• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1508-1520
• /
• 2018

In this paper, we propose an improved model to provide users with a better long-term prediction of waterworks operation data. The existing prediction models have been studied in various types of models such as multiple linear regression model while considering time, days and seasonal characteristics. But the existing model shows the rate of prediction for demand fluctuation and long-term prediction is insufficient. Particularly in the deep running model, the long-short-term memory (LSTM) model has been applied to predict data of water purification plant because its time series prediction is highly reliable. However, it is necessary to reflect the correlation among various related factors, and a supplementary model is needed to improve the long-term predictability. In this paper, convolutional neural network (CNN) model is introduced to select various input variables that have a necessary correlation and to improve long term prediction rate, thus increasing the prediction rate through the LSTM predictive value and the combined structure. In addition, a multiple linear regression model is applied to compile the predicted data of CNN and LSTM, which then confirms the data as the final predicted outcome.

• Computers and Concrete
• /
• v.33 no.2
• /
• pp.137-145
• /
• 2024

The technique of experimentally determining concrete's compressive strength for a given mix design is time-consuming and difficult. The goal of the current work is to propose a best working predictive model based on different machine learning algorithms such as Gradient Boosting Machine (GBM), Stacked Ensemble (SE), Distributed Random Forest (DRF), Extremely Randomized Trees (XRT), Generalized Linear Model (GLM), and Deep Learning (DL) that can forecast the compressive strength of ternary geopolymer concrete mix without carrying out any experimental procedure. A geopolymer mix uses supplementary cementitious materials obtained as industrial by-products instead of cement. The input variables used for assessing the best machine learning algorithm not only include individual ingredient quantities, but molarity of the alkali activator and age of testing as well. Myriad statistical parameters used to measure the effectiveness of the models in forecasting the compressive strength of ternary geopolymer concrete mix, it has been found that GBM performs better than all other algorithms. A sensitivity analysis carried out towards the end of the study suggests that GBM model predicts results close to the experimental conditions with an accuracy between 95.6 % to 98.2 % for testing and training datasets.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.13 no.4
• /
• pp.217-231
• /
• 2018

In Korea, small and medium sized domestic enterprises(SMEs) play an pivotal role in the national economy, accounting for 99.8% of all enterprises, 87.9% of total employment, and 48.3% of production. and SMEs were driving a real force of the development of national economy in many respects such as innovation, job creation, industrial diversity, balanced regional development. Despite their crucial role in the national development, most of SMEs suffer from a lack of R&D capabilities and equipments as well as funding capacity. Government-Supported Research Institute(GRI) can provide SMEs with valuable supplementary technological knowledges and help them build technological capacities. so, In order to effectively support SMEs, government and GRI must be a priority to know about the factors influencing the performance related to technology transfer and technological collaborations. The purpose of this study is to analyze the influence of Innovative competences and CEO's entrepreneurship on Organizational performance in ICT small and medium enterprises, including the moderating effect of Social capital. This study adopted research variables such as Innovative competence, CEO's entrepreneurship as independent variables, with Organizational performance as a dependent variable, including the moderating variable of Social capital. 1,200 companies data which in the field of ICT SMEs were collected from the survey. The result of this empirical study is summarized as follows, First, CEO's entrepreneurship was confirmed to have a significant effect on organizational performance, and social capital variables were confirmed to have a moderating effect between entrepreneurship and organizational performance. Second, it was found that the company's Innovative competence was significantly affected the organizational performance. and also that social capital variables moderating effects. From these findings, it was confirmed that the Innovatibe competence plays an important role in influencing corporate performance.

• Korean Journal of Human Ecology
• /
• v.19 no.3
• /
• pp.523-536
• /
• 2010

This study analyzed the effects of demographic factors and sensory experiences of customers on customer satisfaction, using data from 302 customers in the Pusan, Ulsan, and Kyungnam areas who have visited family restaurants within 3 month period prior to the study. This study defined the sub-factors of sensory experience as vision, sound, smell, taste, and touch, and defined the sub-factors of customer satisfaction as main services, supplementary facilities, services related to sales promotion, served food, and the location of a restaurant. The study revealed that each evaluation score of the sub-factors of sensory experience and each evaluation score of the sub-factors of customer satisfaction was a little higher than the middle score. Respondents evaluated taste as the highest score among the sub-factors of sensory experience and evaluated main services as the highest score among the sub-factors of customer satisfaction. In terms of the effects of the sub-factors of sensory experiences and demographic factors on overall customer satisfaction, more positive taste experience, vision experience, and sound experience led to higher overall customer satisfaction and the married group in terms of marital state gave higher evaluation scores on overall customer satisfaction than the counterpart. In terms of the effects of the sub-factors of sensory experiences and demographic factors on individual customer satisfaction, consumers' sensory experiences were shown to exert far greater influences than the demographic variables.

• Journal of Korean Society of Transportation
• /
• v.24 no.1 s.87
• /
• pp.39-52
• /
• 2006

This study divided the large-scale traffic accident locations into its own characteristics by using Cluster Analysis. Also, Quantification II and Classification and Regression Tree methods were used enabling evaluation for the amount of affecting influence by the crash type. After these analyses, we tested the fitness of the results and suggested the simplification of the quantification index. With the results from the discussed procedure, obvious differences were observed by groups according to the characteristics of crash type from the Discrimination and Classification analysis of divided four groups. Thus, measures and supplementary measures for the traffic accidents could be suggested in groups systematically. However, a lot of missing values in variables caused a huge loss of data and made this study difficult for more detailed analysis, With this difficulty. recording mandatory log files with a standardized format is also recommended to Prevent this Problem in advance.

• Journal of Labour Economics
• /
• v.41 no.2
• /
• pp.61-88
• /
• 2018

This paper examines the impact of internal migration on wage growth among college graduates using Propensity Score Matching methods. We define migration as moving between Seoul Metropolitan Area (SMA) and non-SMA based on the locations of graduates' first and second jobs. We also take the direction of migration into account for examining the wage premium in SMA. In order to estimate the impact of migration on wage growth, we use the Graduate Occupational Mobility Survey (2010GOMS) coupled with other supplementary data such as College Scholastic Ability Test score and local characteristic variables. The results reveals that graduates moving from SMA to non-SMA do not experience significant wage growth. However, we find that graduates moving from non-SMA to SMA experience an increase in their monthly wage about 170,000~186,000 KRW on average (9.5~10.3% of their monthly wage on the first job).

• The Journal of the Korea Contents Association
• /
• v.18 no.5
• /
• pp.149-155
• /
• 2018

The purposes of this paper are to describe the burnout, absence and disciplinary action among police officers in Korea and to identify the correlation among these three variables. And aim of this study is to provide basic information for the health improvement of police officers in Korea. Studies have shown significant static correlation between the practice of absence from work and the absence from work that is false, but the coefficient of correlation is very low. In addition, there was no significant correlation between burnout and disciplinary action. Regression analysis showed significant relationships with burnout and absence intention, practice of absence and types of disciplinary action, but they were very poorly explained. So you can see that the burnout of police officers generally has a small effect on absence, but not on the disciplinary action. Future studies should include supplementary studies of these associations.

• Journal of Distribution Science
• /
• v.14 no.10
• /
• pp.109-116
• /
• 2016

Purpose - This study investigates the purchase pattern relating to soybean products in Korea. Specifically, the effect of branding based on a regional name was analyzed in terms of consumer purchase frequencies. The primary purpose of this study is to understand why family characteristics affect product selection for a regional brand in the soybean food category. Research design, data, and methodology - We used data collected by the Rural Development Administration (RDA) of Korea. The RDA has monitored agricultural food consumers for years in order to obtain purchase records. Panel participants live in regions near the capital city of Seoul, Korea. Examining data from January 2010 to May 2016, 667 families were selected for analysis. The final data set was 1,335,402. Each purchase item by each individual family was aggregated to a countable weekly observation. To analyze the data set quantitatively, zero-inflation regression was adopted, which was appropriate to avoid biases from overly dispersed observations. Results - We hypothesized the effects of regional branding from the viewpoint of the family characteristics. The first hypothesis was that the number of children would be positively associated with the purchase of a regional brand of soybean products. The result strongly supported this hypothesis. The second hypothesis was that the number of family members would be negatively associated with the purchase of the soybean products of a regional brand. Based on empirical analysis, we concluded that this hypothesis was partially supported. The third hypothesis was the presence of an interaction effect between the number of children and the family size, which was supported by the results. As a supplementary analysis, we also tested mean-variance differences in terms of categories and regional branding with corporate branding. Conclusion - The results of this study provide insights for regional branding strategies in agricultural food management. This study appears to be one of the seminal studies trying to analyze purchase patterns from longitudinal observations. In addition, this study adopted variables characterizing family lifestyle. This study confirmed that children and family size should be considered when soybean product brands are introduced.

• Health Policy and Management
• /
• v.15 no.4
• /
• pp.161-175
• /
• 2005

Since the introduction of mandatory health insurance in In, the Korean national health insurance(KNHI) has grown rapidly. In 2004, about $96.9\%$ of the total population are covered by the KNHI and the remaining $3.1\%$ by the Medical Aid program. Despite national health insurance system in Korea, private health insurance market has grown rapidly. In 2004, the size of the private health insurance market was estimated at 6,568 billion won. The purpose of this study Is to identify the factors that determine the purchasing decisions of supplementary private health insurance under mandatory national health insurance system in Korea. The data from n04 Busan Health Survey were analysed for the Purpose. The variables in this study are demographic factors, health status and health behavioral factors, health care systemic factors, and socioeconomic factors. For statistical analyse, we used logistic regression. The Findings show that female, economically active age group(especially 35-49 years), persons with better health status or experience of health screening test are more likely to purchase private health insurance. And higher household income and expenditure, higher education level are more associated with the increased probabilities of private health insurance purchases. This results imply that the expanding of private health insurance market could widen the gap between the have and have-not in terms of equal health care accessibility.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2009.03a
• /
• pp.759-767
• /
• 2009

Recently, there is a trend to introduce a reliability approach to the design of al large scale improvement of weak ground due to the uncertainty of the influence factors in the consolidation. Since the reliability analysis is not easily adopted to geotechnical engineers because of some difficulties in working up the theories, Duncan(2000) proposed a simplified method for using reliability method to goetechnical problems. In this study, the applicability of Duncan's simplified reliability approach is evaluated by comparing the traditional reliability results with Duncan's. In the sensitivity analysis, the two results were quite similar. However, the probability of failure showed an error range of 20~50% and further Duncan's approach could not make a distinction for the distribution of geotechnical random variables. The simplified reliability method seems to be used properly in preliminary design if it is used supplementary with the deterministic method.