This study attempts a comparison between AHP(Analytic Hierarchy Process) in which the importance weight is structured by individual subjective values and regression model with importance weight based on statistical theory in determining the importance weight of casual model. The casual model is designed by for students’ satisfaction with university, and SERVQUAL modeling methodology is applied to derive factors affecting students’ satisfaction with university. By comparison of importance weights for regression model and AHP, the following characteristics are observed. 1) the lower the degree of satisfaction of the factor, the higher the importance weight of AHP, 2) the importance weight of AHP has tendency to decrease as the standard deviation(or p-value) increases. degree of decreases. the second sampling is conducted to double-check the above observations. This study empirically checks that the importance weight of AHP has a relationship with the mean and standard deviation(or p-value) of independence variables, but can not reveal how exactly the relationship is. Further research is needed to clarify the relationship with long-term perspective.

Deep learning, which has recently shown excellent performance, has a problem that the amount of computation and required memory are large. Model compression is very useful because it saves memory and reduces storage size while maintaining model performance. Model compression methods reduce the number of edges by pruning weights that are deemed unnecessary in the calculation. Existing weight pruning methods using ADMM construct an optimization problem by a layer-by-layer addition of pre-defined removal-ratio constraints. Decomposing into two subproblems through the ADMM process, one can solve them through gradient descent and projection. However, the layer-by-layer removal ratios must be structurally specified, causing a sharp increase in training time due to a large number of parameters, and hardly feasible to use for large models that actually require weight pruning. Our proposed method performs weight pruning, producing similar performance, by setting a global removal ratio for the entire model without prior knowledge of structural characteristics in order to solve the shortcomings of the existing ADMM weight-pruning methods. To effectively avoid performance degradation, the method removes a relatively small number of previous layers in charge of feature extraction. Experiments show high-quality performance, not necessarily setting layer-by-layer removal ratios. Additionally, experiments increasing layers yield an insight for feature extraction in pruned layers. The experiment of the proposed method to the LeNet-5 model using MNIST data results in a higher compression ratio of 99.3% outperforming those of other existing algorithms. We also demonstrate the effectiveness of the proposed method in YOLOv4, an object detection model requiring substantial computation.

The 37 indicators for performance evaluation of public sewage management agencies are divided into four major categories (agency manpower management ability, wastewater treatment plant operation and management, sludge and water reuse, service quality) in the first stage, and the necessity and score acquisition for the detailed indicators by each major category in the second stages. Priority was investigated through the Analytic Hierarchy Process (AHP) analysis technique for ease and relevance of company efforts. Also, based on the results of this analysis, integrated type weighting and relative importance were analyzed. As a result of the analysis, the weight and relative importance of the first stage classification were in the order of wastewater treatment plant operation and maintenance, operation agency manpower management ability, sludge and water reuse, and service quality. As a result of analyzing the weights and priorities of the detailed performance indicators in the second stage, it was found that operator’s career years, the percentage of certification holding rate in operators, compliance with the effluent water quality standards, training times for operators, and efforts to manage hazardous chemicals were important. Some of the indicators of operation agency performance evaluation may include indicators in which the performance of the company's efforts is underestimated or overestimated. In order to improve this, it is necessary to give weights in consideration of the necessity of the indicator, the relevance of the company's efforts, and the ease of obtaining scores.

본 연구는 태백산국립공원 백두대간 생태축 연결을 위한 평가항목 및 요인별 가중치 설정을 위해 공원관리와 생태계 조사, 생태환경계획과 관련된 분야별 전문가 대상의 설문조사를 토대로 계층화 분석을 실시하였다. 문헌연구와 담당자 면담조사로 생태축 연결을 위한 상위 평가지표 4개와 하위 평가지표 13개를 선정하였으며, 일관성 분석에 의한 유효 설문을 대상으로 항목별 가중치를 산정하였다. 분석결과, 상위평가 지표에서는 생태계 가치증진이 0.474로 가장 높고, 자연-인간 갈등완화(0.247), 지역주민의 참여(0.165), 경제적 측면(0.114) 순으로 나타났으며, 하위 평가지표에서는 생물이동경로(0.116), 경관생태적 패치 연결성(0.112), 기능적 서식지(0.099) 등이 중요 항목으로 추출되었다. 분야별 평가항목과 가중치 비교에 따르면 생태계조사 분야에서는 생물종 이동경로(0.116)을 가장 중시하는 반면, 공원관리 분야에서는 기능적 서식지가 0.110로 가장 중요한 항목으로 평가되었으며, 생태환경계획 분야에서는 지역의 보전 및 이용자원 분포현황이 0.123으로 가장 높게 나타났다. 본 연구결과는 태백산국립공원 일대의 생태축 연결에 필요한 조사항목의 선정이나 분야별 연결성 분석방향 설정에 기여할 것이다.

베어링은 많은 회전체에서 사용되는 핵심부품으로, 예기치 않은 고장을 방지하기 위해 많은 연구가 집중되고 있다. 이때 중요한 것은 되도록 초기에 건전성 상태를 잘 나타내는 적절한 특징신호를 추출하는 것이다. 그러나 기존의 연구들은 주로 진단관점에서 특징신호를 추출하여 고장예지에는 적합하지 않은 측면이 있었다. 본 논문에서는 이러한 문제를 극복하기 위 해 베어링 고장 주파수의 에너지와 시간 사이의 상관계수 가중 합을 이용하여 베어링 수명 예측에 용이한 특징신호를 추출 하는 방법을 개발하였다. 그 결과 일반적으로 고장진단에서 많이 사용되고 있는 특징신호인 RMS에 비해서 결함 초기부터 단조로운 증가 경향의 특징신호를 추출함을 알 수 있었다. 이를 입증하기 위해서 NASA Ames에서 제공한 IMS bearing 진 동 데이터를 이용하였고 제시한 특징신호와 일반적인 RMS와 의 거동을 비교하여 유효성을 검증하였다.

PURPOSES: The purpose of this study is to analyze the characteristics of the weight values of evaluation items by traffic safety project type. METHODS: In general, a large-scale investment in projects such as the traffic safety project requires economic analyses to be performed in advance. However, there is an argument for considering special characteristics of the traffic safety project. Therefore, this study conducted characteristic analysis of the weight values of evaluation items. The analysis consisted of two steps. The first step was hypothesis verification using analysis of variance (ANOVA). In this process, the authors examined whether the weight of evaluation items is the same regardless of the traffic safety project type. Based on the first step's results, the authors proceeded to the second step. The objective of this step was to analyze how different the weight values are by traffic safety project type using an analytic hierarchy process. RESULTS: According to the ANOVA test results, the benefit to cost ratios have different weight values based on traffic safety project type at the 0.01 significance level. The policy evaluation items, such as the plans connection, resident opinion, and regional equity, also showed the same results except that the result for the related plans connection was statistically significant at the 0.05 level. Based on the first step's result, the AHP analysis in the second step showed that the traffic safety projects for vulnerable users and pedestrians have very low weight values in economic evaluation factors compared with other safety project types. The weight values for vulnerable users and pedestrians were 0.29 and 0.26, respectively, in economic evaluation items. On the other hand, the weight values for other safety project types were around 0.6. Among the policy evaluation items, resident opinion showed a higher weight value than other factors, such as connection and regional equity items. CONCLUSIONS: The social and economic impact of a traffic safety project varies by project type and project characteristics. Although the economic approach is overarching and a reasonable methodology is applied for large-scale projects, it should be noted that the safety issue, especially for transportation of vulnerable uses, requires a non-economical approach. Based on the analysis results, this study suggests that the priority of the projects should be determined by separating them into independent assessment groups depending on their characteristics.

PURPOSES: This study aims to develop a rational procedure for estimating the pavement roughness index considering vehicle wandering. METHODS: The location analysis of the passing vehicle in the lane was performed by approximately 1.2 million vehicles for verification of the wandering distribution. According to verification result, the distribution follows the normal distribution pattern. The probability density function was estimated using each lane's wandering distribution model. Then the procedure for applying a weighted value into the lane profile was conducted using this function. RESULTS : The modified index, MRIw, with consideration towards applying the wandering weighted value application was computed then compared with MRI. It was found that the Coefficient of Variation for distribution of lateral roughness index in the lane was high in the case of a large difference between each index (i.e., MRIw and MRI) observed. CONCLUSIONS : This result confirms that the new procedure with consideration of the weight factor can successfully improve the lane representative characteristics of the roughness index.

본 연구는 한우 능력검정체계에 이용되는 선발형질에 따른 부분육 중량 및 수율의 간접선발반응을 파 악하고 부분육 형질을 선발형질로 포함하였을 경우 선호부위의 유전적 개량량 변화를 파악하기 위하여 시뮬레이션 프로그램인 ZPLAN+를 이용하였다. 분석에 이용한 자료는 1996년도부터 2013년까지 농협 중앙회 한우개량사업소, 도 축산연구센터, 국립축산과학원, 한우육종농가에서 당·후대 검정한 한우 수 소 및 거세우 총 10,351두의 자료를 이용하였다. 그 결과 후보 및 보증씨수소 선발가중치와 동일조건 하에서 등심단면적의 가중치를 각각 1, 3, 6으로 하였을 때 등심수율의 연간 유전적 개량량은 각각 0.222%, 0.282%, 0.328%로 증가하는 결과를 보였다. 현재 선발가중치와 동일한 조건에서 부분육 형질 을 선발형질로 포함하여 등심수율에만 가중치를 주었을 경우 갈비, 채끝수율은 등심수율과 함께 증가하 는 것으로 나타났으나 안심수율의 연간 유전적 개량량의 변화는 미미하였다. 또한 안심, 등심, 채끝 등 의 선호부위에 8가지의 경우의 수(가중치: 1 또는 2)로 그룹별 가중치를 주었을 경우, 가중치가 각각 2:2:2인 그룹에서 선호부위의 연간 유전적 개량량이 가장 높았다. 따라서 선호되는 부위의 생산량 증대 를 위해서는 이들 부위에 상대적으로 높은 가중치를 동일하게 적용하는 것이 한우의 선발에 효과적인 방법이라 사료된다.

Two key challenges in statistical relational learning are uncertainty and complexity. Standard frameworks for handling uncertainty are probability and first-order logic respectively. A Markov logic network (MLN) is a first-order knowledge base with weights attached to each formula and is suitable for classification of dataset which have variables correlated with each other. But we need domain knowledge to construct first-order logics and a computational complexity problem arises when calculating weights of first-order logics. To overcome these problems we suggest a method to generate first-order logics and learn weights using association analysis in this study.

The objective of this study was to estimate genetic parameters on days to 90 kg body weight and ultrasound measured traits (back fat thickness, eye muscle area, retail cut percentage) and predict genetic progress when the weights for selection on the paternal traits of Duroc, which can be incorporated into sire line selection indexes. A simulation program, ZPLAN+, was used for the simulation. Genetic parameters of days to 90 kg body weight (D90KG), back fat thickness (BFT), eye muscle area (EMA) and retail cut percentage (RCP) used in the simulation were estimated from 27,972 heads of farm tested Duroc pigs from 2005 to July, 2012. Parameters of simulation used genetic parameters with parturition rates, ratios of test pigs and replacement rates that were dependent on selection protocols of simulated farms. Different weights of selection for traits of days to 90 kg and backfat thickness were compared. Estimates of heritability were 0.406, 0.355, 0.159 and 0.379 for D90KG, BFT, EMA and RCP, respectively. Genetic correlation of D90KG with BFT, EMA and RCP were –0.043, 0.049 and 0.021, respectively. Genetic correlation of BFT with EMA and RCP were –0.394 and –0.937. And genetic correlation between EMA with RCP were 0.524. Simulation result showed that index weight of 3:1 on D90KG and BFT was effective to shorten days to 90 kg without any significant changes in backfat thickness. Generally the genetic changes were greater as parturition rate and ratios of test pigs increased. Increase in replacement rate had a small effect on genetic changes in negative way. Thus, we recommend that index weight of 3:1 on days to 90 kg and backfat thickness could be utilized for sire line selection.

We undertook the quantitative evaluations of Industrial Accident Prevention Program (IAPP). The six parameters, such as relevance, efficiency, consistency, sustainability, effectiveness, coherence, were chosen by expert plenary sessions. Two stage of Analytic Hierarchy Process were used to determine the weighted value of assessment criteria. This expert plenary suggests that the six parameters and its weight values are useful for quantitative evaluations of IAPP. Additional researches regarding the real world application of this assessment tool should be initiated.

Determining relative importance among many quality attributes under financial constraints is an important task. The weighted value of an attribute particularly in QFD, will influence on engineering characteristics and this will eventually influence the whole manufacturing process such as parts deployment, process planning, and production planning. Several scholars have suggested weighting formulas using CSC (Customer Satisfaction Coefficient) in the Kano model. However, previous research shows that the validity of the CSC approaches has not been proved systematically. The aim of the present study is to address drawbacks of CSC and to develop APC (Average Potential Coefficient), a new approach for weighting of quality attributes. For this, the current study investigated 33 quality attributes of e-learning and conducted a survey of 375 university students for the results of APC, the Kano model, and the direct importance of the quality attributes. The results show that the proposed APC is better than other approaches based on the correlation analysis with the results of direct importance. An analysis of e-leaning’s quality perceptions using the Kano model and suggestions for improving e-learning’s service quality are also included in this study.

본 논문에서는 Cone-ratio 가중치 제약이 DEA 단일 입력, 다중 출력(또는 다중 입력, 단일 출력)에 맞게 constant return을 하는 문제에 적용될 때 효율성을 측정하는 방법에 필요한 특성을 제안하였다. 또한 제안된 특성들을 기반으로 DEA에서의 단일 입력, 이중 출력에 대한 다중 해결 문제의 예시를 제시한 후 Cone-ratio 및 Wong과 Beasley 가중치 제약의 특성들을 도식적으로 비교 설명하였다.

In this paper, we suggested the property that shows the way to measure the efficiency when cone-ratio weight restrictions are applied under constant returns to scale with one-input, multiple-outputs (or multiple-inputs, one-output) in DEA. Based on the suggested property, we proposed graphical illustration of multiple solution problem with one-input, two-outputs in DEA. Then we showed some characteristics of cone-ratio and Wong and Beasley weight restrictions with an illustrative example.

DEA 모델중 널리 사용되는 교차평가모델(cross efficiency model)은 가중치에 제한을 두지 않고 어떤 특정분야에 탁월한 성과를 내는 DMU(Decision Making Unit)보다는 보다 전반적인 분야에서 두각을 나타내는 DMU를 선발함으로써 많은 연구자들이 DEA문헌에서 적용하여 왔다. 본 연구에서는 이러한 교차평가모델이 실제에 있어서는 암묵적으로 고정 가중치를 사용한다는 것과 동일한 결과를 나타낸다는 것을 분석적으로 밝혔다(one

The study investigates the various Acceptance Control Charts (ACCs) based on the factors that include process independence, data weighting scheme, subgrouping, and use of control charts. USL - LSL 〉 6Σ that used in the good condition processes in the ACCs are designed by considering user's perspective, producer's perspective and both perspectives. ACCs developed from the research is efficiently applied by using the simple control limit unified with APL (Acceptable Process Level), RLP (Rejectable Process Level), Type I Error α, and Type II Error β. Sampling interval of subgroup examines i.i.d. (Identically and Independent Distributed) or auto-correlated processes. Three types of weight schemes according to the reliability of data include Shewhart, Moving Average(MA) and Exponentially Weighted Moving Average (EWMA) which are considered when designing ACCs. Two types of control charts by the purpose of improvement are also presented. Overall, α, β and APL for nonconforming proportion and RPL of claim proportion can be designed by practioners who emphasize productivity and claim defense cost.