• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.6
• /
• pp.469-484
• /
• 2021

Rock mass classification results have a great influence on construction schedule and budget as well as tunnel stability in tunnel design. A total of 3,526 tunnels have been constructed in Korea and the associated techniques in tunnel design and construction have been continuously developed, however, not many studies have been performed on how to assess rock mass quality and grade more accurately. Thus, numerous cases show big differences in the results according to inspectors' experience and judgement. Hence, this study aims to suggest a more reliable rock mass classification (RMR) model using machine learning algorithms, which is surging in availability, through the analyses based on various rock and rock mass information collected from boring investigations. For this, 11 learning parameters (depth, rock type, RQD, electrical resistivity, UCS, V_p, V_s, Young's modulus, unit weight, Poisson's ratio, RMR) from 13 local tunnel cases were selected, 337 learning data sets as well as 60 test data sets were prepared, and 6 machine learning algorithms (DT, SVM, ANN, PCA & ANN, RF, XGBoost) were tested for various hyperparameters for each algorithm. The results show that the mean absolute errors in RMR value from five algorithms except Decision Tree were less than 8 and a Support Vector Machine model is the best model. The applicability of the model, established through this study, was confirmed and this prediction model can be applied for more reliable rock mass classification when additional various data is continuously cumulated.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.

• Industry Promotion Research
• /
• v.5 no.3
• /
• pp.145-155
• /
• 2020

Co-operatives are a deep-rooted organization that was first organized in Britain in the 19th century and spread to Europe and North America in the early 20th century and to the rest of the world from the mid-20th century. Cooperative in Italy are fraternal (friendly societies) separated from religion, and in the early days of socialism and the late 19th century Catholic Italy, but independent of activity. And the Church's social participation, as well as multiple personalities. Therefore, the purpose of this study is to study the laws and institutions of Italian cooperatives. And let's look at how the laws and systems of Italian co-operatives support society and the national economy. Specifically, firstly, based on prior research, the concept of co-operatives and the cooperative movement and social values are considered. Second, review the development process and characteristics of Italian co-operatives and the legal system. Third, I would like to analyze the case of Italian co-operatives. Fourth, suggest implications according to the results of the study. The results of the study suggested the following. First, the attitude such as attachment and sincerity of representatives and staff of village enterprises is very important. Second, all members of the organization should participate in decision making with empathy and attachment to the vision of the village enterprise. Third, it should be highly likely that village enterprises, which can draw capital from outside according to the needs of the organization, will generate higher economic results. Fourth, it is important to establish a model of mind enterprise by presenting factors and success factors in establishing a village enterprise based on cases and theories. In conclusion, Co-operatives should contribute to social contribution rather than economic profit-seeking.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.17 no.2
• /
• pp.72-81
• /
• 2014

As big data are one of main issues in the recent days, the interests on their technologies are also increasing. Among several technological bases, this study focuses on data visualization and R based on open source. In general, the term of data visualization can be summarized as the web technologies for constructing, manipulating and displaying various types of graphic objects in the interactive mode. R is an operating environment or a language for statistical data analysis from basic to advanced level. In this study, a web application with these technological aspects and components is newly implemented and exemplified with data visualization for geo-based open data provided by public organizations or government agencies. This application model does not need users' data building or proprietary software installation. Futhermore it is designed for users in the geo-spatial application field with less experiences and little knowledges about R. The results of data visualization by this application can support decision making process of web users accessible to this service. It is expected that the more practical and various applications with R-based geo-statistical analysis functions and complex operations linked to big data contribute to expanding the scope and the range of the geo-spatial application.

• Journal of Bio-Environment Control
• /
• v.5 no.2
• /
• pp.174-186
• /
• 1996

This study was carried out in order to understand the plan, design, constructing and actual condition of management of modernized horticultural facilities in Kyungpook Province which had been constructed from 1992 to 1995 funded by Government support. The aim of this study is to provide reference data for success of the forth project. It was performed by making up a question about driving of project and management condition of equipment after constructing. The results obtained from this study are as follows: 1. 73.5% of facilities horticulture farmhouse recognized that the prospect of greenhouse is bright, but 92.5% of the farmhouse also recognised that they need technical consultation on protected horticulture farming. Therefore, technical educations would must be enhanced about foundation of greenhouse and cultivation technique. 2. The holding times of explanatory meetings, cause of understanding to farmhouse, were one or two times in greenhouse construction, and 62.5% of the farmhouse expressed the insufficiency at the explanation and educational data. For this reason, it was judged that the construction contract had been delayed more than 5 months in 49.3% of the farmhouse after the decision of project budget. 3. In constructing after a contract, the rates of construction delay is 53.4% and defect occurrence is 41.1%. The biggest reasons of construction delay was insufficiency of worker and materials supply. Each percentage is 29.1%. And the reason of defect occurrence is badness of machinery equipment(62.9% ). 4. In management of greenhouse, a pipe-constructed plastic film greenhouse changes plastic film every one and three years because of sticking dust on plastic film. It was needed to about in cleaning technique of coverings. Because that used 3-5 years only half of the expected life span. 5. The order of broken rating in the subsidiary equipment is like this lollop ventilator (42.8%), a general control system(33.3%) especially, in the case of a general control system, the rate of all family can control is 52.7%. so, it is time to develop easy control equipment which every one could use as soon as possible. 6. When choose heat generator as decide capacity, the most priority is the mount of heat generator the percent is 45.5% heat generator and as decide model, the private purchase's percent is 77.3%. It is higher than a public bidding heat generator the percent is 22.7% heat generator when it compare with a public bidding. In the case of $CO_2$ generator, using rate is only 19.0%. The using rate is very low, so it needs education how to use depends on the way of the subsidiary equipment. 7. In the case of seedlings, it is asked to use factory-processed seedling effectively. because it's difficult to get security of labors(58.8%), hoped crops (55.9%) access same crops(29.4%) much more and changing of crops depends on market situation. that is the main reason the lack of knowhow.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.6
• /
• pp.636-645
• /
• 2017

An information system for defense technology information management should assist the user's work and manager's decision-making by managing and timely providing data held by defense-related organizations. This paper proposes a plan for constructing an advance defense technology information service. DTiMS concentrates on the collection and management of defense science technology information but not its distribution. Therefore, it is important that the advanced distribution service model be established on the concept of total life cycle management that utilizes user information, so that it can provide proper information to each user in the defense field who require the information processed by their roles. This study examined the management of information and operation method through advanced case analysis. In addition, the analysis of existing services revealed improvements in the management of an information standard, the trace ability of information and usability, and improved user-interface. The proposed development direction was implemented by deploying the advanced DTiMS. Therefore, it is expected that the proposed methodology will contribute to the weapon system total life cycle, and will support defense technology planning, and R&D decisions.

• Journal of Distribution Science
• /
• v.13 no.2
• /
• pp.85-94
• /
• 2015

Purpose - This study attempts to examine the impacts of consumers' perceived service convenience of retailers on various service performance metrics such as service quality and customer satisfaction. It also tries to investigate differences in the importance of service convenience dimensions on service performance between a department store and a general super market. Research design, data, and methodology - The four hypotheses in this study were proposed and tested. Two hypotheses were on the causal relationships between service convenience dimensions and service performances (service quality and customer satisfaction). The other two hypotheses were on comparisons for the effects of convenience dimensions on service quality and customer satisfaction between department stores and general super markets. To test the hypotheses, three department store chains (Hyundai, Lotte, and Shinsegae department Store) and three general super markets (E-mart, Homeplus, and Lotte mart) were involved. Overall, 510 usable responses were used. The data were analyzed using regression analysis. Results - The results largely support the hypothesized relationships of the proposed model. The results show that access convenience, transaction convenience, benefit convenience, and post-benefit convenience have positive influences on service quality, whereas decision convenience, access convenience, transaction convenience, benefit convenience, and post-benefit convenience have positive effects on customer satisfaction. Furthermore, the results show that there are differences between department stores and general super markets in the effects of benefit convenience and post-benefit convenience on service quality as well as the effects of transaction convenience and post-benefit convenience on customer satisfaction. Conclusions - The concept of service convenience is important in retail environments but little is known about this topic in retail literature. Specially, while service convenience dimensions have different impacts on service performance in distinct retail environments, there has been little investigation or comparison between retail types as regards service convenience. This study is the first to test the differences between distinct retail types (department stores and general super markets) on the service convenience-service performance links. Managerially, the findings of this study suggest that the service convenience management of retailers is an important part of successful service performance management. Because it is most important that both department stores and general super markets enhance benefit convenience to improve service performance, managers of both store types need to invest their resources to reduce consumers' perceived time and effort expenditures to experience the retailer's core benefits. Therefore, the results of this study suggest that retail stores should spend human and financial resources to enhance customer perceptions of service convenience, while also considering what constitutes the service outcome in the consumer's mind. Furthermore, the findings suggest that managers need to use different service convenience management tactics in department stores and general super markets. Specifically, managers in general super markets should pay more attention to benefit convenience and transaction convenience to achieve better service performance whereas managers in department stores should concentrate on post-benefit convenience to create customers' positive evaluation.

• Journal of Distribution Science
• /
• v.12 no.10
• /
• pp.75-84
• /
• 2014

Purpose - This article aims to examine whether the stock issuance of firms in the retail industry follows Myers' (1984) pecking order theory, which is based on information asymmetry. According to the pecking order model, firms have a sequence of financing decisions, of which the first choice is to use retained earnings, the second one is to get into safe debt, the next involves risky debt, and the last involves finance with outside equity. Since the 2000s, the polarization of the LEs (Large enterprises) and SMEs (Small and Medium Enterprises) arose in the retail industry. The LEs exhibited an improvement in growth and profitability, whereas SMEs had a tendency to degenerate. This study contributes to corroborating the features of financing decisions in the retail industry distinguished from the other industries. Research design, data, and methodology - This study considers the stocks listed on the KOSPI and KOSDAQ markets from 1991 to 2013, and is more concentrated on the stocks in the retail industry. The data were collected from the financial information company, WISEfn. The empirical analysis is conducted by employing two measures of net equity issues (and), which were introduced in Fama and French (2005), and can be calculated from firms' accounting information. All variables are generated as the aggregate value of the numerator divided by aggregate assets, which, in effect, treats the entire sample as a single firm. Substantially, the financing decisions of the firms were analyzed by examining how often and under what circumstances firms issue and repurchase equity. Then, this study compares the features of the retail industry with those of the other industries. Results - The proportion of sample firms that show annual net stock issues reaching the level of the year's average was 54.33% for the 1990s, and fell to 39.93% per year for the 2000s. In detail, the fraction of the small firms actually increases from 45.08% to 51.04%, whereas that of large firms shows a dramatic decline from 58.94% to 24.76%. Considering the fact that the large firms' rapid increase in growth after the 2000s may lead to an increase in equity issues, this result is rather surprising. Meanwhile, net stock repurchases of assets are considerably disproportionate between the large (-50.11%) and the small firms (-15.66%) for the 2000s. Conclusions - Stock issuance of retail firms is not in line with the traditional seasoned equity offering based on information asymmetry. The net stock issuance of the small firms in the retail industry can be interpreted as part of an effort to reorganize business and solicit new investment to resolve degenerating business performance. For large firms, on the other hand, the net repurchase can be regarded as part of an effort to rearrange business for efficiency and amplifying synergy across business sections through spin-off. These results can help the government establish a support policy on retail industry according to size.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.2
• /
• pp.67-78
• /
• 2006

Local governments began to construct geographic information system to improve government productivity and performance. In support, central government organized a national commission for GIS. The master plan by NGIS has been the base for local government to participate in the construction of GIS at the local level in the under ground facilities management including water and sewers. The challenge faced by sewer facility managers includes controlling 'data accuracy'. The input for sewer data handling for efficient performance in local government requires accurate data. However data manipulation to get the 'good quality' data can be burdensome. Thus, the aim of this research is to provide the appropriate tool to guarantee the high quality of digital data in sewer facility management. It is helpful to pass the data examination by government as well as to insure confidence of decision and data analysis works in local government. In this research, error types of sewer data were classified and pointed the limitation of traditional examination methods. Thus this research suggested more improved method for finding and correcting errors in data input using sewer volume analysis and prediction model as immigrating sewer facility management work to Geographic Information System.

• Journal of Environmental Health Sciences
• /
• v.43 no.3
• /
• pp.223-232
• /
• 2017

Objectives: In response to increased interest in the safety of children's products, a risk management system is being prepared through exposure assessment of hazardous chemicals. To estimate exposure levels, risk assessors are using deterministic and probabilistic approaches to statistical methodology and a commercialized Monte Carlo simulation based on tools (MCTool) to efficiently support calculation of the probability density functions. This study was conducted to analyze and discuss the usage patterns and problems associated with the results of these two approaches and MCTools used in the case of probabilistic approaches by reviewing research reports related to exposure assessment for children's products. Methods: We collected six research reports on exposure and risk assessment of children's products and summarized the deterministic results and corresponding underlying distributions for exposure dose and concentration results estimated through deterministic and probabilistic approaches. We focused on mechanisms and differences in the MCTools used for decision making with probabilistic distributions to validate the simulation adequacy in detail. Results: The estimation results of exposure dose and concentration from the deterministic approaches were 0.19-3.98 times higher than the results from the probabilistic approach. For the probabilistic approach, the use of lognormal, Student's T, and Weibull distributions had the highest frequency as underlying distributions of the input parameters. However, we could not examine the reasons for the selection of each distribution because of the absence of test-statistics. In addition, there were some cases estimating the discrete probability distribution model as the underlying distribution for continuous variables, such as weight. To find the cause of abnormal simulations, we applied two MCTools used for all reports and described the improper usage routes of MCTools. Conclusions: For transparent and realistic exposure assessment, it is necessary to 1) establish standardized guidelines for the proper use of the two statistical approaches, including notes by MCTool and 2) consider the development of a new software tool with proper configurations and features specialized for risk assessment. Such guidelines and software will make exposure assessment more user-friendly, consistent, and rapid in the future.