• Journal of Korean Society for Quality Management
• /
• v.51 no.1
• /
• pp.67-78
• /
• 2023

Purpose: The purpose of this study is to investigate the COVID-19 pandemic-driven effect changes of quality factors on customer satisfaction in Korean Police Civil Affairs Service. Methods: This study fitted a regression model to the data collected by Korean National Police Agency from 2019 (before COVID-19 pandemic) to 2020 (during COVID-19 pandemic). In order to simultaneously estimate the effects of major seven quality factors on customer satisfaction for 'before the pandemic' and for 'during the pandemic', the regression model included not only customer satisfaction as the dependent variable, but also the fourteen independent variables consisting of the seven quality factors and their seven interaction terms. The interaction terms were defined by multiplying each quality factor by a dummy variable indicating either before or during the pandemic. Therefore, the coefficient estimates of the interaction terms indicate the changes of their corresponding quality factor effects on customer satisfaction between before and during the pandemic. The double bootstrap method was applied to test the significance of coefficient estimates. Results: Both before and during the pandemic, all quality factors had positive effects on customer satisfaction. However, these effects changed differently from before to during the pandemic: (increased) supportability, sincerity, and convenience; (decreased) integrity, professionalism, and fairness; (unchanged) promptness. Conclusion: This study found that the pandemic caused significant effect changes of quality factors on customer satisfaction in Korean Police Civil Affairs Service. This finding suggests the necessity of carefully monitoring such effect changes to effectively and efficiently improve customer satisfaction. This study also identified that from before to during the pandemic, supportability, sincerity, and convenience become more important and hence, need to be better managed.

• 한국생물공학회:학술대회논문집
• /
• 2004.07a
• /
• pp.47-84
• /
• 2004

Principal Component Analysis나 Partial Least Squares와 같은 다변량 통계 기법은 변수간의 correlation structure로부터 공정의 variance를 설명할 수 있는 latent variable를 얻고 이를 이용하여 공정을 효과적으로 modeling할 수 있는 방법으로 최근 들어 많은 관심을 얻고 있다. 하지만 PLS는 공정이 stationary state에 있다고 가정하기 때문에, 생물학적 공정의 non-stationary and time-varying behavior를 설명하기에 부적절하다. 본 논문에서는 PLS 알고리즘의 혐기성 폐수처리 공정에의 적용에 있어, 이와 같은 문제를 해결하기 위해서 adaptive PLS 알고리즘을 사용함으로써 변화하는 공정의 특성에 대응하여 모델을 update하는 방법을 이용하였다. 하지만 실시간 데이터로부터 adaptive PLS 방법을 적용하는 데에는 많은 어려움이 존재하며, 특히 outlier나 abnormal disturbance에 모델이 부적절하게 adaptation하는 문제가 발생할 수 있다. 따라서 이의 해결을 위해 adaptive PLS를 적용하는데 있어 robustness를 향상시키기 위해 monitoring index를 이용하여 abnormal data에 weight를 주고 안정적인 모델의 update가 가능하게 하는 방법을 제안하였으며, 이를 적용하여 성공적으로 혐기성 폐수처리 공정의 Output을 예측하고 효과적으로 공정을 모니터링할 수 있었다. 만들어진 PLS 모델은 산업폐수를 처리하기 위한 industrial plan에서 측정된 실제 데이터에 적용하여 그 효용성을 입증하였으며, 그 결과는 mechanistic model을 적용하기 힘든 실공정에 비교적 쉽게 implementation할 수 있는 장점이 있다.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.201-203
• /
• 2007

The paper concerns the successive optimization for structure and parameters of fuzzy inference systems that is based on parallel Genetic Algorithms (PGA) and information data granulation (IG). PGA is multi, population based genetic algorithms, and it is used tu optimize structure and parameters of fuzzy model simultaneously, The granulation is realized with the aid of the C-means clustering. The concept of information granulation was applied to the fuzzy model in order to enhance the abilities of structural optimization. By doing that, we divide the input space to form the premise part of the fuzzy rules and the consequence part of each fuzzy rule is newly' organized based on center points of data group extracted by the C-Means clustering, It concerns the fuzzy model related parameters such as the number of input variables to be used in fuzzy model. a collection of specific subset of input variables, the number of membership functions according to used variables, and the polynomial type of the consequence part of fuzzy rules, The simultaneous optimization mechanism is explored. It can find optimal values related to structure and parameter of fuzzy model via PGA, the C-means clustering and standard least square method at once. A comparative analysis demonstrates that the Dnmosed algorithm is superior to the conventional methods.

• Journal of Korean Institute of Industrial Engineers
• /
• v.43 no.1
• /
• pp.62-71
• /
• 2017

In order to attract foreign tourists, it is important to understand what factors on domestic tour spots are critically considered and how they are evaluated after visit. However, most of the researches on tour business have collected information from tourists through survey on a small number of tourists, which leads to inaccurate and biased conclusion. In this paper, we suggest a data-driven methodology to figure out tourists' satisfaction factors and estimate sentiment scores on them. To do so, we collected review comments data from popular web site. Latent dirichlet allocation is employed to extract key factors and elastic net is used to estimate sentiment scores. Then, an aggregated evaluation score is generated by combining the factors and the sentiment scores per topics. Our proposed method can be used to recommend travel schedules with themes and discover new spots.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.12
• /
• pp.5464-5484
• /
• 2016

Few samples face recognition has become a highly challenging task due to the limitation of available labeled samples. As two popular paradigms in face image representation, sparse component analysis is highly robust while parts-based paradigm is particularly flexible. In this paper, we propose a probabilistic generative model to incorporate the strengths of the two paradigms for face representation. This model finds a common spatial partition for given images and simultaneously learns a sparse component analysis model for each part of the partition. The two procedures are built into a probabilistic generative model. Then we derive the score function (i.e. feature mapping) from the generative score space. A similarity measure is defined over the derived score function for few samples face recognition. This model is driven by data and specifically good at representing face images. The derived generative score function and similarity measure encode information hidden in the data distribution. To validate the effectiveness of the proposed method, we perform few samples face recognition on two face datasets. The results show its advantages.

• Journal of Korean Academy of Nursing Administration
• /
• v.8 no.3
• /
• pp.381-392
• /
• 2002

Purpose : The purpose of this study was to examine the degrees of turnover intention among Korean staff nurses(N=175) and to identify discriminating factors of their turnover intention. Method : The data were driven from a larger study and staff nurses who had worked more than 1 year as nurses were included in the analyses. The original data were collected from May 1999 to March 2000. Descriptive and discriminant analyses were utilized. Results : 87% of the participants reported turnover intention. Nurses were grouped into three group(GP)s depending on the frequencies of turnover intention: Never GP(N=23), Sometimes GP(N=107), Frequent GP(N=43). With three GPs, two functions were produced and only function 1 was significant that significantly discriminated Never and Frequent GPs. Additional discriminant analysis with only Never and Frequent GPs produced function classified 93% of the participants correctly into two GPs. Sub-dimensions of work satisfaction were significant discriminating factors. Nurses who are satisfied with doctor and nurse relationship, pay, and hospital administration tend to report no intention in turnover. Conclusion : Based on the findings of this study, possible managemental intervention for increasing interpersonal skills and assertiveness of nurses, inviting medical residents in ward team meeting, increasing incentives or baseline adjustment of annual income for registered nurses were suggested.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2001.11b
• /
• pp.1162-1165
• /
• 2001

Operational Modal Analysis also known as Output Only Modal Analysis has in the recent years been used for extracting modal parameters of civil engineering structures and is now becoming popular for mechanical structures. The advantage of the method is that no artificial excitation need to be applied to the structure or force signals to be measured. All the parameter estimation is based upon the response signals, thereby minimising the work of preparation for the test. This test case is a controlled lab set-up enabling different parameter estimation methods techniques to be used and compared to the Operational Modal Analysis. For Operational Modal Analysis two different estimation techniques are used： a non-parametric technique based on Frequency Domain Decomposition (FDD), and a parametric technique working on the raw data in time domain, a data driven Stochastic Subspace Identification (SS!) algorithm. These are compared to other methods such as traditional Modal Analysis.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.10
• /
• pp.197-205
• /
• 2021

This study aims to investigate factors influencing customer behavior towards nylon bags and single-use plastics. These factors are environmental protection awareness, health protection awareness, sense of responsibility, expectations, and green marketing. A quantitative method with the use of surveys is deployed to collect data of young people under 30, generating 1650 valid responses. The collected data is then analyzed with SPSS 22, using Cronbach's Alpha and Exploratory Factor Analysis to test the reliability of the model before validating the hypotheses by regression analysis. The study found that the majority of respondents are inclined to use plastic bags, despite their environmental awareness. The results also demonstrate that health consciousness, environmental concerns, self-driven responsibility for the sustainability of young people have a significant impact on their behaviors in using nylon bags and plastic products, whereas expectation and green marketing are confirmed not to be the factors. The study suggests that if green marketing is to gain higher influence, an increase in research and development to support other environmentally friendly packaging would be the right path. Finally, this research proposes some feasible recommendations for the government, which include imposing bolder and more targeted environmental policies on consumers and introducing educational campaigns to raise awareness about minimizing plastic consumption.

• Korean Journal of Childcare and Education
• /
• v.15 no.3
• /
• pp.21-38
• /
• 2019

Objective: The goal of this study was to investigate the effects of early childhood teachers' current working conditions such as welfare and wages, working hours, ECEC center's environmental characteristics, and parental involvement and community engagement on the professionalism of teachers. Method: A total of 988 respondents participated in the nationwide online survey. The data were analyzed by correlation analysis and structual equation modeling. Results: First, there were no statistically significant direct effects of ECEC teachers' working conditions on teacher professionalism. Second, there were significant direct effects of teacher efficacy and well-being on teacher professionalism. Third, there were significant indirect effects of teachers' working conditions on their professionalism, via efficacy and well-being, linking the impact of working conditions and the professionalism of teachers. Conclusion/Implication: The results of this structural model imply that policy input for teacher welfare, wage increases, and the enhancement of teachers' well-being and efficacy are valid and significant for the professional development of ECEC teachers. These results provide the data-driven evidence for the importance of welfare and socio-cognitive approaches for teachers.

• Nuclear Engineering and Technology
• /
• v.50 no.8
• /
• pp.1306-1313
• /
• 2018

The randomness and incipient nature of certain faults in reactor systems warrant a robust and dynamic detection mechanism. Existing models and methods for fault diagnosis using different mathematical/statistical inferences lack incipient and novel faults detection capability. To this end, we propose a fault diagnosis method that utilizes the flexibility of data-driven Support Vector Machine (SVM) for component-level fault diagnosis. The technique integrates separately-built, separately-trained, specialized SVM modules capable of component-level fault diagnosis into a coherent intelligent system, with each SVM module monitoring sub-units of the reactor coolant system. To evaluate the model, marginal faults selected from the failure mode and effect analysis (FMEA) are simulated in the steam generator and pressure boundary of the Chinese CNP300 PWR (Qinshan I NPP) reactor coolant system, using a best-estimate thermal-hydraulic code, RELAP5/SCDAP Mod4.0. Multiclass SVM model is trained with component level parameters that represent the steady state and selected faults in the components. For optimization purposes, we considered and compared the performances of different multiclass models in MATLAB, using different coding matrices, as well as different kernel functions on the representative data derived from the simulation of Qinshan I NPP. An optimum predictive model - the Error Correcting Output Code (ECOC) with TenaryComplete coding matrix - was obtained from experiments, and utilized to diagnose the incipient faults. Some of the important diagnostic results and heuristic model evaluation methods are presented in this paper.