• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.9
• /
• pp.77-81
• /
• 2016

Logistic regression (LR) has been widely used for predicting the relationships among variables in various fields. We propose a new logistic regression model with a fine-grained weighting method, called value weighted logistic regression, by assigning different weights to each feature value. A gradient approach is utilized to obtain the optimal weights of feature values. We conduct experiments on several data sets and the experimental results show that the proposed method shows meaningful improvement in prediction accuracy.

• The Korean Journal of Applied Statistics
• /
• v.19 no.1
• /
• pp.43-55
• /
• 2006

CS(Customer Satisfaction) has been focused as one of the most important factors in business administration nowadays. After measuring and evaluating CS level, most companies are performing many activities to improve it. Therefore, it is very important for driving CS management to measure the exact CS level. When measuring CS level, however, CSI(Customer Satisfaction Index) is changed by the computing method of importance for CS factors, and the corporate strategy is changed by CSI. In this research, some computing methods are reviewed and compared through the analysis of real data. Also, a hybrid computing method for CSI is proposed and compared it with other methods.

• Journal of Digital Contents Society
• /
• v.17 no.2
• /
• pp.81-88
• /
• 2016

The general frequent pattern mining considers frequency and support of items. To extract useful information, it is necessary to consider frequency and weight of items that reflects the changing of user interest as time passes. The suitable services considering time or location is requested by user so that the weighted mining method is necessary. We propose a method of weighted frequent pattern mining based on service ontology. The weight considering time and location is given to service items and it is applied to association rule mining method. The extracted rule is combined with stored service rule and it is based on timely service to offer for user.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.583-583
• /
• 2016

다양한 평가지표가 반영된 복합 지수(Composite Index)는 물관리 정책의 우선순위 결정 및 정책성과의 모니터링에 유용한 도구로 사용되고 있다. 각 지표별 중요도를 나타내는 가중치는 최종 지수의 산정에 영향을 미칠 수 있으며, 그 결정방법도 Data Envelopment Analysis(DEA), Benefit of doubt Approach(BOD), Unobserved Component Model(UCM), Budget Allocation Process(BAP), Analytic Hierarchy Process(AHP), Conjoint Analysis(CA) 등 다양하다. 본 연구에서는 여러 가지 가중치 결정방법 중 통계적 방법인 주성분 분석(Principal Component Analysis, PCA)을 사용하여 Park et al.(2016)이 제시한 물관리 탄력성 지수(Water Management Resilience Index, WMRI)에 대한 가중치를 산정하여 동일 가중치를 적용한 기존 결과와 비교하였다. 물관리 탄력성 지수는 자연조건상 물관리 취약성(Vulnerability), 기존 수자원 인프라의 견고성(Robustness), 물위기 적응전략의 다양성(Redundancy)의 3가지 부지수(sub-index)는 각각 13개, 11개, 7개의 지표(Indicator)로 구성되어 있으며, 117개 중권역을 다목적댐 하류 본류유역(범주 1), 용수공급 및 유량조절이 불가능한 지류(범주 2)와 가능한 지류(범주 3)로 분류하여 적용되었다. 각 부지수별로 추출된 3개, 5개, 3개의 주성분이 전체 자료의 76.4%, 71.2%, 63.2%를 설명하는 것으로 분석되었으며 부지수별 주성분의 고유벡터(Eigenvector)와 고유값(Eigenvalue)를 계산하고 각 지표의 가중치를 산정하였다. 주성분 분석에 의한 가중치와 동일 가중치를 적용하였을 경우와 비교해보면 취약성 부지수 1.9%, 견고성 부지수 1.9%, 다양성 부지수 2.1%의 차이가 나타나며 물관리 탄력성 지수는 0.4%의 차이를 보임에 따라 Park et al.이 제시한 연구결과의 적정성을 확인할 수 있었다. 주성분 분석은 객관적인 가중치 설정을 위한 통계적 접근방법의 하나로써 다양한 물관리 정책지수 산정시 활용될 수 있을 것이며, 향후 다른 가중치 산정방법을 적용함으로써 각 방법에 따른 지수 결과의 민감도 및 장단점을 분석할 수 있을 것으로 판단된다.

• Journal of Korea Water Resources Association
• /
• v.37 no.8
• /
• pp.663-674
• /
• 2004

In this study, the principle of water allocation is proposed based on efficiency, equity, sustainability. Also weighting factors are estimated with sectoral factors and regional factors. The former represents relative weights among water use and the latter represents physical characteristics of water demand places. The AHP(Analytic Hierarchy Process) is applied to estimate the sectoral factors, and compounded regional-characteristic factors and regional-scale factors, which reflects socioeconomic statistics for the regional factors. By applying these weighting factors, water allocation rules for dam is developed and applied to Andong dam which supplies water to parts of Busan Shi, Daegu Shi and Goryeong Gun in a water-deficit situation. As a result, it is estimated that Water allocation by priorities distributes the entire water shortage to the lowest rank of water sectors or regions, while water allocation by relative weighting factors disperse all the burdens of water shortage to all sectors and regions.

• Journal of Korea Port Economic Association
• /
• v.27 no.3
• /
• pp.273-288
• /
• 2011

Recently, the rankings of Korean container ports in terms of container handling cargo volume were plunged down due to the emerging Chinese ports. The efficient container ports strategies which increase container port competitiveness were requested. In this respect, it is urgently required to draw out constituent factors for Port Logistics, weigh these factors, and finally focus on improving the suggested factors. The aim of this paper is to evaluate weight and priority values for 'inner consisted factors' and 'outer requested factors' of port logistics by using the AHP(Analytic Hierarchy Process) method. As for the analysis regarding the inner consisted factors, the results were shown as follows: a storage and handling system (0.288) as the first rank; an information system of port logistics (0.210) as the second rank; an inland intermodal system (0.189) as the third rank; a ship's entering and departuring system (0.184) as the fourth rank, and a ship's berthing system (0.129) as the fifth rank. In terms of analysis regarding outer requested factors, the results came out as follows: a logistics cost (0.360) as the first rank; a port service (0.128) as the second rank; a connectivity (0.118) as the third rank; a hinterland condition (0.116) as the fourth rank; an convenience (0.106) as the fifth rank; a regional center (0.095) as the sixth rank, and an availability (0.077) as the seventh rank. For analyzing the priorities changes in constituent factors, the comparison of results between the year 2007 and the year 2011 was done. As the results, among inner consisted factors, 'information system of port logistics' was ranked first in the year 2007 while 'a storage and handling system' became the most important factor in the year 2011. Among the inner consisted factors, however, the logistics cost was the important factor in 2007 and 2011, respectively.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.361-361
• /
• 2021

가뭄의 경우 타 자연재난에 비해 발생경로, 피해범위, 발생기간 등이 매우 다양해 다각적인 측면에서의 대응책 마련이 필요하다. 따라서, 극한가뭄에 대비한 지자체별 가뭄 역량 평가를 수행하는 것은 재난관리에 있어서 최우선이라고 할 수 있다. 현재 국내외적으로 가뭄과 관련된 지역적 복원력을 평가한 사례는 매우 적다. 가뭄은 지진, 홍수 등과 같은 타 자연재난에 비하여 지속기간이 길고, 그 지속기간에 따라 피해의 영향 또한 파급력이 달라지므로 복원력 산정을 위한 항목, 복원력 곡선의 저하 형태 및 양상 역시 가뭄의 특성에 맞춰 도출되어야 한다. 본 연구에서는 지자체별 극한가뭄에 대한 복원력 정량화를 위하여 가뭄과 관련된 내구성, 대체성, 신속성, 자원동원력의 세부인자를 정성인자와 정량인자로 구분하여 총 18개 항목으로 구성하였다. 구성된 18가지 항목이 정량인자 뿐만 아니라 정성인자로 구성됨에 따라, 모든 인자를 동일한 가중치로 평가할 경우 최종결과가 상대적 중요도의 미 고려로 인해 왜곡될 가능성이 존재한다. 따라서 계층적분석기법(AHP, Analytic Hierarchy Process)을 통해 내구성, 대체성, 신속성, 그리고 자원동원력에 대한 가중치와 내구성, 대체성, 그리고 신속성에 대한 세부 지표별 가중치를 도출하여 지역별 메가가뭄 복원력을 정량화 하였다. 분석결과를 동일한 가중치를 적용한 결과와 비교분석하였으며, 과거 가뭄사례를 통해 검토하였다.

• Culinary science and hospitality research
• /
• v.22 no.4
• /
• pp.81-94
• /
• 2016

The purpose of this study is to measure the relative importance of the factors that affect school to work transition that food service-related majors and workers recognize. To this end, this study composed such factors into a second hierarchy level of individual background, educational background, and preparation effort to enter labor market. The study made us of the analytic hierarchy process(AHP), which calculates the importance of each factor through the relative evaluation of each factor in the hierarchy. The results of analysis are as follows. First, in the second hierarchy level, effort to enter the labor market exhibited the highest relative importance. In the case of four-year college students, educational background had the highest relative importance. Second, in case of third hierarchy level factors relating to personal background, gender had the highest relative importance. As for educational background, the type of college had the highest relative importance. As to the effort to enter labor market, overseas working experience while in college and job searching channels had high relative importance, while vocational training experience had the lowest relative importance. Third, the analysis result of complex weighted value showed that the type of college had the highest complex weighted value. In future studies, the type of businesses and business conditions in the food service industry should be subdivided for an analysis of influential factors, and, based on this, customized career guidance should be made for specific career paths of each student.

• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1349-1360
• /
• 2015

In order to improve software quality, it is necessary to efficiently and effectively remove software defects in source codes. In the development field, defects are removed according to removal ratio or severity of defects. There are several studies on the removal of defects based on software quality attributes, and several other studies have been done to improve the software quality using classification of the severity of defects, when working on projects. These studies have thus far been insufficient in terms of identifying if there exists relationships between defects or whether any type of defect is more important than others. Therefore, in this study, we collected various types of software defects, standards organization, companies, and researchers. We modeled the defects types using an ANP model, and developed the weighted severities of the defects types, with respect to the general application software, using the ANP model. When general application software is developed, we will be able to use the weight for each severity of defect type, and we expect to be able to remove defects efficiently and effectively.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.34 no.2
• /
• pp.115-136
• /
• 2023

The purpose of this study is to establish a weighting system for the diagnostic criteria of the KISTI Open Access Maturity Model. The maturity model consists of three dimensions, 12 sub-dimensions, and 28 measurement questions. Weighting was performed for the three dimensions and 12 sub-dimensions to determine their relative importance. The results showed that 'Institutionalization of OA' (48%) was the most important factor in the three dimensions. Among the sub-factors of "institutionalizing OA," "enacting and revising relevant regulations" (64%) was important, and "financing" (39%) was important for "OA sustainability. Submission and review (23%) and author rights (22%) were identified as important elements of "journal openness".