• Animal Systematics, Evolution and Diversity
• /
• 제29권2호
• /
• pp.136-143
• /
• 2013

The collared scops owl that occurs in Korea is a protected species but its exact specific status has been questioned. To resolve the species status, a molecular phylogenetic analysis was conducted using two fragments of mitochondrial DNA, cytochrome b (cyt b, 891 bp) and NADH dehydrogenase subunit 2 (ND2, 627 bp) genes. Phylogenetic trees of cyt b revealed that all Korean specimens formed a monophyletic group with Japanese scops owl Otus semitorques with very low sequence divergence (d=0.008). We obtained a similar ND2 tree as well (d=0.003); however, the genetic distance between Korean individuals and O. lempiji from GenBank (AJ004026-7, EU348987, and EU601036) was very high and sufficient enough to separate them as species (cyt b, d=0.118; ND2, d=0.113). We also found that Korean species showed high differentiation from O. bakkamoena (AJ004018-20 and EU601034; cyt b, d=0.106; ND2, d=0.113) and O. lettia (EU601109 and EU601033, cyt b, d=0.110; ND2, d=0.117) as well. Therefore, we suggest that the Korean collared scops owl should be designated as Otus semitorques.

• 대한지역사회영양학회지
• /
• 제19권5호
• /
• pp.468-478
• /
• 2014

Objectives: Intake of fruits and vegetables has protective effects against stroke attack. This study intended to examine the status of consuming fruits and vegetables and to find out which factors may influence the frequency of consumption of fruits and vegetables in individuals with a history of stroke. Methods: The data of 208 subjects from 5th (2010, 2011) Korea National Health and Nutrition Examination Survey (KNHNES) who reported a stroke diagnosis was used for analysis. To identify major factors influencing the consumption of fruits and vegetables, a classification-tree analysis was carried out. Results: Among those who reported a stroke diagnosis, the frequencies of consumption of fruits and vegetables were influenced by their age, place of residence (urban or rural), economic status, educational level, occupation, number of family members, frequency of eating out, and having meals (breakfast or lunch) with family members. Two factors from fruits and three factors from vegetables were generated by exploratory factor analyses. Urban residents ate fruits and vegetables more frequently in all factors than rural residents. Eating frequencies of 'seasonal fruits (orange, apple, strawberry, melon, pear and watermelon)', 'easily-accessible fruits (persimmon, tangerine, grape, peach, banana)', and 'Western-style vegetables (cabbage, mushroom, carrot, tomato, spinach)' were influenced by the socioeconomic status. Eating frequencies of 'Korean-style vegetables (bean sprout, radish leaves, pumpkin/squash, sea weed)', 'preserved vegetables (Korean cabbage, radish, laver, cucumber)' were influenced by having breakfast with family members. Conclusions: The results of this study suggested that by eating more fruits and vegetables, more preventive effects against secondary stroke attack are expected in stroke patients who live in the rural areas and who do not eat breakfast with family members. In addition, more outreach and education programs are needed for them.

• Neurospine
• /
• 제15권4호
• /
• pp.329-337
• /
• 2018

Objective: Machine learning algorithms excel at leveraging big data to identify complex patterns that can be used to aid in clinical decision-making. The objective of this study is to demonstrate the performance of machine learning models in predicting postoperative complications following anterior cervical discectomy and fusion (ACDF). Methods: Artificial neural network (ANN), logistic regression (LR), support vector machine (SVM), and random forest decision tree (RF) models were trained on a multicenter data set of patients undergoing ACDF to predict surgical complications based on readily available patient data. Following training, these models were compared to the predictive capability of American Society of Anesthesiologists (ASA) physical status classification. Results: A total of 20,879 patients were identified as having undergone ACDF. Following exclusion criteria, patients were divided into 14,615 patients for training and 6,264 for testing data sets. ANN and LR consistently outperformed ASA physical status classification in predicting every complication (p < 0.05). The ANN outperformed LR in predicting venous thromboembolism, wound complication, and mortality (p < 0.05). The SVM and RF models were no better than random chance at predicting any of the postoperative complications (p < 0.05). Conclusion: ANN and LR algorithms outperform ASA physical status classification for predicting individual postoperative complications. Additionally, neural networks have greater sensitivity than LR when predicting mortality and wound complications. With the growing size of medical data, the training of machine learning on these large datasets promises to improve risk prognostication, with the ability of continuously learning making them excellent tools in complex clinical scenarios.

• 한국학교보건학회지
• /
• 제19권1호
• /
• pp.79-88
• /
• 2006

Purpose : To identify general characteristics of school personnel with recent fatigue which was the most frequent symptom among subjective symptoms and to explore fatigue-related factors by evaluating physical and perceived health status, life style, and symptoms through data mining techniques. Methods : We collected a data of the 1,147(male 545, female 602) who were elementary, middle, or high school personnel, answered a questionnaire, and received physical examination in Seoul School Health Center from September to November in 2000. And we investigated the differences between fatigue group and non-fatigue group for demographic characteristics, physical health status, perceived health status, symptoms, and laboratory values by frequency, chi-square test, t-test, or simple logistic regression analysis by SAS package 8.1, and then selected significant variables as input variables of a decision tree analysis of CART model by SAS E-miner. Results : In general characteristics, the fatigue consisted of 41.1%(male 35.2%, female 46.4%) among 1,147 school personnel. In classical statistics, factors related with fatigue were female, lower means of systolic and diastolic pressure, young age, personnel in middle school, irregular eating habit, no exercise a week or less than 30minutes exercise a day, perception of unhealthy status, and subjective symptoms including short of breath at exercise. In simple logistic regression to examine the relationship between selected independent variables and fatigue as a dependent variable, the odds ratio of gender (female vs male) was 1.58 times, and young age ( 20s vs 60s) 20.67 times, and middle vs high school personnel 1.86 times. However, we mined combined several characteristics by SAS-E miner. In CART model, if health perception was healthy, and age was >= 37.5 years, the proportion of the fatigue was only 19.3%. but if health perception was not healthy and symptom was severe 'short of breath' during exercise and age was < 53.5 years, and BMI was >= 22.69, the proportion of the fatigue was up to 84.8%. Conclusions : The fatigue consisted of 41.1%(male 35.2%, female 46.4%). In classical statistics, fatigue-related factors among school personnel were young age, female gender, perceived unhealthy status, subjective physical symptoms, poor life-style, and lower blood pressure rather than only physical health status. However, in data mining, if health perception was healthy and age was >= 37.5 years, the proportion of the fatigue was only 19.3%. but if health perception was not healthy and symptom was severe 'short of breath' during exercise and age was < 53.5 years, and BMI was >= 22.69, the proportion of the fatigue was up to 84.8%.

• 한국콘텐츠학회논문지
• /
• 제18권5호
• /
• pp.265-279
• /
• 2018

본 연구에서는 데이터 마이닝 기법을 활용하여 근로자의 이직준비 여부에 관한 예측모형을 구축하는 실험을 진행하였다. 이를 위해, 한국고용정보원 주관으로 수집된 "2015년 대졸자 직업 이동경로조사" 데이터를 사용하였다. 이직준비 여부 예측모형에는 의사결정나무, 베이즈넷, 인공신경망 알고리즘이 사용되었다. 전체 직종을 대상으로 한 분석에서는 의사결정나무 기반 예측모형에서 최고 예측률을 기록하였으며, 이직준비 여부에 영향을 주는 요인은 '근로시간 형태', '종사상 지위', '정규직 여부', '주당 정규 근로시간', '주당 정규 근로일', '개인의 발전가능성'으로 나타났다. 의사결정나무 기반 예측모형의 결과를 활용하여 근로자 전반에 관한 12개의 이직준비 여부 규칙을 최종 도출하였고, 도출된 규칙을 바탕으로 근로자의 고용유지 강화에 도움을 주는 방안들을 제안하였다. 또한 직종별 영향 요인을 분석하기 위해 직종을 사무, 문화예술, 건설, 정보기술 분야로 구분하여 실험을 진행하였다. 그 결과 사무 분야는 10개, 문화예술 분야는 9개, 건설 분야는 4개, 그리고 정보기술 분야는 6개의 이직준비 규칙이 도출되었고 이를 토대로 직종별 맞춤화된 고용유지 강화 방안을 제시하였다.

• 디지털융복합연구
• /
• 제16권7호
• /
• pp.63-69
• /
• 2018

본 연구는 6차 년도 국민노후보장패널조사 자료를 활용하여 노인빈곤에 영향을 미치는 원인을 규명하고자 한다. 이에 본 연구에서는 성별, 연령, 교육수준, 건강상태와 같은 노인의 개인적 특성, 거주지역, 가족 구성 형태와 같은 노인가구의 특성, 근로소득 유무, 임금근로자 여부와 같은 노인 근로적 특성, 그리고 공적연금수급 여부, 사적연금수급 여부, 사회보장급여수급 여부, 부동산 소득 여부, 개인연금형태 수입 여부와 같은 은퇴 후 근로 외의 발생소득 특성을 노인빈곤 변인으로 선정하였다. 본 연구는 6차 년도 조사대상 5,254가구 중 65세 이상 그리고 노인가구를 분류한 후 결측값이 포함된 것을 제외한 총 3,418명이 분석에 활용하였다. 의사결정나무분석 결과, 노인빈곤에 영향을 미치는 가장 중요한 변인은 근로소득 유무로 나타났다. 근로소득이 없는 빈곤노인의 경우 공적연금수급 여부, 교육수준, 거주지역이 그리고 근로소득이 있는 빈곤노인의 경우 임금근로자 여부와 성별이 빈곤에 영향을 미치는 변인으로 확인되었다. 이런 분석결과를 토대로, 노인빈곤을 해소하기 위한 방안으로 Senior re-employment 노동환경 조성, 무료 직업교육 프로그램 개발 제공, 공적연금 수급 확대 및 미래연금수급 안전성 보장 및 강화 차원의 현행 연금제도 개선 필요성, 여성 노인 우선적 고용 및 임금근로 조건에 의한 노인 고용 업체 인센티브 제공 등을 제안하였다.

• 지능정보연구
• /
• 제24권2호
• /
• pp.111-124
• /
• 2018

본 연구는 만성질환 중의 하나인 고지혈증 유병을 예측하는 분류모형을 개발하고자 한다. 이를 위해 SVM과 meta-learning 알고리즘을 이용하여 성과를 비교하였다. 또한 각 알고리즘에서 성과를 향상시키기 위해 변수선정 방법을 통해 유의한 변수만을 선정하여 투입하여 분석하였고 이 결과 역시 각각 성과를 비교하였다. 본 연구목적을 달성하기 위해 한국의료패널 2012년 자료를 이용하였고, 변수 선정을 위해 세 가지 방법을 사용하였다. 먼저 단계적 회귀분석(stepwise regression)을 실시하였다. 둘째, 의사결정나무(decision tree) 알고리즘을 사용하였다. 마지막으로 유전자 알고리즘을 사용하여 변수를 선정하였다. 한편, 이렇게 선정된 변수를 기준으로 SVM, meta-learning 알고리즘 등을 이용하여 고지혈증 환자분류 예측모형을 비교하였고, TP rate, precision 등을 사용하여 분류 성과를 비교분석하였다. 이에 대한 분석결과는 다음과 같다. 첫째, 모든 변수를 투입하여 분류한 결과 SVM의 정확도는 88.4%, 인공신경망의 정확도는 86.7%로 SVM의 정확도가 좀 더 높았다. 둘째, stepwise를 통해 선정된 변수만을 투입하여 분류한 결과 전체 변수를 투입하였을 때보다 각각 정확도가 약간 높았다. 셋째, 의사결정나무에 의해 선정된 변수 3개만을 투입하였을 때 인공신경망의 정확도가 SVM보다 높았다. 유전자 알고리즘을 통해 선정된 변수를 투입하여 분류한 결과 SVM은 88.5%, 인공신경망은 87.9%의 분류 정확도를 보여 주었다. 마지막으로, 본 연구에서 제안하는 meta-learning 알고리즘인 스태킹(stacking)을 적용한 결과로서, SVM과 MLP의 예측결과를 메타 분류기인 SVM의 입력변수로 사용하여 예측한 결과, 고지혈증 분류 정확도가 meta-learning 알고리즘 중에서는 가장 높은 것으로 나타났다.

• Journal of Information Processing Systems
• /
• 제11권2호
• /
• pp.165-172
• /
• 2015

The inactive student rate is becoming a major problem in most open universities worldwide. In Indonesia, roughly 36% of students were found to be inactive, in 2005. Data mining had been successfully employed to solve problems in many domains, such as for educational purposes. We are proposing a method for preventing inactive students by mining knowledge from student record systems with several state of the art ensemble methods, such as Bagging, AdaBoost, Random Subspace, Random Forest, and Rotation Forest. The most influential attributes, as well as demographic attributes (marital status and employment), were successfully obtained which were affecting student of being inactive. The complexity and accuracy of classification techniques were also compared and the experimental results show that Rotation Forest, with decision tree as the base-classifier, denotes the best performance compared to other classifiers.

• Communications for Statistical Applications and Methods
• /
• 제10권2호
• /
• pp.575-583
• /
• 2003

We proposed imputation strategies for the Population and Housing Census 2000 in Korea. The total area of floor space and marital status which have relatively high non-response rates in the Census are considered to develope the effective missing value imputation procedures. The Classification and Regression Tree(CART) is employed to construct the imputation cells for hot-deck imputation, as well as to predict missing value by model-based approach. We compare three imputation methods which include CART model-based imputation, hot-deck imputation based on CART and logical hot-deck imputation proposed by The Korea National Statistical Office. The results suggest that the proposed hot-deck imputation based on CART is very efficient and strongly recommendable.

• Biotechnology and Bioprocess Engineering:BBE
• /
• 제7권4호
• /
• pp.185-193
• /
• 2002

With Increasing awareness towards environment-friendly and non-toxic pesticide azadirachtin obtained from neon tree (Azadirachta indica) is gaining more and more importance. Its broad-spectrum activity, Peculiar mode of action. eco-friendly and non-toxic action towards beneficial organisms has offered many advantages over chemical pesticides. All currently use commercial formulations based on azadirachtin contains azadirachtin extracted from seeds of naturally grown whole plants which is labour intensive process depending upon many uncontrollable geographical and climatic factors. Plant tissue culture can be a potential process for the pro-duction, offering consistent, stable and controlled supply of this bioactive compound, However the research on tissue culture aspects of production are in preliminary stage and requires culture and process optimization for the development of a commercially viable process. This review states the present status and future challenges of plant tissue culture for azadirachtin production.