• 전기학회논문지
• /
• 제57권6호
• /
• pp.1058-1062
• /
• 2008

In clinical decision support system(CDSS), unlike rule-based expert method, appropriate data-driven machine learning method can easily provide the information of individual feature(clinical test) for disease classification. However, currently developed methods focus on the improvement of the classification accuracy for diagnosis. With the analysis of feature importance in classification, one may infer the novel clinical test sets which highly differentiate the specific diseases or disease states. In this background, we introduce a novel CDSS that integrate a classifier and feature selection module together. Random forest algorithm is applied for the classifier and the feature importance measure. The system selects the significant clinical tests discriminating the diseases by examining the classification error during backward elimination of the features. The superior performance of random forest algorithm in clinical classification was assessed against artificial neural network and decision tree algorithm by using breast cancer, diabetes and heart disease data in UCI Machine Learning Repository. The test with the same data sets shows that the proposed system can successfully select the significant clinical test set for each disease.

• 대한인간공학회지
• /
• 제36권4호
• /
• pp.325-341
• /
• 2017

Objective: The purpose of this study is to suggest the guidelines of operation phases to minimize injuries and musculoskeletal disorders in manual material handling (MMH) tasks through literature reviews. The guidelines are presented as the preparing phase, lifting phase, carrying phase, and lowering phase. Also, we summarized the non-numerical general guidelines for MMH tasks. Background: Manual material handling is still a main cause to musculoskeletal disorders. Method: Procedures of a literature review are classified into database selection, keyword search, title review, abstract review related to literature selection, guideline review and arrangement. A total 48 papers and books were analyzed in detail by title and abstract reviews. Results: In the preparing phase, we suggested the basic conditions in MMH, preparing procedure, clothing and protective equipment, and education. In the lifting and carrying phases, we recommended maximal acceptable weight by frequency and body posture. In the lowering phase, we suggested the lowest weight and safety body postures. Finally, we recommended general guidelines and guideline items for MMH. General guidelines are presented to suggest worker selection, technical education, and work design parts. Conclusion: We suggested the guidelines on the four operation phases of MMH tasks such as preparing, lifting, carrying, and lowering phases. Application: The findings of this study can be utilized as guidelines for proactive recommendations according to workers in MMH tasks.

• 한국지하수토양환경학회지:지하수토양환경
• /
• 제18권2호
• /
• pp.19-26
• /
• 2013

This study developed the classification of National Soil Quality Monitoring Network (NSQM) and its site selection criteria to meet the recently established purposes of the NSQM. The NSQM were suggested by this study to classify into the six-purposes site groups from the current classification of land uses. The six purposes site groups were 1) intensive observation sites, 2) contaminant loading sites, 3) human activity sites, 4) background sites, 5) river soil sites, and 6) sites near the groundwater quality monitoring wells. Furthermore, this study developed the site selection criteria of NSQM utilizing the accumulated NSQM data, road traffic data, chemical emission data, census, soil information, and the literature related to soil quality variation due to contaminant loads. For selecting suitable sites for NSQM, this study used road traffic, chemical emission, the distance from the contaminant sources, and population information as specific criteria. The suggested site classification and criteria were appled for the current 100 NSQM sites for evaluation. Forty sites were met to the criteria suggested by this study, but sixty sites were not met to the criteria. However, some of the sixty sites also included the obscure sites that their addresses were not apparent to find them.

• 한국병원경영학회지
• /
• 제10권3호
• /
• pp.1-24
• /
• 2005

This study purports to investigate the determinants of individual personnel rating of the employees at a university hospital in Seoul, Korea. The sample used in this study consisted of 63 nurses, 41 para-medical staff (Clinical Pathologist, and Radiologist), and 67 administrative staff. Independent variables of the study included the achievement level of the selection test (English, major subject, and interview), post-entrance development factors (education and training, career development, supervisory support, co-worker support, and organizational support), and demographic characteristics. Data for the achievement level of the entrance exam and years for the first promotion were collected from the administrative records of the study hospital, while data for the post-entrance development factors were collected from the survey with self-administered questionnaires using 5-point Likert Scale during June 10-25, 2003. Collected data were analyzed using hierarchical multiple regression. The results of the study showed that achievement level of the interview and English exam at the selection test, education and training, organizational support, and supervisory support while working at the hospital, and length of duration (below 8 years) and educational background (4-year college graduates) among demographic variables had significant positive effects on the personnel rating. The results of the study imply that hospital administrators should make an effort to improve the validity of the selection test, and to motivate the employees to receive more education and training.

• 천문학회보
• /
• 제38권1호
• /
• pp.66.2-66.2
• /
• 2013

In this study, we present a pore-selection technique to estimate the size of pore. The estimation of the size of pore is important to examine the temporal evolution of size itself and corresponding intensity. The size of pore is typically estimated by applying the intensity threshold technique to the fixed box which contains the entire pore. The typical method has disadvantages in the following circumstances; there are small features near the pore or the image has low spatial resolution. In the former, it is difficult to define a box containing the pore only, excluding the small features near the pore. In the latter, the background and threshold intensity are insignificant due to the insufficient number of pixel in the box. To avoid these difficulties, we use a pore-selection technique which is simply based on the measurement of distances from the pore center. In addition, we will discuss the advantage of the technique for the imaging spectrograph data like the NST FISS.

• 정보관리학회지
• /
• 제21권2호
• /
• pp.45-67
• /
• 2004

본 연구는 인쇄잡지 중심의 소장 패러다임 대 전자잡지 위주의 접근 패러다임이 대립하는 상황에서 대학도서관의 하이브리드형 학술지 수집정책의 이론적 토대가 되는 평가요소를 분석하여 한국적 실정을 고려한 외국 학술지의 평가모형 개발에 필요한 기초자료를 마련하는데 그 목적이 있다. 구체적으로 질문지법을 통하여 학술지 수집규모 상위 40개 대학도서관의 외국학술지 선정과정에서 예비평가지표(인쇄형 27개, 전자형 37개)의 적용도를 조사하고, 그 데이터를 다양한 통계적기법으로 분석하였다. 인쇄학술지 평가지표의 요인별 상대적 중요성은 응답 평균값으로 산출하였는데 그 결과는 학과당 구독종수, 이용도, 선정권한, 전자학술지 구독조건, ISI 영향지수, 국제성과 지명도, 구독가격, ILL/DDS 수장공간 순으로 나타났다. 한편, 전자학술지는 구독가격, 접근성, 전자학술지 구독조건, 컨소시엄, 선정권한, 접근확장성, 학과당 구독종수, 대학의 학문적 특성, ISI 영향지수, ILL/DDS 국제성과 지명도 순으로 나타났다.

• Archives of Plastic Surgery
• /
• 제44권5호
• /
• pp.428-433
• /
• 2017

Background Candidate characteristics for hand surgery fellowship training remains unknown, as very little data is available in the literature. This study aims to provide information on the criteria that are employed to select candidates for the hand surgery fellowship match. Methods A 38-question survey was sent in April 2015 to all Accreditation Council for Graduate Medical Education recognized hand surgery fellowship program directors (n=81) involved in the U.S. match. The survey investigated factors used for the selection of applicants, including medical school, residency training, research experience, fellowship interview, and candidate characteristics. A 5-point Likert scale was used to grade 33 factors from "not at all important" (1) to "essential in making my decision" (5); or for five controversial factors from "very negative impact" (1) to "very positive impact in making my decision" (5). Results A total of 52% (42 out of 81) of responses were received from hand surgery fellowship program directors. The most important influential factors were interactions with faculty during interview and visit ($4.6{\pm}0.6$), interpersonal skills ($4.6{\pm}0.5$), overall interview performance in the selection process ($4.6{\pm}0.6$), professionalism and ethics ($4.6{\pm}0.7$), and letters of recommendation from hand surgeons ($4.5{\pm}0.7$). Factors that have a negative impact on the selection process include visa requirement ($2.1{\pm}1.2$), graduate of non-plastic surgery residency program ($2.4{\pm}1.3$), and graduate of a foreign medical school ($2.4{\pm}1.1$). Conclusions This study provides data on hand surgery fellowship directors' perception on the criteria important for fellowship applicant selection, and showed that interview-related criteria and letters of recommendation are the important factors.

• Journal of Ecology and Environment
• /
• 제38권1호
• /
• pp.119-122
• /
• 2015

It is very useful and important to see the status and change of necessary parts in a short period through selecting and observing the bioindicator continually to forecast and prepare the future. Especially, living things are so closely related to the environment that the indicator between the environment and living things shows close interrelationship. Also, the indicator related to environment provides information about representative or decisive environmental phenomenon and is used to simplify complicated facts. Considering wide range of background and application including various indicators such as the change-, destruction-, pollution-, and restoration of habitats, climate change, and species diversity, the closest category includes "environmental indicator," "ecological indicator," and "biodiversity indicator." The selection and use of bioindicator is complicated and difficult. The necessary conditions for the indicator selection are flexible and greatly depend on the goals of investigation such as the indicator for biological diversity investigation of specific area, the indicator for habitat destruction, the indicator for climate change, and the indicator for polluted area. It should meet many various conditions to select a good indicator. In this study, eleven selection standards are established based on domestic and overseas studies on bioindicator selection: species with clear classification and ecology, species distributed in geographically widespread area, species that show clear habitat characteristics, species that can provide early warning for a change, species that are easy and economically benefited for the investigation, species that have many independent individual groups and that is not greatly affected by the size of individual groups, species that is thought to represent the response of other species, species that represent the ecology change caused by the pressure of human influence, species for which researches on climate change have been done, species that is easy to observe, appears for a long time and forms a group with many individuals, and species that are important socially, economically, and culturally.

• 한국멀티미디어학회논문지
• /
• 제7권7호
• /
• pp.877-885
• /
• 2004

본 논문은 여러 가지 장면 검출 방식들 중 강인한 특징 변수들의 선별과 신경망을 이용하여 향상된 장면 전환점 검출 기법을 제안한다. 기존의 장면 전환점 검출 방식에서는 인접한 프레임 간에 단일 특징과 고정된 임계값을 주로 사용하였다. 하지만, 비디오 시퀀스 내의 장면 전환점에서는 인접한 프레임 간의 내용(content)인 컬러, 모양, 배경 혹은 질감 등이 동시에 변화한다. 따라서 단일 특징보다는 상호 보완 관계를 갖는 강인한 특징을 이용하여 장면 전환점을 효율적으로 검출한다. 본 논문에서 강인한 특징 변수들을 선택하기 위해, 데이터 마이닝 기법 중 대표적인 CART(classification and regression tree)를 이용하고, 다차원 변수에 따른 임계값을 선정하기 위해 역전파 신경망(backpropagation neural net)을 이용한다. 제안한 방식과 대표적인 특징 추출인 PCA(principal component analysis)기법을 비교하여 특징 변수의 추출 성능을 평가한다. 실험 결과에 따라 제안된 방식이 PCA 기법과 비교하여 우수한 성능이 나타남을 확인한다.

• 대한간호학회지
• /
• 제37권3호
• /
• pp.414-421
• /
• 2007

Background: Nursing intervention studies often suffer from a selection bias introduced by failure of random assignment. Evaluation with selection bias could under or over-estimate any intervention's effects. PS matching (PSM) can reduce a selection bias through matching similar Propensity Scores (PS). PS is defined as the conditional probability of being treated given the individual's covariates and it can be reused to balance the covariates of two groups. Purpose: This study was done to assess the significance of PSM as an alternative evaluation method of nursing interventions. Method: An intervention study for patients with some baseline individual characteristic differences between two groups was used for this demonstration. The result of a t-test with PSM was compared with a t-test without matching. Results: The level of HbA1c at 12 months after baseline was different between the two groups in terms of matching or not. Conclusion: This study demonstrated the effects of a quasi-random assignment. Evaluation using PSM can reduce a selection bias impact that affects the result of the nursing intervention. Analyzing nursing research more objectively to reduce selection bias using PSM is needed.