores of subjective fatigue symptoms were higher in the groups who had daily breakfasts, no intermeal snacks, daily exercise, no smoking than their counterparts. 5. The factors exerting influence upon the stress included the satisfaction with school life, friend's relation, satisfaction with the home life, exercise, school grades, interests of parents, school year, sex, scores of health habit, degree of obesity, economic conditions of home. Those influencing on the degree os stress included stress, intermeal snacks, smoking, friend's relation and satisfaction with the home life.

• Journal of Oral Medicine and Pain
• /
• 제20권1호
• /
• pp.39-52
• /
• 1995

Burning mouth syndrome is characterized by a burning sensation in oral cavity without clinical signs. There has b een no established theories about the diagnosis and treatment. The purpose of this article is to examine the clinical feature of BMS patients of Korean and to present a treatment protocol that can be helpful in clinical applications. The subjects chosen for the study were 52 patients who had visited Department of Oral Diagnosis at Yonsei University Dental Hospital and were diagnosed as BMS. We did questionnaires and precise oral exam, laboratory exam, grouping of our patients, individual treatment for the groups and classification of responses to the treatment. The following results were obtained: 1. Chief complaints were throbbing (71.2%), pricking, stinging, tingling (30.8%), burning(25a%). The tongue is the most frequently affected site (82.7%), followed by full mouth, gingiva, palate, buccal mucosa, lips, throat, labial mucosa and floor of mouth. 2. The average age of onset was 48.1 year and the male to female ratio was 1 to 3. The average duration of symptom was 11.69 months for male and 23.07 months for female. 3. 32.7% of patients had appealed continuous pain, which was the most cases. Aggravating factors were peppery food, salty food, hot food, fatigue, tension conversation, sour food, cold food and toothpaste. Reducing factors were cold food, diet, going to sleep and smoking. 4. Associated symptoms were dry mouth, other life problem, altered taste perception, bad taste, throat pain, tingle and difficulty in swallowing. 5. Most of patients had appealed that there was not associated event on onset of symptom, and the order of prevalence is as fallow; dental treatment, stress, denture wearing, an attack of a systemic disease. 92.3% of patient appealed that there was no psychological withering and 7.7% of patients appealed positively. 6. There were eight males and four females that had jobs. 7. There was no family history in 100% of patients in questions about presence of family history. 8. 96.2% of patients appealed that there was no oral habits. 13.5% of patients had dryness of oral mucosa in oral exam. A significant relation to dental prosthesis was not observable, but incidence of diseases due to stress appeared high in BMS which had the clinical characteristics as above. A group having low serum iron was 63.5% and in this group period of potential iron deficiency appeared high in incidence just before move to anemia. A group represented positive response was 38.5% in fungus study for Candida albicans. Since we can expect high treatment response by prescription of iron-contained drug and antifungal drug in these patients, diagnosing patients' condition of BMS can be achieved in more various aspects through study for serum iron and Candida albicans. Furthermore, it is expected that treatment protocol can be made.