• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.1-19
• /
• 2018

Since stock movements forecasting is an important issue both academically and practically, studies related to stock price prediction have been actively conducted. The stock price forecasting research is classified into structured data and unstructured data, and it is divided into technical analysis, fundamental analysis and media effect analysis in detail. In the big data era, research on stock price prediction combining big data is actively underway. Based on a large number of data, stock prediction research mainly focuses on machine learning techniques. Especially, research methods that combine the effects of media are attracting attention recently, among which researches that analyze online news and utilize online news to forecast stock prices are becoming main. Previous studies predicting stock prices through online news are mostly sentiment analysis of news, making different corpus for each company, and making a dictionary that predicts stock prices by recording responses according to the past stock price. Therefore, existing studies have examined the impact of online news on individual companies. For example, stock movements of Samsung Electronics are predicted with only online news of Samsung Electronics. In addition, a method of considering influences among highly relevant companies has also been studied recently. For example, stock movements of Samsung Electronics are predicted with news of Samsung Electronics and a highly related company like LG Electronics.These previous studies examine the effects of news of industrial sector with homogeneity on the individual company. In the previous studies, homogeneous industries are classified according to the Global Industrial Classification Standard. In other words, the existing studies were analyzed under the assumption that industries divided into Global Industrial Classification Standard have homogeneity. However, existing studies have limitations in that they do not take into account influential companies with high relevance or reflect the existence of heterogeneity within the same Global Industrial Classification Standard sectors. As a result of our examining the various sectors, it can be seen that there are sectors that show the industrial sectors are not a homogeneous group. To overcome these limitations of existing studies that do not reflect heterogeneity, our study suggests a methodology that reflects the heterogeneous effects of the industrial sector that affect the stock price by applying k-means clustering. Multiple Kernel Learning is mainly used to integrate data with various characteristics. Multiple Kernel Learning has several kernels, each of which receives and predicts different data. To incorporate effects of target firm and its relevant firms simultaneously, we used Multiple Kernel Learning. Each kernel was assigned to predict stock prices with variables of financial news of the industrial group divided by the target firm, K-means cluster analysis. In order to prove that the suggested methodology is appropriate, experiments were conducted through three years of online news and stock prices. The results of this study are as follows. (1) We confirmed that the information of the industrial sectors related to target company also contains meaningful information to predict stock movements of target company and confirmed that machine learning algorithm has better predictive power when considering the news of the relevant companies and target company's news together. (2) It is important to predict stock movements with varying number of clusters according to the level of homogeneity in the industrial sector. In other words, when stock prices are homogeneous in industrial sectors, it is important to use relational effect at the level of industry group without analyzing clusters or to use it in small number of clusters. When the stock price is heterogeneous in industry group, it is important to cluster them into groups. This study has a contribution that we testified firms classified as Global Industrial Classification Standard have heterogeneity and suggested it is necessary to define the relevance through machine learning and statistical analysis methodology rather than simply defining it in the Global Industrial Classification Standard. It has also contribution that we proved the efficiency of the prediction model reflecting heterogeneity.

• Journal of Korea Port Economic Association
• /
• v.30 no.3
• /
• pp.163-185
• /
• 2014

The growth of a city requires substantial resources, an appropriate environment, and the alignment of several factors. City growth also evolves through changes in its history, culture, economics, societies, groups, and government systems. However, current port city development plans designed to encourage the growth of local businesses fail to provide the support needed for both the city and businesses. The recent actions of urban administrations and federal and local governments have revealed that they have yet to create a mature decentralized management system, or perhaps have ignored the reality of needing one. Taking a clear look at the differences between port regions, such as Gwangyang and Pyeongtaek, and understanding their effect on city growth would be a prudent course of action when preparing for future developments. The purpose of this study is to determine the relationship between ports and cities by analyzing the effect of port characteristics on nearby city growth. This study used a comparison analysis to determine how port characteristics affected the growth of Pyeongtaek and Gwangyang. One result of this analysis showed that an increase in the number of goods being imported or exported had a positive effect on the growth of both port cities, In this respect, an aggressive plan and cooperation between the federal and local government should occur simultaneously. Furthermore, efficient local policies that focus on the increase of personnel and material resources should be pursued as a standard strategy, which would also promote the international status of these locations. The results of this study show the importance of government cooperation. The federal government should lead with aggressive strategies that aim to optimize efficiency, while the local government should provide the necessary assistance and coordination in order to achieve optimal results.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.43 no.6
• /
• pp.934-942
• /
• 2014

The purpose of this study was to investigate factors affecting problematic drinking by university students in the Chuncheon area. Lifelong drinking rate of subjects was 98.1%. Problematic drinking rates according to AUDIT (alcohol use disorders identification test) were as follows: 21.3% 'no problem', 58.0% 'at-risk drinking', 10.0% 'alcohol abuse' and 10.7% 'alcohol dependence'. Research has shown that problematic drinking is more prevalent among freshmen, early drinkers, those with hypochondria, and students who are less satisfied with their campus life or whose own parents are frequent drinkers. It has been shown that more serious problematic drinking is associated with higher 'positive alcohol outcome expectancies' and 'coping motives for drinking', and 'recognition level of drinking cultures' is considered less desirable. Multiple regression analysis revealed that 'coping motives for drinking' was the most significant variable affecting the problematic drinking of university students. Developing and fostering various alcohol-reducing programs that largely focus on 'coping motives for drinking' will greatly contribute to solving problematic drinking.

• Journal of the Korean Geographical Society
• /
• v.43 no.5
• /
• pp.681-700
• /
• 2008

In this study, the spatial and temporal patterns of changes in means and extreme events of temperature and precipitation across the Republic of Korea over the last 35 years (1973-2007) are examined. Over the study period, meteorological winter (December-February) mean minimum (maximum) temperature has increased by $+0.54^{\circ}C$/decade ($+0.6^{\circ}C$/decade), while there have been no significant changes in meteorological summer (June-August) mean temperatures. According to analyses of upper or lower $10^{th}$ percentile-based extreme temperature indices, the annual frequency of cool nights (days) has decreased by -9.2 days/decade (-3.3 days/decade), while the annual frequency of warm nights (days) has increased by +4.9 days/decade (+6.8 days/decade). In contrast, the increase rates of summer warm nights (+8.0 days/$^{\circ}C$) and days (+6.6 days/$^{\circ}C$) relative to changes in summer means minimum and maximum temperatures means are greater than the decreasing rates of winter nights (-5.2 days/$^{\circ}C$) and days (-4.3 days/$^{\circ}C$) relative to changes in winter temperatures. These results demonstrate that seasonal and diurnal asymmetric changes in extreme temperature events have occurred. Moreover, annual total precipitation has increased by 85.5 mm/decade particularly in July and August, which led to the shift of a bimodal behavior of summer precipitation into a multi-modal structure. These changes have resulted from the intensification of heavy rainfall events above 40mm in recent decades, and spatially the statistically-significant increases in these heavy rainfall events are observed around the Taebaek mountain region.

• Journal of Hospice and Palliative Care
• /
• v.9 no.1
• /
• pp.1-10
• /
• 2006

Purpose: Terminal cancer influences on patients as well as their family members. This research was performed to evaluate the quality of lift of primary family caregivers and to investigate the influencing factors. Methods: The results of survey were collected from 81 family caregivers who were taking care of hospitalized terminal cancer patients at an oncology department of university hospital in Daejeon from March 2005 to January 2006 with questionnaires. The questionnaires were consisted of the general characteristics of the subjects, and 36-items short-form Health Survey (SE-36) Korean version to evaluate the quality of life of family caregivers, the characteristics of patients and family caregivers' caring trait. Results: Family caregivers' mean (${\pm}SD$) SF-36 score was 47.9 (${\pm}20.7$). Influential factors on family caregivers' life quality were daily raring hours, economic burden, type of treatment; only supportive care, caring duration, sex, the numbers of ADLs (activity of daily livings) items that patients needed help in order by stepwised multiple logistic regression analysis (overall $R^2=0.639$, P=0.044). Conclusion: Daily raring hours and economic burden were two influential modifiable factors on family caregivers' quality of life. Therefore, social supportive systems are required to reduce family caregivers' daily caring hour and economic burden.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.21 no.6
• /
• pp.98-105
• /
• 2017

In this study, the fiber blending ratio and strain rate effect on the tensile behavior of hybrid fiber reinforced cement composite was evaluated. Hooked steel fiber and polyvinyl alcohol fiber were used for reinforcing fiber. The fiber blending ratio of HSF+PVA were 1.5+0.5, 1.0+1.0 and 0.5+1.5vol.%. As a results, the tensile strength, strain capacity and fracture toughness of the hooked steel fiber reinforced cement composites were improved by the increase of the bond strength of the fiber and the matrix according to increase of strain rate. However, the tensile stress sharply decreased after the peak stress because of the decrease in the number of straightened pull-out fibers by micro cracks in the matrix around hooked steel fiber. On the other hand, PVA fiber showed cut-off fracture at strain rate $10^{-6}/s$ with multiple cracks. However, at the strain rate $10^1/s$, the multiple cracks and strain capacity were decreased because of the pull-out fracture of PVA fiber. The HSF1.5PVA0.5 shown the highest tensile strength because the PVA fiber suppressed the micro cracks in the matrix around the hooked steel fiber and improved the pull-out resistance of hooked steel fiber. Thus, DIF of strain capacity and fracture toughness of HSF1.5PVA were greatly improved. In addition, the synergistic response of fracture toughness was positive because the tensile stress was slowly decreased after the peak stress by improvement of the pull-out resistance of hooked steel fiber at strain rate $10^1/s$.

• Management & Information Systems Review
• /
• v.38 no.4
• /
• pp.137-157
• /
• 2019

Companies are trying to use enterprise SNS for collaboration and speedy decision-making. This study verified the mediating effect of communication between enterprise SNS and job performance, and proved the moderating effect of nationality between enterprise SNS and communication. This study collected survey data of 81 Korean and 81 Chinese from employees who have used enterprise SNS in Korea and China. As results of data analysis, first, enterprise SNS improved job performance through speedy information sharing and error reduction. Second, communication mediated the effect of enterprise SNS on job performance. Third, enterprise SNS increased the level of organizational communication through decreasing the burden of offline face-to-face communication. Compared with Chinese corporate organizations, Korean corporate organizations have high power distances, centralized control, and high superior authority. Therefore, in the off-line communication situation, the subordinate feels the social pressure to follow the command of the superior. Thus communication is one-way and closed. In this Korean organizational situation, corporate SNS can be used as a means to bypass rigid offline communication. In the online communication environment of non face-to-face corporate SNS, anxiety and stress of face-to-face communication can be reduced, so communication between the upper and lower sides can flow more smoothly. The contribution of this paper is that it proved that enterprise SNS promotes communication and improve job performance by reducing the anxiety or stress of offline communication, while according to prior research successful adoption of many types of information systems requires the fit between an organization and its organizational culture.

• Journal of Life Science
• /
• v.25 no.3
• /
• pp.329-335
• /
• 2015

This study was performed to determine the optimal ratio of Petasites japonicus, Luffa cylindrica, and Houttuynia cordata, all of which are supposed to have anti-respiratory disease effects, such as against rhinitis. The experiment incorporated a mixture design and included 12 experimental points with center replicates for three different independent variables (Petasites japonicus 30~70%; Luffa cylindrica 10~30%; and Houttuynia cordata 10~30%). Based on this design, the mixture was extracted in hot water at 121℃ for 45 min and anti-allergy and anti-microbial activities were observed. The response surface and trace plot described for the anti-allergy activity showed Petasites japonicas was a relatively important factor. The correlation coefficient (R²) value 82.10% for the inhibition effect of degranulation was analyzed by the regression equation. The analysis of variance showed the model fit was statistically significant (p<0.05). The optimal ratio of the mixture was Petasites japonicus 0.75%, Luffa cylindrica 0.11%, and Houttuynia cordata 0.14%. The anti-microbial activity for each extraction of the mixture was valid on gram-positive, such as Staphylococcus aureus (KCCM 40881) and Staphylococcus epidermidis (KCCM 35494), while it was less effective on gram-negative, such as Escherichia coli (KCCM 11234) and Pseudomonas aeruginosa (KCCM 11328).

• Korean Business Review
• /
• v.13
• /
• pp.49-66
• /
• 2000

Despite the fact that understanding customers satisfaction with transportation services is a subject of great importance, authors, so far, found no systematic researches referred to that issue. From this point, studying the satisfaction with subways services can be extremely useful. Empirical study of key factors in the satisfaction with subway services is the departure point, which holds as objectives, and we believe, will contribute to overall increasing in the number of subways services used and in the amount of public benefits derived from that usage. In order to achieve these goals: First, several items referred to some key factors in the satisfaction of subway usage were systemized. Second, a research of specific weights attached to those key factors by subway passengers was conducted. Knowledge of the satisfaction variables system can provide deep insights into ones perceptual experience when using a subway. The results were as follows: Various interrelated factors compose a passengers satisfaction with subway services. People do not just use subway passively; a number of key factors, like physical and personal services, exact timing, easiness to access etc. determine the passengers satisfaction with subway. In order to find out specific weights of these key factors multiple regression analysis was employed. Results showed that satisfaction with subway is determined by (in order of importance) easiness to access, quality of physical services, friendliness of working stuff and timing exactness. According to the findings, passengers do not use subway as a simple mean of transportation, rather they perceive it as a complex combination of environmental elements and overall satisfaction depends on these various factors. Therefore, to learn passengers satisfaction with subways services, passengers subway experience must be thoroughly studied and analyzed, and this is where papers value resides.

• Journal of agricultural medicine and community health
• /
• v.30 no.1
• /
• pp.101-111
• /
• 2005

Objectives: This study was to evaluate the compliance of hypertensive patients and its related factors registered at Community Health Practitioner Post(CHCP). Methods: 304 patients were interviewed by trained nursing students during one month(June~July 2004). The questionnaire included general charactristics, knowledge of hypertension, health education experience, constructs of Health Belief Model, self efficacy and so on. Compliance group was defined "having regularly medication and good life style". Good life style included regular exercise, non-smoking, little alcohol, low salt diet, weight control. Results: In compliance group 90.3% of man and 93.3% of woman were regularly taking hypertensive medicine, and 45.2% of man and 56.4% of woman were having good life style (compliance group). In both man and woman, the group of higher education were more compliance group, but were statistically significant were in man(p<0.05). In woman, the compliance group have significantly higher score in knowledge of hypertension(p(0.05). The compliance group have significantly higher self-efficacy score in both man and woman (p<0.05). In Health Belief Model, susceptibility and benefit were statistically significant in man, seriousness, benefit and barrier in woman(p<0.05). In multiple logistic regression analysis, education level and self efficacy in man and knowledge of hypertension, self-efficacy and benefit in woman were significant variables (p<0.05). Conclusions: It is very important to evaluate and modify life-style adding to having regularly medication in hypertensive patients registered at CHCP. To this, health education programs about benefit to compliance and the methods to improve self-efficacy should be developed for this patients.