• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.1-17
• /
• 2019

Because stock price forecasting is an important issue both academically and practically, research in stock price prediction has been actively conducted. The stock price forecasting research is classified into using structured data and using unstructured data. With structured data such as historical stock price and financial statements, past studies usually used technical analysis approach and fundamental analysis. In the big data era, the amount of information has rapidly increased, and the artificial intelligence methodology that can find meaning by quantifying string information, which is an unstructured data that takes up a large amount of information, has developed rapidly. With these developments, many attempts with unstructured data are being made to predict stock prices through online news by applying text mining to stock price forecasts. The stock price prediction methodology adopted in many papers is to forecast stock prices with the news of the target companies to be forecasted. However, according to previous research, not only news of a target company affects its stock price, but news of companies that are related to the company can also affect the stock price. However, finding a highly relevant company is not easy because of the market-wide impact and random signs. Thus, existing studies have found highly relevant companies based primarily on pre-determined international industry classification standards. However, according to recent research, global industry classification standard has different homogeneity within the sectors, and it leads to a limitation that forecasting stock prices by taking them all together without considering only relevant companies can adversely affect predictive performance. To overcome the limitation, we first used random matrix theory with text mining for stock prediction. Wherever the dimension of data is large, the classical limit theorems are no longer suitable, because the statistical efficiency will be reduced. Therefore, a simple correlation analysis in the financial market does not mean the true correlation. To solve the issue, we adopt random matrix theory, which is mainly used in econophysics, to remove market-wide effects and random signals and find a true correlation between companies. With the true correlation, we perform cluster analysis to find relevant companies. Also, based on the clustering analysis, we used multiple kernel learning algorithm, which is an ensemble of support vector machine to incorporate the effects of the target firm and its relevant firms simultaneously. Each kernel was assigned to predict stock prices with features of financial news of the target firm and its relevant firms. The results of this study are as follows. The results of this paper are as follows. (1) Following the existing research flow, we confirmed that it is an effective way to forecast stock prices using news from relevant companies. (2) When looking for a relevant company, looking for it in the wrong way can lower AI prediction performance. (3) The proposed approach with random matrix theory shows better performance than previous studies if cluster analysis is performed based on the true correlation by removing market-wide effects and random signals. The contribution of this study is as follows. First, this study shows that random matrix theory, which is used mainly in economic physics, can be combined with artificial intelligence to produce good methodologies. This suggests that it is important not only to develop AI algorithms but also to adopt physics theory. This extends the existing research that presented the methodology by integrating artificial intelligence with complex system theory through transfer entropy. Second, this study stressed that finding the right companies in the stock market is an important issue. This suggests that it is not only important to study artificial intelligence algorithms, but how to theoretically adjust the input values. Third, we confirmed that firms classified as Global Industrial Classification Standard (GICS) might have low relevance and suggested it is necessary to theoretically define the relevance rather than simply finding it in the GICS.

• Journal of Distribution Science
• /
• v.10 no.3
• /
• pp.51-61
• /
• 2012

This study seeks to understand how the choice of a coffee shop is related to a customer's loyalty and which characteristics of a shop influence this choice. It considers large-sized coffee shops brands whose market scale has gradually grown. The users' choice of shop is determined by price, employee service, shop location, and shop atmosphere. The study investigated the effects of these four properties on the brand attitudes of coffee shops. The effects were found to vary depending on users' characteristics. The properties with the largest influence were shop atmosphere and shop location Therefore, the purpose of the study was to examine the properties that could help coffee shops get loyal customers, and the choice properties that could satisfy consumers' desires The study examined consumers' perceptions of shop properties at selection of coffee shop and the difference between perceptual difference and coffee brand in order to investigate customers' desires and needs and to suggest ways that could supply products and service. The research methodology consisted of two parts: normative and empirical research, which includes empirical analysis and statistical analysis. In this study, a statistical analysis of the empirical research was carried out. The study theoretically confirmed the shop choice properties by reviewing previous studies and performed an empirical analysis including cross tabulation based on secondary material. The findings were as follows: First, coffee shop choice properties varied by gender. Price advantage influenced the choice of both men and women; men preferred nearer coffee shops where they could buy coffee easily and more conveniently than women did. The atmosphere of the coffee shop had the greatest influence on both men and women, and shop atmosphere was thought to be the most important for age analysis. In the past, customers selected coffee shops solely to drink coffee. Now, they select the coffee shop according to its interior, menu variety, and atmosphere owing to improved quality and service of coffee shop brands. Second, the prices of the brands did not vary much because the coffee shops were similarly priced. The service was thought to be more important and to elevate service quality so that price and employee service and other properties did not have a great influence on shop choice. However, those working in the farming, forestry, fishery, and livestock industries were more concerned with the price than the shop atmosphere. College and graduate school students were also affected by inexpensive price. Third, shop choice properties varied depending on income. The shop location and shop atmosphere had a greater influence on shop choice. The customers in an income bracket of less than 2 million won selected low-price coffee shops more than those earning 6 million won or more. Therefore, price advantage had no relation with difference in income. The higher income group was not affected by employee service. Fourth, shop choice properties varied depending on place. For instance, customers at Ulsan were the most affected by the price, and the ones at Busan were the least affected. The shop location had the greatest influence among all of the properties. Among the places surveyed, Gwangju had the least influence. The alternate use of space in a coffee shop was thought to be important in all the cities under consideration. The customers at Ulsan were not affected by employee service, and they selected coffee shops according to quality and preference of shop atmosphere. Lastly, the price factor was found to be a little higher than other factors when customers frequently selected brands according to shop properties. Customers at Gwangju reacted to discounts more than those in other cities did, and the former gave less priority to the quality and taste of coffee. Brand preference varied depending on coffee shop location. Customers at Busan selected brands according to the coffee shop location, and those at Ulsan were not influenced by employee kindness and specialty. The implications of this study are that franchise coffee shop businesses should focus on customers rather than aggressive marketing strategies that increase the number of coffee shops. Thus, they should create an environment with a good atmosphere and set up coffee shops in places that customers have good access to. This study has some limitations. First, the respondents were concentrated in metropolitan areas. Secondary data showed that the number of respondents at Seoul was much more than that at Gyeonggi-do. Furthermore, the number of respondents at Gyeonggi-do was much more than those at the six major cities in the nation. Thus, the regional sample was not representative enough of the population. Second, respondents' ratio was used as a measurement scale to test the perception of shop choice properties and brand preference. The difficulties arose when examining the relation between these properties and brand preference, as well as when understanding the difference between groups. Therefore, future research should seek to address some of the shortcomings of this study: If the coffee shops are being expanded to local areas, then a questionnaire survey of consumers at small cities in local areas shall be conducted to collect primary material. In particular, variables of the questionnaire survey shall be measured using Likert scales in order to include perception on shop choice properties, brand preference, and repurchase. Therefore, correlation analysis, multi-regression, and ANOVA shall be used for empirical analysis and to investigate consumers' attitudes and behavior in detail.

• The Journal of Korean Society for Radiation Therapy
• /
• v.30 no.1_2
• /
• pp.161-167
• /
• 2018

Purpose : This study evaluates the usefulness of the Modified Hybrid-VMAT scheme with consideration of background radiation when establishing a treatment plan for multiple bone metastatic cancer including multiple tumors on the same axis. Materials and Methods : The subjects of this study consisted of five patients with multiple bone metastatic cancer on the same axis. The planning target volume(PTV) prescription dose was 30 Gy, and the treatment plan was established using Ray Station(Ray station, 5.0.2.35, Sweden). In the treatment plan for each patient, two or more tumors were set as one isocenter. A volumetric modulated arc therapy(VMAT) plan, a hybrid VMAT(h) plan with no consideration of background radiation, and a modified hybrid VMAT(mh) with consideration of background radiation were established. Then, using each dose volume histogram(DVH), the PTV maximum dose($D_{max}$), mean dose($D_{mean}$), conformity index(CI), and homogeneity index(HI) were compared among the plans. In addition, the organ at risk(OAR) of each treatment site was evaluated, and the total MU(Monitor Unit) and treatment time were also analyzed. Results : The PTV $D_{max}$ values of VMAT, VMAT(h) and VMAT(mh) were 3188.33 cGy, 3526 cGy, and 3285.67 cGy, the $D_{mean}$ values were 3081 cGy, 3252 cGy, and 3094 cGy; the CI values were $1.35{\pm}0.19$, $1.43{\pm}0.12$, and $1.30{\pm}0.06$; the HI values were $1.06{\pm}0.01$, $1.14{\pm}0.06$, and $1.09{\pm}0.02$; and the VMAT(h) OAR value was increased 3 %, and VMAT(mh) OAR value was decreased 18 %, respectively. Furthermore, the mean MU values were 904.90, 911.73, and 1202.13, and the mean beam on times were $128.67{\pm}10.97$, $167.33{\pm}7.57$, and $190.33{\pm}4.51$ respectively. Conclusions : Applying Modified Hybrid-VMAT when treating multiple targets can prevent overdose by correcting the overlapping of doses. Furthermore, it is possible to establish a treatment plan that can protect surrounding normal organs more effectively while satisfying the inclusion of PTV dose. Long-term follow-up of many patients is necessary to confirm the clinical efficacy of Modified Hybrid-VMAT.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.1-32
• /
• 2018

In addition to stakeholders including managers, employees, creditors, and investors of bankrupt companies, corporate defaults have a ripple effect on the local and national economy. Before the Asian financial crisis, the Korean government only analyzed SMEs and tried to improve the forecasting power of a default prediction model, rather than developing various corporate default models. As a result, even large corporations called 'chaebol enterprises' become bankrupt. Even after that, the analysis of past corporate defaults has been focused on specific variables, and when the government restructured immediately after the global financial crisis, they only focused on certain main variables such as 'debt ratio'. A multifaceted study of corporate default prediction models is essential to ensure diverse interests, to avoid situations like the 'Lehman Brothers Case' of the global financial crisis, to avoid total collapse in a single moment. The key variables used in corporate defaults vary over time. This is confirmed by Beaver (1967, 1968) and Altman's (1968) analysis that Deakins'(1972) study shows that the major factors affecting corporate failure have changed. In Grice's (2001) study, the importance of predictive variables was also found through Zmijewski's (1984) and Ohlson's (1980) models. However, the studies that have been carried out in the past use static models. Most of them do not consider the changes that occur in the course of time. Therefore, in order to construct consistent prediction models, it is necessary to compensate the time-dependent bias by means of a time series analysis algorithm reflecting dynamic change. Based on the global financial crisis, which has had a significant impact on Korea, this study is conducted using 10 years of annual corporate data from 2000 to 2009. Data are divided into training data, validation data, and test data respectively, and are divided into 7, 2, and 1 years respectively. In order to construct a consistent bankruptcy model in the flow of time change, we first train a time series deep learning algorithm model using the data before the financial crisis (2000~2006). The parameter tuning of the existing model and the deep learning time series algorithm is conducted with validation data including the financial crisis period (2007~2008). As a result, we construct a model that shows similar pattern to the results of the learning data and shows excellent prediction power. After that, each bankruptcy prediction model is restructured by integrating the learning data and validation data again (2000 ~ 2008), applying the optimal parameters as in the previous validation. Finally, each corporate default prediction model is evaluated and compared using test data (2009) based on the trained models over nine years. Then, the usefulness of the corporate default prediction model based on the deep learning time series algorithm is proved. In addition, by adding the Lasso regression analysis to the existing methods (multiple discriminant analysis, logit model) which select the variables, it is proved that the deep learning time series algorithm model based on the three bundles of variables is useful for robust corporate default prediction. The definition of bankruptcy used is the same as that of Lee (2015). Independent variables include financial information such as financial ratios used in previous studies. Multivariate discriminant analysis, logit model, and Lasso regression model are used to select the optimal variable group. The influence of the Multivariate discriminant analysis model proposed by Altman (1968), the Logit model proposed by Ohlson (1980), the non-time series machine learning algorithms, and the deep learning time series algorithms are compared. In the case of corporate data, there are limitations of 'nonlinear variables', 'multi-collinearity' of variables, and 'lack of data'. While the logit model is nonlinear, the Lasso regression model solves the multi-collinearity problem, and the deep learning time series algorithm using the variable data generation method complements the lack of data. Big Data Technology, a leading technology in the future, is moving from simple human analysis, to automated AI analysis, and finally towards future intertwined AI applications. Although the study of the corporate default prediction model using the time series algorithm is still in its early stages, deep learning algorithm is much faster than regression analysis at corporate default prediction modeling. Also, it is more effective on prediction power. Through the Fourth Industrial Revolution, the current government and other overseas governments are working hard to integrate the system in everyday life of their nation and society. Yet the field of deep learning time series research for the financial industry is still insufficient. This is an initial study on deep learning time series algorithm analysis of corporate defaults. Therefore it is hoped that it will be used as a comparative analysis data for non-specialists who start a study combining financial data and deep learning time series algorithm.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.39 no.5
• /
• pp.57-75
• /
• 2011

The purpose of this study is to find ways of evaluating the suitability of sites being considered for development of different types of parks in the vicinity of yangmock-myun kyoung buk, where a large project(as large as about14.0$km^2$) has been planned. The results are as follows. Three surveys for selecting the assessment indicators were performed. ${\cdot}$ The first survey analyzed the importance of 23 selected assessment indicators based on a review of existing literature review and an on-the-spot research. ${\cdot}$ The second survey selected assessment indicators for each park type. ${\cdot}$ The third survey computed additive values of selected assessment indicators by the park types. It used a method of standardizing the average importance of indicators by making their sum equal to 10. These additive values were then multiplied by each grade of indicators to make a final evaluation. An evaluation of the site-suitability of park types was performed twice. The purpose of the first evaluation was to figure out how much each type met the minimum requirements targeted for all landscape types. The minimum requirements were derived by using a relative comparison between the standard of value rating of the assessment indicators, which was over the medium magnitude on the importance analysis, and the result of field research. A second evaluation estimated the targeted sites that met the minimum requirements. Value ratings of second assessment indicators were quantitatively divided as 1 to 3 grade and the evaluation scores were added, giving an additive value for each assessment indicator. The evaluation score on each park type was rated on a scale of 1 to 3 according to their averages, (from lowest to highest). Since this evaluation model of the site suitability on park types only focused on the 'face' of space in this study, additional analysis is necessary for setting the evaluation model and incorporating the overall impact of space, network connection and other factors, considering 'spot', 'line' and 'face' aspects of space.

• Geophysics and Geophysical Exploration
• /
• v.10 no.3
• /
• pp.173-182
• /
• 2007

It is well known that manganese nodules enriched with valuable metals are abundantly distributed in the abyssal plain area in the Clarion-Clipperton (C-C) fracture zone of the northeast Pacific. Previous studies using deep-sea camera (DSC) system reported different observations about the relation of seafloor topographic change and nodule abundance, and they were sometimes contradictory. Moreover, proper foundation on the estimation of DSC underwater position, was not introduced clearly. The variability of the mining condition of manganese nodule according to seafloor topography was examined in the Korea Deep Ocean Study (KODOS) area, located in the C-C zone. In this paper, it is suggested that the utilization of deep towing system such as DSC is very useful approach to whom are interested in analysing the distributional characteristics of manganese nodule filed and in selecting promising minable area. To this purpose, nodule abundance and detailed bathymetry were acquired using deep-sea camera system and multi-beam echo sounder, respectively on the seamount free abyssal hill area of southern part ($132^{\circ}10'W$, $9^{\circ}45'N$) in KODOS regime. Some reasonable assumptions were introduced to enhance the accuracy of estimated DSC sampling position. The accuracy in the result of estimated underwater position was verified indirectly through the comparison of measured abundances on the crossing point of neighboring DSC tracks. From the recorded seafloor images, not only nodules and sediments but cracks and cliffs could be also found frequently. The positions of these probable unminable area were calculated by use of the recorded time being encountered with them from the seafloor images of DSC. The results suggest that the unminable areas are mostly distributed on the slope sides and hill tops, where nodule collector can not travel over.

• Analytical Science and Technology
• /
• v.17 no.6
• /
• pp.496-513
• /
• 2004

This study was carried out to evaluate the performance of sampling and analytical methodology used for the measurement of toxic volatile organic compounds (VOCs) in the ambient air. VOCs were determined by the adsorbent tube sampling and automatic thermal desorption coupled with GC/MSD analysis. Target analytes were 33 compounds including major aromatic compounds such as BTEX, and halogenated compounds. The methodology was investigated with a wide range of different adsorbents which are commercially available and have been frequently adopted for the VOC measurement. A total of 10 adsorbents were tested in this study: 6 carbon-based adsorbents such as Carbotrap, Carbopack B, Carbosieve S-III, Carboxen 1000, Carbotrap C, Activated Charcoal; and 4 polymer-based adsorbents including Tenax, Porapak Q, Chromosorb 102, and Chromosorb 106. The sampling performance was evaluated with respect to the sampling capacity of VOCs with single-adsorbent and multiple-adsorbents methods for standard samples and field samples. As a result, the best adsorbents for single-adsorbent method in the sampling of toxic organic compounds (including benzene, toluene, xylenes etc.) appeared to be Carbotrap, Carbopack B and Tenax TA. On the other hand, Chromosorb 102, Chromosorb 106 and Porapak Q were found to be unsuitable adsorbents for VOC measurement based on thermal desorption method. Multi-adsorbent packings were evaluated with 4 carbon-based adsorbents, which classified by 3 combination sets of double adsorbents and 2 combination sets of triple adsorbents. The results indicated that the most suitable combination for toixc VOC measurements is Carbotrap C with Carbotrap. Multi-sorbents tubes packed with a strong adsorbent such as Carbosieve S-III or Carboxen 1000 were found to be relatively unsuitable for several compounds, not only owing to the effect of migration of adsorbed compounds from weaker adsorbent to stronger adsorbent, but to hydrophobic nature of the adsorbents. Therefore, it should be addressed that selection of a proper adsorbent (or combination of multi sorbents) is extremely important to obtain reliable data for the concentrations of toxic VOCs in indoor and outdoor environments.

• The Korean Journal of Emergency Medical Services
• /
• v.18 no.1
• /
• pp.83-94
• /
• 2014

Purpose : This study assessed the improvement of competency levels for participants, as well as their satisfaction from completion of the special international disaster response program. Methods : The program structure followed an intensive two-week course that included a combination of lectures, discussions, case studies, and field trips. "ICN Framework of Disaster Nursing Competencies" was used for designing the program. A pre-post survey was done to measure the change in the competencies of students and assess their satisfaction after finishing the program. Focus group interviews were also performed to further understand the attitudes of participants toward the disaster issues. Results : The overall pre-program test score for disaster competency was $2.18{\pm}0.68$ and the post-program test score was $6.30{\pm}0.84$, which showed statistically significant gains in all competency items (p <.001). The general satisfaction of participants with the program was quite high, demonstrated by a mean score of $4.5{\pm}0.51$. The benefits for students from program participation included increased knowledge and better understanding of the important roles of international organizations and NGOs. Conclusion : The international disaster education programs are necessary to provide an opportunity for students to increase their disaster competency. In addition, future development of a unified educational competency framework is also necessary.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.3
• /
• pp.51-62
• /
• 2020

The purpose of this study was to verify whether the quality of service provided by culture and arts education has a bearing on the service value of dance education, and to verify the role of the intention of reuse of culture and arts education participants in this relationship. The survey was conducted from October 1, 2019 to December 30, 2019, and a sample was collected from stratified sampling methods for the general public participating in culture and arts education. In order to verify the relationship between the independent variable and the dependent variable, multiple regression analysis was performed, and the role of the parameter in the relationship between the independent variable and the dependent variable was examined using the three-step intermediary regression analysis. The research results are as follows. First, as a result of analyzing the relationship between the sub-factors of service quality and emotional value, it was found that facilities and environmental services had the greatest impact. Second, the results of analyzing the relationship between the sub-factors of service quality and functional value showed that the most significant impact was on facilities and environmental services. Third, as a result of analyzing the relationship between the sub-factors of service quality and social values, it was found that facilities and environmental services had the greatest impact. Fourth, In the relationship between contents and instructor service and service value, the intention to reuse was found to have a full mediating effect. In addition, in the relationship between facility and environmental services and service value, the intention to reuse was found to have a partial mediating effect. Based on the quality of service of culture and arts education, this study suggested a way for dance education to work with the region.

• The Korean Journal of Applied Statistics
• /
• v.36 no.1
• /
• pp.49-62
• /
• 2023

Solar energy, which is rapidly increasing in proportion, is being continuously developed and invested. As the installation of new and renewable energy policy green new deal and home solar panels increases, the supply of solar energy in Korea is gradually expanding, and research on accurate demand prediction of power generation is actively underway. In addition, the importance of solar radiation prediction was identified in that solar radiation prediction is acting as a factor that most influences power generation demand prediction. In addition, this study can confirm the biggest difference in that it attempted to predict solar radiation using medium-term forecast weather data not used in previous studies. In this paper, we combined the multi-linear regression model, KNN, random fores, and SVR model and the clustering technique, K-means, to predict solar radiation by hour, by calculating the probability density function for each cluster. Before using medium-term forecast data, mean absolute error (MAE) and root mean squared error (RMSE) were used as indicators to compare model prediction results. The data were converted into daily data according to the medium-term forecast data format from March 1, 2017 to February 28, 2022. As a result of comparing the predictive performance of the model, the method showed the best performance by predicting daily solar radiation with random forest, classifying dates with similar climate factors, and calculating the probability density function of solar radiation by cluster. In addition, when the prediction results were checked after fitting the model to the medium-term forecast data using this methodology, it was confirmed that the prediction error increased by date. This seems to be due to a prediction error in the mid-term forecast weather data. In future studies, among the weather factors that can be used in the mid-term forecast data, studies that add exogenous variables such as precipitation or apply time series clustering techniques should be conducted.