• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.149-169
• /
• 2020

"The Urban Renewal New Deal project", one of the government's major national projects, is about developing underdeveloped areas by investing 50 trillion won in 100 locations on the first year and 500 over the next four years. This project is drawing keen attention from the media and local governments. However, the project model which fails to reflect the original characteristics of the area as it divides project area into five categories: "Our Neighborhood Restoration, Housing Maintenance Support Type, General Neighborhood Type, Central Urban Type, and Economic Base Type," According to keywords for successful urban regeneration in Korea, "resident participation," "regional specialization," "ministerial cooperation" and "public-private cooperation", when local governments propose urban regeneration projects to the government, they can see that it is most important to accurately understand the characteristics of the city and push ahead with the projects in a way that suits the characteristics of the city with the help of local residents and private companies. In addition, considering the gentrification problem, which is one of the side effects of urban regeneration projects, it is important to select and implement urban regeneration types suitable for the characteristics of the area. In order to supplement the limitations of the 'Urban Regeneration New Deal Project' methodology, this study aims to propose a system that recommends urban regeneration types suitable for urban regeneration sites by utilizing various machine learning algorithms, referring to the urban regeneration types of the '2025 Seoul Metropolitan Government Urban Regeneration Strategy Plan' promoted based on regional characteristics. There are four types of urban regeneration in Seoul: "Low-use Low-Level Development, Abandonment, Deteriorated Housing, and Specialization of Historical and Cultural Resources" (Shon and Park, 2017). In order to identify regional characteristics, approximately 100,000 text data were collected for 22 regions where the project was carried out for a total of four types of urban regeneration. Using the collected data, we drew key keywords for each region according to the type of urban regeneration and conducted topic modeling to explore whether there were differences between types. As a result, it was confirmed that a number of topics related to real estate and economy appeared in old residential areas, and in the case of declining and underdeveloped areas, topics reflecting the characteristics of areas where industrial activities were active in the past appeared. In the case of the historical and cultural resource area, since it is an area that contains traces of the past, many keywords related to the government appeared. Therefore, it was possible to confirm political topics and cultural topics resulting from various events. Finally, in the case of low-use and under-developed areas, many topics on real estate and accessibility are emerging, so accessibility is good. It mainly had the characteristics of a region where development is planned or is likely to be developed. Furthermore, a model was implemented that proposes urban regeneration types tailored to regional characteristics for regions other than Seoul. Machine learning technology was used to implement the model, and training data and test data were randomly extracted at an 8:2 ratio and used. In order to compare the performance between various models, the input variables are set in two ways: Count Vector and TF-IDF Vector, and as Classifier, there are 5 types of SVM (Support Vector Machine), Decision Tree, Random Forest, Logistic Regression, and Gradient Boosting. By applying it, performance comparison for a total of 10 models was conducted. The model with the highest performance was the Gradient Boosting method using TF-IDF Vector input data, and the accuracy was 97%. Therefore, the recommendation system proposed in this study is expected to recommend urban regeneration types based on the regional characteristics of new business sites in the process of carrying out urban regeneration projects."

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.239-251
• /
• 2019

Statistical methods such as moving averages, Kalman filtering, exponential smoothing, regression analysis, and ARIMA (autoregressive integrated moving average) have been used for stock market predictions. However, these statistical methods have not produced superior performances. In recent years, machine learning techniques have been widely used in stock market predictions, including artificial neural network, SVM, and genetic algorithm. In particular, a case-based reasoning method, known as k-nearest neighbor is also widely used for stock price prediction. Case based reasoning retrieves several similar cases from previous cases when a new problem occurs, and combines the class labels of similar cases to create a classification for the new problem. However, case based reasoning has some problems. First, case based reasoning has a tendency to search for a fixed number of neighbors in the observation space and always selects the same number of neighbors rather than the best similar neighbors for the target case. So, case based reasoning may have to take into account more cases even when there are fewer cases applicable depending on the subject. Second, case based reasoning may select neighbors that are far away from the target case. Thus, case based reasoning does not guarantee an optimal pseudo-neighborhood for various target cases, and the predictability can be degraded due to a deviation from the desired similar neighbor. This paper examines how the size of learning data affects stock price predictability through k-nearest neighbor and compares the predictability of k-nearest neighbor with the random walk model according to the size of the learning data and the number of neighbors. In this study, Samsung electronics stock prices were predicted by dividing the learning dataset into two types. For the prediction of next day's closing price, we used four variables: opening value, daily high, daily low, and daily close. In the first experiment, data from January 1, 2000 to December 31, 2017 were used for the learning process. In the second experiment, data from January 1, 2015 to December 31, 2017 were used for the learning process. The test data is from January 1, 2018 to August 31, 2018 for both experiments. We compared the performance of k-NN with the random walk model using the two learning dataset. The mean absolute percentage error (MAPE) was 1.3497 for the random walk model and 1.3570 for the k-NN for the first experiment when the learning data was small. However, the mean absolute percentage error (MAPE) for the random walk model was 1.3497 and the k-NN was 1.2928 for the second experiment when the learning data was large. These results show that the prediction power when more learning data are used is higher than when less learning data are used. Also, this paper shows that k-NN generally produces a better predictive power than random walk model for larger learning datasets and does not when the learning dataset is relatively small. Future studies need to consider macroeconomic variables related to stock price forecasting including opening price, low price, high price, and closing price. Also, to produce better results, it is recommended that the k-nearest neighbor needs to find nearest neighbors using the second step filtering method considering fundamental economic variables as well as a sufficient amount of learning data.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.19 no.3
• /
• pp.107-115
• /
• 2009

Particular interest in the role of convection in vapor crystal growth has arisen since some single crystals under high gravity acceleration of $10g_0$ appear considerably larger than those under normal gravity acceleration ($1g_0$). For both ${\Delta}T=60\;K$ and 90 K, the mass flux increases by a factor of 3 with increasing the gravity acceleration from $1g_0$ up to $10g_0$. On the other hand, for ${\Delta}T=30\;K$, the flux is increased by a factor of 1.36 for the range of $1g_0{\leq}g{\leq}10g_0$. The maximum growth rates for $1g_0$, $4g_0$, $10g_0$ appear approximately in the neighborhood of y = 0.5, and the growth rates shows asymmetrical patterns, which indicate the occurrence of either one single or more than one convective cell. The maximum growth rate for $10g_0$ is nearly greater than that for $1g_0$ by a factor of 2.0 at $P_B=20\;Torr$. For three different gravity levels of $1g_0$, $4g_0$ and $10g_0$, the maximum growth rates are greater than the minimum rates by a factor of nearly 3.0, based on $P_B=20\;Torr$. The mass flux increases with increasing the gravity acceleration, for $1g_0{\leq}g_y{\leq}10g_0$, and decreases with increasing the partial pressure of component B, xenon (Xe), $P_B$. The $|U|_{max}$ is directly proportional to the gravity acceleration for $20\;Torr{\leq}P_B{\leq}300\;Torr$. As the partial pressure of $P_B$ (Torr) decreases from 300 Torr to 20 Torr, the slopes of the $|U|_{max}s$ versus the gravity accelerations increase from 0.1 sec to 0.17 sec. The mass flux of $Hg_2Cl_2$ is exponentially decayed with increasing the partial pressure of component B, $P_B$ (Torr) from 20 Torr up to 300 Torr.

• Journal of the Korean Society for Library and Information Science
• /
• v.47 no.2
• /
• pp.25-43
• /
• 2013

South Korea has fewer public libraries than other developed nations of OECD. This calls for a more diverse role of school libraries in the geographically isolated areas. School libraries should provides services for not only its students and faculty, but also the surrounding neighborhood as a part of cultural community. Based on the needs for an expanded role of school libraries, this research aims to identify the necessary factors for school libraries to provide services to their local residents. Two things should be identified for this research. First, we should confirm the necessity of policies that provide library services to local residents of school libraries. Second, we should propose a way to have the libraries as a part of cultural community where meet the information and cultural demand of their local residents. The study surveyed users, school principals and working-level staff members of cultural communities in order to study the two questions. These groups were from Uri-school Village Library, which is supported by the NHN Culture Foundation. Through the survey, the research confirmed the need for a consistent outside assistance, job training, open door policy for local residents and diverse library services in order for school libraries to serve their local community.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.46 no.3
• /
• pp.36-45
• /
• 2018

Cemeteries in the United States are frequently observed near residential areas in cities even though they are spaces for the dead. However, it has not been fully studied when and how cemeteries were formed in the process of urbanization. Thus, this research aimed to investigate the spatial structure and historical change of cemeteries in Seattle due to urbanization, focusing on the contextual relationship between cemeteries and the surroundings according to two time periods: the early formation period of cemeteries in Seattle and the current period. For this, a mixed method was taken in this paper that combined historical analysis based on old references and historic maps with cluster analysis using GIS. In conclusion, the research found that early cemeteries of Seattle in downtown areas were introduced as by-products of urban formation, but the cemeteries in the suburbs were established ahead of urban growth and neighborhood development. In addition, Seattle's cemeteries not only showed a similar locational pattern to Seattle's shopping centers, but also were positively associated with population distribution given the Hot Spot Analysis. In other words, Seattle's cemeteries were originally located in rural areas, but later came to be located in urban areas, sustaining the landscape of American rural cemeteries.

• Journal of Korean Society of Rural Planning
• /
• v.20 no.2
• /
• pp.71-80
• /
• 2014

This study intended for Cheongryongsan Community Garden in Gwanak-gu, one of the demonstration places for 'Community Garden' Project recently implemented by the Seoul Government. This study had two major purposes: investigating the current status of the management and usage and identifying its characteristics; investigating users' awareness to consider the construction and operation directions of sustainable community gardens. This study was conducted based on several surveys such as an investigation into the spatial configuration and the management system of parks through a field study, a use survey through a questionnaire survey for vegetable garden users and an awareness survey about the construction direction of gardens direction preferred by users through the analytical hierarchy process (AHP). As a result of a questionnaire survey for vegetable garden users, the usage status was summarized as follows: Considering the common trends in the 2012 and the 2013 user survey, women used Cheongryongsan Vegetable Garden more than men. Over fifties used it most of all users. Users were mostly neighborhood residents. They used to visit there three to five times a week and stayed for about 30 minutes to one hour. Users differently responded to the question related to the order of priority for the use of the garden in the 2012 and the 2013 survey. They had increasingly used it for individuals' production activities more than social exchanges. As a result of making an AHP analysis for general park users, vegetable garden users there were clear differences in the targets which each subject put emphasis on in relation to the construction and operation of vegetable gardens. General park users recognized a vegetable garden as a park where park functions and the functions of the vegetable garden coexisted. On the other hand, vegetable garden users viewed it as a space where they attached importance to the functions of the vegetable garden like an allotment. Last, this study contemplated subjects related to the construction and operation of vegetable gardens which had to be considered in the future. Vegetable gardens tended to be biased as personal hobby places. It was viewed that the main reason was insufficient support activities for vegetable garden education and exchange programs originally planned when vegetable gardens had been constructed. Vegetable garden users recognized vegetable gardens as places for individuals' farming activities like allotments. For the desirable operation of vegetable gardens, it would be necessary to give priority to the park management before the production activities in individuals' vegetable gardens. The important role of the government would be to build the base through the provision of education and opportunities so that a local resident organization could actively participate in the management of a vegetable garden after a vegetable garden was constructed. It would be necessary to make a use survey and an awareness survey for users conducted in this study on a regular basis because the surveys could be important basic data in the decision-making process for the sustainable operations of the vegetable garden.

• Environmental and Resource Economics Review
• /
• v.21 no.4
• /
• pp.999-1024
• /
• 2012

The Purpose of this study was to assess the willingness to pay(WTP) for the new road construction plan(slip road of urban highway which was advertising extensively to reduce the time to the core of metropolitan area) on housing prices using contingent valuation method(CVM). And this study was an empirical study which was based on the consciousness of residents whose apartment was within the Suwon Si's new plan of 47th road construction zone. In this study, it was revealed that the resident's WTP for the plan of new road construction which was built on the neighborhood of apartment was within the 10 percent of housing prices that was similar to the standard declared price of MLTM(Ministry of Land, Transport and Maritime Affairs). And also revealed that the difference of sale prices of real estate company was 24 percent. The statistical assessment results show that both the resident's characteristic variables such as gender, incomes, size of apartment and the accessability variables such as distance to parks, schools, department stores, living facilities were positive effects on the prices of apartments significantly. Finally, the house has depreciated than that of MLTM and WTO since torpedoed the road construction plan. These results imply that, we have to take capital appreciation of the property into account due to road construction since the accessibility was very significantly positive internal effects on the apartment housing prices.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.8
• /
• pp.167-175
• /
• 2018

The purpose of this study was to investigate the status and the factors associated with death preparation of in Community-Dwelling Elderlys. This study was secondary analysis using with 2014 National Survey on the Elderly in Korea. The number of respondents were 10,281. Data were analyzed with the x2 test, t-test and multiple logistic regression using the SPSS/WIN 23.0 program. 37.7% of respondents had done death preparation. The factors associated with death preparation were sex(CI=1.02-1.25), age(CI=1.90-2.28), living area(CI=1.21-1.45), education level(CI=1.16-1.42), spouse status(CI=1.50-3.22), economic level(CI=1.13-1.36), limit of activity(CI=1.11-1.40), life satisfaction(economic satisfaction(CI=1.17-1.35), children relationship satisfaction(CI=1.25-1.43), friends and neighborhood relationship satisfaction(CI=1.10-1.28)). Based on these results, it is necessary to develop programs for reinforcing elder's psychological death preparation for elders in community organization. To consider elder's characteristics like gender and living area.

• The Journal of the Korea Contents Association
• /
• v.18 no.7
• /
• pp.28-37
• /
• 2018

It is necessary to produce and maintain interior lighting design reasonably and actively. Based on the lighting design applicable to interior design, the purpose of this study is to take into consideration the public design of public facilities installed in neighborhood parks and thereby to suggest a module-type variable interior lighting product design for reasonable use. To achieve that, relevant studies were reviewed to find the basic concepts of a module and the best cases of interior lighting applicable to interior design. To draw a new concept of the lighting design to which the concept of a module is applied, this study suggested the design direction for practical product development and a module-type design featuring easy process, product storage, assembly, and management, analyzed the reasonable maintenance direction for the development of lighting design, and proposed a case of design development applicable to the development of a new product design. Through cognitive strategy process, the design was made. This process, as a conceptual strategy, included the step of interior environment analysis, the step of lighting maintenance, the step of variable mechanism, and the step of emotional activation. These steps were connected with formative beauty of design so as to suggest a MLD(Module Lamp Design) strategy. In this way, this study tried to connect humans' free application for a space to a module product and to apply humans' visual approach and free conceptual value to MLD cognitive strategy design process for development.

• Journal of Distribution Science
• /
• v.12 no.11
• /
• pp.55-65
• /
• 2014

Purpose - This study aims to investigate the process of political changes in Japan, which has introduced regulatory policies for large-scale retail stores since the 1930s, as well as the examples, and suggests improvement schemes for our policies in Korea, which imposes restrictions on business hours and forced holidays in accordance with the current Distribution Industry Development Act. Research design, data, and methodology - After examining the political change processes related to large-scale retail stores in japan, this study analyzes individually regulated cases based on the ordinances enacted by each local government. Through case analysis in Japan, this study makes political suggestions that may be helpful for our country substantially. Results - Since there is an obvious possibility that our economic restrictions on business hours and mandatory holidays do not coincide with WTO GATS, it is necessary for large-scale distributors to introduce new social and environmental regulations similar to Japan, rather than imposing controls to restrict free competition and also introduce a policy to induce cooperation with small businesses for the advancement of the distribution industry. Thus, it is desirable to take measures on noise, waste, traffic, and parking for the preservation of the living environment in the surroundings when building new large-scale retail stores. It is also important to establish measures to improve the welfare of neighborhood residents and consumers, create a pleasant urban environment, and make it mandatory to make presentations at public hearings among residents. Furthermore, it should be mandatory to establish regional contribution plans when a retail store is established, and take measures to solve various civil complaints or problems that may occur after entering the market. Moreover, it is desirable for large-scale retail stores that entered the market to induce cooperation in performing various activities in the area with a strong sense that they are all members of the local economy. Conclusions - If introducing social regulations like in Japan, there is probably an advantage that the conflicts seen when large-scale retail stores enter the market are absorbed by adjusting the persons concerned within the established institution in order to establish a field to solve such conflicts systematically. In contrast, there are still concerns regarding chaotic operation without any active attempts to have a conversation with large-scale retail stores and local small merchants due to a sharp conflict among the persons concerned, and if it is a briefing session without any decision of the restrictions on their opening itself, there may be doubts with regard to their effectiveness. Moreover, if the de facto opening is restricted by the introduction of such a briefing session procedure, the choice of whether to protect the existing rights of large-scale retail stores might become problematic. However, such problems could be minimized in a way by forming a separate consultative group for all persons concerned including residents, local governments, professionals, civic organizations, small merchants, and massive retail store-related persons.