• 한국수정란이식학회지
• /
• 제27권1호
• /
• pp.37-43
• /
• 2012

This study evaluated a method of sorting X and Y chromosomes based on size using the forward angle light scatter related refractive index (FSC) of a flow cytometer. Hanwoo bulls sperm were separated to X and Y chromosomes by the parameters of FSC or Hoechst 33342 intensity. As a result, using monitor program linked flow cytometry during sorting processing, the purities were $97{\pm}0.57$ or $96{\pm}0.67%$ for the X-fraction and $96{\pm}0.33$ or $97{\pm}1.33%$ for the Y-fraction in the two sperm sorting methods. There were no differences in the X and Y ratios (X and Y %) between the sperm sorting methods based on FSC or DNA content. The proportions of female and male embryos used for in vitro fertilization and development were $66.03{\pm}3.31$ or $69.37{\pm}1.41%$, and $70.56{\pm}2.42$ or $56.11{\pm}3.09%$ when sperm were processed using the sex sorting method by FSC or Hoechst 33342. In conclusion, further study is needed to determine the optimum procedure and improve the nozzle to enhancing sorting accuracy or efficiency. Also, the findings of this study do not negate the possibility that the difference method of sperm sorting cannot use a UV laser beam.

• 한국문헌정보학회지
• /
• 제39권2호
• /
• pp.123-146
• /
• 2005

이 연구에서는 문서 자동분류에서 분류자질 선정과 가중치 할당을 위해서 일관된 전략을 채택하여 kNN 분류기의 성능을 향상시킬 수 있는 방안을 모색하였다. 문서 자동 분류에서 분류자질 선정 방식과 자질 가중치 할당 방식은 자동분류 알고리즘과 함께 분류성능을 좌우하는 중요한 요소이다. 기존 연구에서는 이 두 방식을 결정할 때 상반된 전략을 사용해왔다. 이 연구에서는 색인파일 저장공간과 실행시간에 따른 분류성능을 기준으로 분류자질 선정 결과를 평가해서 기존 연구와 다른 결과를 얻었다. 상호정보량과 같은 저빈도 자질 선호 기준이나 심지어는 역문헌빈도를 이용해서 분류 자질을 선정하는 것이 kNN 분류기의 분류 효과와 효율 면에서 바람직한 것으로 나타났다. 자질 선정기준으로 저빈도 자질 선호 척도를 자질 선정 및 자질 가중치 할당에 일관되게 이용한 결과 분류성능의 저하 없이 kNN 분류기의 처리 속도를 약 3배에서 5배정도 향상시킬 수 있었다.

• 한국건설관리학회논문집
• /
• 제8권6호
• /
• pp.246-262
• /
• 2007

The performance of projects has always been an area of interest in the construction industry. Roles of all construction supply chain partners are necessary; however the role of a contractor firm in the construction project is pivotal. So, this research intended to explore a Construction Firm's performance criteria which could measure the level of performance of that firm in an ongoing project. Data was collected from construction professionals working in three principal project participant organizations, namely Owner, Consultant and Contractor. A total of 113 nos. of performance measuring items were sorted from literature review and used to collect data. Statistical tools processed by SPSS program was employed to analyze the data. Out of total 113 items, only 65 nos. of variables were found to be acceptable to every population group of this study. Factor analysis revealed 12 key performance predicting factors (KPPF) with 53 predictive indicators. 12 KPPFS with index weight are: work progress and smoothening (9.3%), change order management and work accuracy (9.1%), business relationship building (8.1%), adequacy of construction work procedure (8.6%), quality performance (8.0%), health and site safety adequacy (8.8%), Innovative contractor (8.0%), adequacy of construction site information (6.8%), compliance with contract plan/specification requirements (8.9%), creditworthiness and financial capability (8.3%), intra-agency relationship and responsiveness (7.0%) and resource management (9.2%). These results could be useful to project management body to evaluate performance of its contractor firm on site as well as the contractor itself to assess own performance and its subcontractors on-site.

• 천문학회지
• /
• 제45권2호
• /
• pp.31-38
• /
• 2012

In this study we apply Support Vector Machine (SVM) to the prediction of geo-effective halo coronal mass ejections (CMEs). The SVM, which is one of machine learning algorithms, is used for the purpose of classification and regression analysis. We use halo and partial halo CMEs from January 1996 to April 2010 in the SOHO/LASCO CME Catalog for training and prediction. And we also use their associated X-ray flare classes to identify front-side halo CMEs (stronger than B1 class), and the Dst index to determine geo-effective halo CMEs (stronger than -50 nT). The combinations of the speed and the angular width of CMEs, and their associated X-ray classes are used for input features of the SVM. We make an attempt to find the best model by using cross-validation which is processed by changing kernel functions of the SVM and their parameters. As a result we obtain statistical parameters for the best model by using the speed of CME and its associated X-ray flare class as input features of the SVM: Accuracy=0.66, PODy=0.76, PODn=0.49, FAR=0.72, Bias=1.06, CSI=0.59, TSS=0.25. The performance of the statistical parameters by applying the SVM is much better than those from the simple classifications based on constant classifiers.

• 융합신호처리학회논문지
• /
• 제20권4호
• /
• pp.226-231
• /
• 2019

한방 설진에서 WTCI(Winkel Tongue Coating Index) 설태 평가는 환자의 설태량 측정을 위한 중요한 객관적인 지표 중의 하나이다. 그러나 이전의 WTCI 설태 평가는 혀영상으로부터 설태 부분을 추출하여 전체 혀 영역에서 추출된 설태 영역의 비율을 정량적으로 측정하는 방법이 대부분으로 혀영상의 촬영 조건이나 설태 인식 성능에 의해서 비객관적 측정의 문제점이 있었다. 따라서 본 논문에서는 빅데이터를 기반으로 하는 인공지능의 딥러닝 방법을 적용하여 설태량을 분류하여 평가하는 딥러닝 기반의 WTCI 평가 방법을 제안하고 검증한다. 설태 평가 방법에 있어서 딥러닝의 유효성 검증을 위해서는 CNN을 학습 모델로 사용하여 소태, 박태, 후태의 3가지 유형의 설태량을 분류한다. 설태 샘플 영상을 학습 및 검증 데이터로 구축하여 CNN 기반의 딥러닝 모델로 학습한 결과 96.7%의 설태량 분류 정확성을 보였다.

• 농업과학연구
• /
• 제39권2호
• /
• pp.227-242
• /
• 2012

Accurate estimation of milk production cost is very important for dairy farmers in establishing strategies for business management (e.g. planning a program for milk production, deciding the size of business and investment, determining the milk price for sale). Since the estimated cost of milk production is used as an important index to determine the basal price of milk in Korea, there has been much interest and debate on the method used to estimate milk production cost among the stakeholder. This study was thus carried out to identify problems in the current methodology for estimating cost of milk production, and to find a better way to improve it. We propose several alternatives and better ways to improve the current method for estimating cost of milk production. Estimation of the income and cost per head should be based on the number of cattle converted to grown cows. Cost estimation per liter of milk should be made for both whole milk and 3.4% milk fat corrected milk. The value of purchased cows and raised replacement heifers should be the same as their market value. The productive life span of cows should be less 4 years, and the terminal or salvage value of cows needs to be 30 to 40% less than her initial value. When calculating depreciation of cows over the productive life span, however, the salvage value should be 0 or 1 Korean won. On calculating labor costs, the farm labor wage corresponding to the average wage of nonfarm industrial workers should be assumed. Beside of these, better estimation procedures for other items are also given. The proposed methods from this study should improve the accuracy of estimation of milk production cost and help to achieve consensus among the stakeholder.

• Safety and Health at Work
• /
• 제5권2호
• /
• pp.80-85
• /
• 2014

Background: Currently available questionnaires for evaluating the quality of worklife do not fully examine every factor related to worklife in all cultures. A tool in Thai is therefore needed for the direct evaluation of the quality of worklife. Our aim was to translate the Work-related Quality of Life Scale-2 (WRQLS-2) into Thai, to assess the validity and reliability of the Thai-translated version, and to examine the tool's accuracy vis-$\grave{a}$-vis nursing in Thailand. Methods: This was a descriptive correlation study. Forward and backward translations were performed to develop a Thai version of the WRQLS. Six nursing experts participated in assessing content validity and 374 registered nurses (RNs) participated in its testing. After a 2-week interval, 67 RNs were retested. Structural validity was examined using principal components analysis. The Cronbach's alpha values were calculated. The respective independent sample t test and intraclass correlation coefficient were used to analyze known-group validity and test-retest reliability. Multistate sampling was used to select 374 RNs from the In- and Outpatient Department of Srinagarind Hospital of the Khon Kaen University (Khon Kaen, Thailand). Results: The content validity index of the scale was 0.97. Principal components analysis resulted in a seven-factor model, which explains 59% of the total variance. The overall Cronbach's alpha value was 0.925, whereas the subscales ranged between 0.67 and 0.82. In the assessment results, the known-group validity was established for the difference between civil servants and university employees [F (7.982, 0.005) and t (3.351; p < 0.05)]. Civil servants apparently had a better quality worklife, compared to university employees. Good test-retest reliability was observed (r = 0.892, p < 0.05). Conclusion: The Thai version of a WRQLS appears to be well validated and practicable for determining the quality of the work-life among nurses in Thailand.

• 대기
• /
• 제27권2호
• /
• pp.189-197
• /
• 2017

Progressing from weather forecasts and warnings to multi-hazard impact-based forecast and warning services represents a paradigm shift in service delivery. Urban flooding is a typical meteorological disaster. This study proposes support plan for urban flooding impact-based forecast by providing inundation risk matrix. To achieve this goal, we first configured storm sewer management model (SWMM) to analyze 1D pipe networks and then grid based inundation analysis model (GIAM) to analyze 2D inundation depth over the Gangnam drainage area with $7.4km^2$. The accuracy of the simulated inundation results for heavy rainfall in 2010 and 2011 are 0.61 and 0.57 in POD index, respectively. 20 inundation scenarios responding on rainfall scenarios with 10~200 mm interval are produced for 60 and 120 minutes of rainfall duration. When the inundation damage thresholds are defined as pre-occurrence stage, occurrence stage to $0.01km^2$, 0.01 to $0.1km^2$, and $0.1km^2$ or more in area with a depth of 0.5 m or more, rainfall thresholds responding on each inundation damage threshold results in: 0 to 20 mm, 20 to 50 mm, 50 to 80 mm, and 80 mm or more in the rainfall duration 60 minutes and 0 to 30 mm, 30 to 70 mm, 70 to 110 mm, and 110 mm or more in the rainfall duration 120 minutes. Rainfall thresholds as a trigger of urban inundation damage can be used to form an inundation risk matrix. It is expected to be used for urban flood impact forecasting.

• 기술혁신학회지
• /
• 제21권2호
• /
• pp.818-837
• /
• 2018

기술혁신에는 본질적인 어려움이 따르는데, 이는 상당부분 기술이 지닌 불확실성에 기인한다. 따라서 혁신과정에서 불확실성에 따른 위험을 감소시키기 위한 예측 방법론은 정량적 분야와 정성적 분야 모두에서 제시되어 왔다. 한편 최근 빅 데이터와 인공지능에 큰 관심이 이어지며 특히 알파고의 알고리즘 중 하나인 딥 러닝이 뛰어난 성능을 보이고 있다. 이에 본 연구는 혁신성과 예측에 있어 딥 러닝을 이용한 방법론을 접목하여 연구를 진행하였다. 모델 구축 및 학습에 있어 KIS 2016 데이터를 이용하였으며, 투입 요인으로는 정보 원천의 사용도와 혁신 목적을 사용하였고 산출 요인으로는 혁신 성과 지표를 구성하여 사용하였다. 분석 결과 선행 연구들에 비해 예측의 정확도가 향상되었음을 확인할 수 있었다. 또한 학습이 진행됨에 따라 예측의 자유도 역시 향상됨을 확인하였다.

• International Journal of Control, Automation, and Systems
• /
• 제2권4호
• /
• pp.423-434
• /
• 2004

In this paper, we introduce a new topology of Self-Organizing Polynomial Neural Networks (SOPNN) based on genetically optimized Multi-Layer Perceptron (MLP) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. Let us recall that the design of the 'conventional' SOPNN uses the extended Group Method of Data Handling (GMDH) technique to exploit polynomials as well as to consider a fixed number of input nodes at polynomial neurons (or nodes) located in each layer. However, this design process does not guarantee that the conventional SOPNN generated through learning results in optimal network architecture. The design procedure applied in the construction of each layer of the SOPNN deals with its structural optimization involving the selection of preferred nodes (or PNs) with specific local characteristics (such as the number of input variables, the order of the polynomials, and input variables) and addresses specific aspects of parametric optimization. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between the approximation and generalization (predictive) abilities of the model. To evaluate the performance of the GA-based SOPNN, the model is experimented using pH neutralization process data as well as sewage treatment process data. A comparative analysis indicates that the proposed SOPNN is the model having higher accuracy as well as more superb predictive capability than other intelligent models presented previously.reviously.