• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.101-112
• /
• 2018

The purpose of the study is to predict the number of police calls using neural network which is one of the machine learning and negative binomial regression, by using the data of 112 police calls received from Chungnam Provincial Police Agency from June 2016 to May 2017. The variables which may affect the police calls have been selected for developing the prediction model : time, holiday, the day before holiday, season, temperature, precipitation, wind speed, jurisdictional area, population, the number of foreigners, single house rate and other house rate. Some variables show positive correlation, and others negative one. The comparison of the methods can be summarized as follows. Neural network has correlation coefficient of 0.7702 between predicted and actual values with RMSE 2.557. Negative binomial regression on the other hand shows correlation coefficient of 0.7158 with RMSE 2.831. Neural network has low interpretability, but an excellent predictability compared with the negative binomial regression. Based on the prediction model, the police agency can do the optimal manpower allocation for given values in the selected variables.

• Korea journal of population studies
• /
• v.30 no.1
• /
• pp.97-124
• /
• 2007

국내 생화학 분야 학자들의 연구성과에 영향을 주는 요인은 무엇인가? 특히 젠더는 연구성과에 어떤 영향을 주는가? 이 연구는 다음과 같은 항목에 초점을 두었다. 첫째 연구성과의 특징에 따른 차이를 보기 위해, 연구성과를 학술지 유형에 따라 SCI논문과 비SCI논문으로 구분해서 비교분석했다. 둘째, 교육기간부터 경력기간별로 연구성과에 미치는 요인이 변화할 가능성을 분석하기 위해, 연구성과를 종속변수로 하는 모델을 대학원 기간과 졸업 이후 경력 기간별로 구성했다. 셋째, 연구성과에 대한 이론적 요인으로서 사회인구학적 요인, 조직적 요인, 그리고 이전 연구업적의 누적효과를 음이항모델을 사용해서 분석했다. 연구 결과는 다음과 같다. 첫째, SCI논문성과의 경우 젠더 효과는 대학원 기간 동안에는 관찰되지 않았지만, 경력 초기부터 다음 기간 연구성과에 영향을 주는 것으로 나타났다. SCI학술지 연구성과의 경우 조직적 요인 중에서 외국 학위가 중요한 것으로 파악되었다. 이전 연구성과 역시 누적적으로 그 후 연구성과에 영향을 주었다. 비SCI논문 수를 분석한 결과, 대학원 기간과 졸업 후 3년간 기간에는 젠더 차이가 관찰되지 않았고, 졸업 후 3-6년 기간에 젠더 효과가 발견되었다. 또한 대학원 기간의 비SCI논문의 누적효과가 지속적으로 나타났다.

• Journal of Industrial Convergence
• /
• v.22 no.8
• /
• pp.1-17
• /
• 2024

Recently, interest in edutech has been focused on its fusion with AI technology, and the market in this field is expanding. This study aims to analyze the technological competitiveness and key technological areas of major countries in the AI-edutech field. Additionally, considering that AI-edutech is a convergence of AI technology and edutech, the study seeks to examine the path dependence of AI-edutech in each country to determine whether they are based on existing AI technologies or edutech. To this end, AI-edutech patents were collected and competitiveness was analyzed using patent activity, patent impact, and market acquisition indicators. Path dependence for each country was analyzed using the hurdle negative binomial regression model. The analysis results indicate that the major countries in the AI-edutech field are China, South Korea, the United States, India, and Japan. In terms of patent activity, China had the highest level, followed by South Korea. In terms of patent impact and market securing power, the United States was high in both aspects, Japan had high market securing power, and South Korea had high patent influence. The results of the hurdle negative binomial analysis presented unique findings. The logit part results indicated that the possession of existing AI and edutech did not positively affect the emergence of current AI-edutech, but the count part results showed a positive influence. This suggests that, overall, it is difficult to assert that current AI-edutechs are based on past AI and edutechs. However, once some AI-edutechs based on existing AI and edutechs emerge, they are influenced by the existing technologies. These findings provide implications for future research and technological strategies in this field.

• The Journal of the Korea Contents Association
• /
• v.13 no.7
• /
• pp.361-368
• /
• 2013

This research aims to offer the information required for demand increase on marketing strategy level by investigating Mudeungsan visitors' demographic characteristics and social economical variables. To accomplish this study, the proper analyzing model needs to be applied because a grave error of parameters will be led if regression model appropriate for analyzing the data of a continuous probability variable is applied, in case that dependent variable is a discrete random variable which have a discrete probability distribution. Therefore data analysis was performed with Poisson model. However, as the data was showing an overdispersion, parameter was estimated with the Binomial Poisson model able to cover the problem. As a result, some explanatory variables turned out to be significant such as visitor's age, occupation, preferred season to visit, type of company, five days working, and preferring type of tourism. Author could offer to the national park the information about characteristics of core market revealed and marketing strategy for it, based on those influential variables.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.857-871
• /
• 2013

Export credit insurance is a policy tool for export growth. In the era of free trade under the governance of WTO, export credit insurance is still allowed as one of the few instruments to increase exports. This paper, using data on short-term export insurance contracts issued to foreign subsidiaries of Korean companies, calculates the expected loss per exposure by combining the effect of risk factors (credit rate of foreign importers, size of mother company, and payment period) on loss frequency and loss severity in different levels. We, applying generalized linear models (GLM), first fit loss frequency and loss severity to negative binomial and lognormal distribution, respectively, and then estimate the loss frequency rate per contract and the ratio of loss severity to coverage amount. Finally, we calculate the expected loss per exposure for each level of risk factors by combining these two rates. Based on the result of statistical analysis, we present the implication for the current premium rate of export insurance.

• Journal of Digital Convergence
• /
• v.20 no.3
• /
• pp.283-295
• /
• 2022

The number of citations in a patent is one of the indicators of the qualitative value of a patent. In this study, negative binomial regression model analysis was performed focusing on 47,354 US patents of 14 global top automotive makers in order to examine the major factors affecting the number of patent citations. As a result of the review, it was found that, elapsed years since filing, the number of patent claims, the number of claim letters, the number of inventors, the number of patent family countries, and the number of patent families, as well as IPC diversity, had a positive and significant effect on the number of citations. The results of this study are expected to provide a basic basis for considering the IPC diversity index together in analyzing and evaluating future patents and establishing strategies for creating excellent patents.

• Korean Journal of Social Welfare
• /
• v.67 no.3
• /
• pp.253-280
• /
• 2015

This study reconsiders the concept of publicness by raising a question about the problems which the recent marketization of social services in South Korea. The existing perspective on publicness, however, is insufficient to account for the entire Long-term care market because only public organizations have publicness. Accordingly, this study presents 'integrated publicness', particularly 'dimensional publicness' and 'normative publicness'. A disproportional stratified sampling procedure was used to consider ownership. A merged dataset combining surveys from 248 Long-term Care facilities and on-line resources was used and analyzed by multiple regression, negative binomial regression and multiple imputation analysis. The analysis results suggest as follows. First, ownership publicness appeared more effective in the overall. Second, the regulations on the government funding did not show effective, and the regulation on evaluation system showed the effect. Third, professionalization of normative publicness showed a negative effect on service structure and showed a positive effect on service process. Lastly, user of free services whose public accountability was identified to be effective on service structure and outcome. These findings suggest that not only existing ownership but also dimensional publicness and normative publicness showed an effect on service quality. In this respect, this is important as the performance produced by empirical models of integrated publicness, in this situation that the outcome of marketization is insignificant.

• International Journal of Highway Engineering
• /
• v.14 no.2
• /
• pp.131-143
• /
• 2012

The past researches on roadway segment safety estimation focused on intersections, which are the primary traffic accident regions. The past researches on roadway segments, However, analyzed the effects of certain factors on the traffic accident occurrence rate by organizing the individual geometric structures of the roads, and there is still a dearth of researches on the development of a traffic accident estimation model for rural roadway segments. Therefore, this research focused on rural two-lane and multilane roadway segments and developed traffic accident estimation models through the application of statistical techniques. This is required to explain such high frequency of zero counts in the traffic accident data. In this research, it was found that the Hurdle model is more suitable than the Poisson or negative binomial-regression model for explaining the excess zeros case. In addition, main variables were chosen to estimate their effects on traffic accident occurrence at rural roadway segments, and the safety at such rural roadway segments was estimated. In this research, it was assumed that there are different factors that affect the safety at two-way lane and multilane roadway segments, and a traffic accident estimation model was developed by dividing the two-way lane and multilane roadway segments.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.19 no.3
• /
• pp.109-121
• /
• 2024

This paper adopts a resource-based approach to analyze why some universities have a greater number of faculty startups, and how this impacts on performance, in terms of indictors such as the number of employees and revenue sales. More specifically, we propose 9 hypotheses which link institutional resources to faculty startups and their performance, and compare 5 different groups of university resources for cross-college variation, using data from 134 South Korean four-year universities from 2017 to 2020. We find that the institutional factors impacting on performance of faculty startups differ from other categories of startups. The results show that it is important for universities to provide a more favorable environment, incorporating more flexible personnel policies and accompanying startup support infrastructure, for faculty startups, whilest it is more effective to have more financial resources and intellectual property for other categories of startups. Our findings also indicate that university technology-holding company and technology transfer programs are crucial to increase the number of faculty startups and their performance. Our analysis results have implications for both university and government policy-makers, endeavoring to facilitate higher particaption of professors in startup formation and ultimate commercialization of associated teachnologies.