• The Korean Journal of Applied Statistics
• /
• v.33 no.5
• /
• pp.615-625
• /
• 2020

The document-term frequency matrix is a term extracted from documents in which the group information exists in text mining. In this study, we generated the document-term frequency matrix for document classification according to research field. We applied the traditional term weighting function term frequency-inverse document frequency (TF-IDF) to the generated document-term frequency matrix. In addition, we applied term frequency-inverse gravity moment (TF-IGM). We also generated a document-keyword weighted matrix by extracting keywords to improve the document classification accuracy. Based on the keywords matrix extracted, we classify documents using a deep neural network. In order to find the optimal model in the deep neural network, the accuracy of document classification was verified by changing the number of hidden layers and hidden nodes. Consequently, the model with eight hidden layers showed the highest accuracy and all TF-IGM document classification accuracy (according to parameter changes) were higher than TF-IDF. In addition, the deep neural network was confirmed to have better accuracy than the support vector machine. Therefore, we propose a method to apply TF-IGM and a deep neural network in the document classification.

• Journal of Periodontal and Implant Science
• /
• v.32 no.1
• /
• pp.89-112
• /
• 2002

The earliest reports of the use of electrical energy to directly stimulate bone healing seem to be in 1853 from England, the techniques involved the introduction of direct current into the non-united fracture site percutaneously via metallic needles, with subsequent healing of the defect. One endpoint of the periodontal therapy is to generate structure lost by periodontal diseases. Several procedural advances may support regeneration of attachment, however, regeneration of alveolar bone does not occur consistently. Therefore, factors which stimulate bone repair are areas for research in periodontal reconstructive therapy. Effects of cytokines or growth factors on bone repair are examples of such areas. Another one is electrical current which occurs in bone naturally, so that such bone may be particularly susceptible to electrical therapy. The purposes of this study were to observe the effects of electrical stimulation on the normal periodontium, to determine whether the electricity is the useful means for periodontal regeneration or not. Forty rats weighted about 100 gram were used and divided into 4 groups, the first group, there was no electrical stimulation with the connection of electrodes only. In the second group, there was stimulated by the 10 mA during 10 minutes per a day, in the third group was stimulated by the 25 mA , and the fourth by the 50 mA. At 3, 5, 10 and 15 days post-appliance , two rats in each group were serially sacrificed. and the maxillae and the mandible processed to paraffin, and the specimens were prepared with Hematoxylin-Eosin stain for the light microscopic evaluation. The results of this study were as follows : 1. There was the distinct reversal line on the lingual alveolar crest, whereas a little changes in the labial alveolarcrest to the duration and amount of currents. 2. In 50 mA group, the cells were highly concentrated at the apex of anterior teeth, and was observed the necrotic tissue. In posterior root apex, the hypercementosis was appeared, and newly formed cementum layer has been increased continuously with the time. 3. The periodontal ligament fiber and Sharpey's fiber were arranged in order, and the bone trabeculae were increased as the experiment proceeded by, relatively the bone marrows were decreased. 4. In the pulp tissue, the blood vessels were increased with blood congestion in the experimetal specimens remarkably, and the dentinal tubules were obstructed . 5. The osteoblasts in alveolar bone proper had been showed highly activity, and also observed the formation of bone trabeculea. In the conclusion, it was suggested that the electrical stimulation has influence on the periodontium and the pulp tissue. However, there might be the injurious effects.

• Journal of Digital Convergence
• /
• v.15 no.7
• /
• pp.97-109
• /
• 2017

Domestic vehicle penetration rate is growing at 3% per year, but consumers are increasingly buying used cars due to steady price hikes Nevertheless, the used car export market is expected to decline due to import regulations of major countries and the low grade environment of Used car export complex. Therefore, this study using Fuzzy-AHP was aimed to find operational factors of Used car logistics complex and establish a practical management plan of Used car logistic complex in incheon port. Fuzzy-AHP is the method that can be calculated weight of multi-level criteria and change linguistic ambiguity of human to Fuzzy Number. So it's able to propose the realistic decision making alternatives. As a result of the literacture reviews, present study focused on the analysis of the present situation of the logistics of the used car and the activation of the complex, suggested the activation plan and activation of the logistics complex. In the analysis of operational factors, logistic complex cost factors were found to be the most important factors by recording the weighted value of 0.306 in the above factors. The detailed factors were as follows: rent, accessibility, and logistics site size. It is necessary to compute competitive rent for the highly-advanced used car logistics complex, and to realize the rental support policy and to consider designating the free trade zone. In addition, it is necessary to expand the access infrastructure and secure the scale of the company for overseas buyers, and it is necessary to improve the overall government laws and introduce IT system for the future.

• Journal of Cadastre & Land InformatiX
• /
• v.53 no.1
• /
• pp.83-105
• /
• 2023

A robot-friendly building certification system was established in 2022 to accommodate the growing number of service robots introduced into buildings. However, this system primarily targeted office buildings, with limitations in applying other functional architectures. To address this problem, we developed a certification model of a robot-friendly environment to extend the existing system to apartment complexes. Using focus group interviews and the analytic hierarchy process, we established 28 evaluating items categorized as (a) architecture and facility design, (b) networks and systems, (c) building operations management, and (d) support for robot activity and other services. These indicators were weighted based on their relative importance within and between categories, resulting in scores ranging from 1 to 18 points and a total of 176 points. According to evaluations with the 28 items, each apartment complex could be graded as "best," "excellent," or "general" based on its total achieved scores. This study is significant, as we present the world's first certification model of a robot-friendly environment for apartment complexes that considers human-robot interactions

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.35 no.3
• /
• pp.57-66
• /
• 2023

In order to understand the economic feasibility of an offshore wind farm, this paper analyzed the differences in LCOE (levelized cost of energy) according to the support type and construction method of the substructure in terms of LCOE and sensitivity analysis was conducted according to the main components of LCOE. As for the site to be studied, the Southwest Offshore Wind Farm was selected, and the capital expenditures were calculated according to the size of the offshore wind farm and the installation unit. As a result of the sensitivity analysis, major components showed high sensitivity to availability, turbine related cost, weighted average cost of capital and balance of system related cost. Moreover, the post-piling jacket method, which was representatively applied to the substructure of the offshore wind farm in Korea, was selected as a basic plan to calculate the capital expenditures, and then the capital expenditures of the pre-piling jacket method and the tripod method were calculated and compared. As a result of analyzing the LCOE, it was confirmed that the pre-piling jacket method of the supporting structure lowers the LCOE and improves economic feasibility as the installation number of turbines increases.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.127-137
• /
• 2019

Recidivism prediction has been a subject of constant research by experts since the early 1970s. But it has become more important as committed crimes by recidivist steadily increase. Especially, in the 1990s, after the US and Canada adopted the 'Recidivism Risk Assessment Report' as a decisive criterion during trial and parole screening, research on recidivism prediction became more active. And in the same period, empirical studies on 'Recidivism Factors' were started even at Korea. Even though most recidivism prediction studies have so far focused on factors of recidivism or the accuracy of recidivism prediction, it is important to minimize the prediction misclassification cost, because recidivism prediction has an asymmetric error cost structure. In general, the cost of misrecognizing people who do not cause recidivism to cause recidivism is lower than the cost of incorrectly classifying people who would cause recidivism. Because the former increases only the additional monitoring costs, while the latter increases the amount of social, and economic costs. Therefore, in this paper, we propose an XGBoost(eXtream Gradient Boosting; XGB) based recidivism prediction model considering asymmetric error cost. In the first step of the model, XGB, being recognized as high performance ensemble method in the field of data mining, was applied. And the results of XGB were compared with various prediction models such as LOGIT(logistic regression analysis), DT(decision trees), ANN(artificial neural networks), and SVM(support vector machines). In the next step, the threshold is optimized to minimize the total misclassification cost, which is the weighted average of FNE(False Negative Error) and FPE(False Positive Error). To verify the usefulness of the model, the model was applied to a real recidivism prediction dataset. As a result, it was confirmed that the XGB model not only showed better prediction accuracy than other prediction models but also reduced the cost of misclassification most effectively.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.23-46
• /
• 2017

Although there have been cases of evaluating the value of specific companies or projects which have centralized on developed countries in North America and Europe from the early 2000s, the system and methodology for estimating the economic value of individual technologies or patents has been activated on and on. Of course, there exist several online systems that qualitatively evaluate the technology's grade or the patent rating of the technology to be evaluated, as in 'KTRS' of the KIBO and 'SMART 3.1' of the Korea Invention Promotion Association. However, a web-based technology valuation system, referred to as 'STAR-Value system' that calculates the quantitative values of the subject technology for various purposes such as business feasibility analysis, investment attraction, tax/litigation, etc., has been officially opened and recently spreading. In this study, we introduce the type of methodology and evaluation model, reference information supporting these theories, and how database associated are utilized, focusing various modules and frameworks embedded in STAR-Value system. In particular, there are six valuation methods, including the discounted cash flow method (DCF), which is a representative one based on the income approach that anticipates future economic income to be valued at present, and the relief-from-royalty method, which calculates the present value of royalties' where we consider the contribution of the subject technology towards the business value created as the royalty rate. We look at how models and related support information (technology life, corporate (business) financial information, discount rate, industrial technology factors, etc.) can be used and linked in a intelligent manner. Based on the classification of information such as International Patent Classification (IPC) or Korea Standard Industry Classification (KSIC) for technology to be evaluated, the STAR-Value system automatically returns meta data such as technology cycle time (TCT), sales growth rate and profitability data of similar company or industry sector, weighted average cost of capital (WACC), indices of industrial technology factors, etc., and apply adjustment factors to them, so that the result of technology value calculation has high reliability and objectivity. Furthermore, if the information on the potential market size of the target technology and the market share of the commercialization subject refers to data-driven information, or if the estimated value range of similar technologies by industry sector is provided from the evaluation cases which are already completed and accumulated in database, the STAR-Value is anticipated that it will enable to present highly accurate value range in real time by intelligently linking various support modules. Including the explanation of the various valuation models and relevant primary variables as presented in this paper, the STAR-Value system intends to utilize more systematically and in a data-driven way by supporting the optimal model selection guideline module, intelligent technology value range reasoning module, and similar company selection based market share prediction module, etc. In addition, the research on the development and intelligence of the web-based STAR-Value system is significant in that it widely spread the web-based system that can be used in the validation and application to practices of the theoretical feasibility of the technology valuation field, and it is expected that it could be utilized in various fields of technology commercialization.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.39-55
• /
• 2019

Recently banks and large financial institutions have introduced lots of Robo-Advisor products. Robo-Advisor is a Robot to produce the optimal asset allocation portfolio for investors by using the financial engineering algorithms without any human intervention. Since the first introduction in Wall Street in 2008, the market size has grown to 60 billion dollars and is expected to expand to 2,000 billion dollars by 2020. Since Robo-Advisor algorithms suggest asset allocation output to investors, mathematical or statistical asset allocation strategies are applied. Mean variance optimization model developed by Markowitz is the typical asset allocation model. The model is a simple but quite intuitive portfolio strategy. For example, assets are allocated in order to minimize the risk on the portfolio while maximizing the expected return on the portfolio using optimization techniques. Despite its theoretical background, both academics and practitioners find that the standard mean variance optimization portfolio is very sensitive to the expected returns calculated by past price data. Corner solutions are often found to be allocated only to a few assets. The Black-Litterman Optimization model overcomes these problems by choosing a neutral Capital Asset Pricing Model equilibrium point. Implied equilibrium returns of each asset are derived from equilibrium market portfolio through reverse optimization. The Black-Litterman model uses a Bayesian approach to combine the subjective views on the price forecast of one or more assets with implied equilibrium returns, resulting a new estimates of risk and expected returns. These new estimates can produce optimal portfolio by the well-known Markowitz mean-variance optimization algorithm. If the investor does not have any views on his asset classes, the Black-Litterman optimization model produce the same portfolio as the market portfolio. What if the subjective views are incorrect? A survey on reports of stocks performance recommended by securities analysts show very poor results. Therefore the incorrect views combined with implied equilibrium returns may produce very poor portfolio output to the Black-Litterman model users. This paper suggests an objective investor views model based on Support Vector Machines(SVM), which have showed good performance results in stock price forecasting. SVM is a discriminative classifier defined by a separating hyper plane. The linear, radial basis and polynomial kernel functions are used to learn the hyper planes. Input variables for the SVM are returns, standard deviations, Stochastics %K and price parity degree for each asset class. SVM output returns expected stock price movements and their probabilities, which are used as input variables in the intelligent views model. The stock price movements are categorized by three phases; down, neutral and up. The expected stock returns make P matrix and their probability results are used in Q matrix. Implied equilibrium returns vector is combined with the intelligent views matrix, resulting the Black-Litterman optimal portfolio. For comparisons, Markowitz mean-variance optimization model and risk parity model are used. The value weighted market portfolio and equal weighted market portfolio are used as benchmark indexes. We collect the 8 KOSPI 200 sector indexes from January 2008 to December 2018 including 132 monthly index values. Training period is from 2008 to 2015 and testing period is from 2016 to 2018. Our suggested intelligent view model combined with implied equilibrium returns produced the optimal Black-Litterman portfolio. The out of sample period portfolio showed better performance compared with the well-known Markowitz mean-variance optimization portfolio, risk parity portfolio and market portfolio. The total return from 3 year-period Black-Litterman portfolio records 6.4%, which is the highest value. The maximum draw down is -20.8%, which is also the lowest value. Sharpe Ratio shows the highest value, 0.17. It measures the return to risk ratio. Overall, our suggested view model shows the possibility of replacing subjective analysts's views with objective view model for practitioners to apply the Robo-Advisor asset allocation algorithms in the real trading fields.

• Journal of Global Scholars of Marketing Science
• /
• v.20 no.2
• /
• pp.188-198
• /
• 2010

This study attempts to examine the influence that negative WOM (NWOM) has in an online context. It specifically focuses on the impact of the service failure description and the perceived intention of the communication provider on consumer evaluations of firm competence, attitude toward the firm, positive word of mouth and behavioral intentions. Studies of communication persuasiveness focus on "who says what; to whom; in which channel; with what effect (Chiu 2007)." In this research study, we examine electronic web posting, particularly focusing on two aspects of "what": the level of service failure communicated and perceived intention of the individual posting. It stands to reason electronic NWOM that appears to be trying to damage a product’s or firm's reputation will be viewed as more biased and will thus be considered as less credible. According to attribution theory, people search for the causes of events especially those that are negative and unexpected (Weiner 2006). Hennig-Thurau and Walsh (2003) state "since the reader has only limited knowledge and trust of the author of an online articulation the quality of the contribution could be expected to serve as a potent moderator of the articulation-behavior relationship. We therefore posit the following hypotheses: H1. Subjects exposed to electronic NWOM describing a high level of service failure will provide lower scores on measures of (a) firm competence, (b) attitude toward the firm, (c) positive word of mouth, and (d) behavioral intention than will subjects exposed to electronic NWOM describing a low level of service failure. H2. Subjects exposed to electronic NWOM with a warning intent will provide lower scores on measures of (a) firm competence, (b) attitude toward the firm, (c) positive word of mouth, and (d) behavioral intention than will subjects exposed to electronic NWOM with a vengeful intent. H3. Level of service failure in electronic NWOM will interact with the perceived intention of the electronic NWOM, such that there will be a decrease in mean response on measures of (a) firm competence, (b) attitude toward the firm, (c) positive word of mouth, and (d) behavioral intention from electronic NWOM with a warning intent to a vengeful intent. The main study involved a2 (service failure severity) x2 (NWOM with warning versus vengeful intent) factorial experiment. Stimuli were presented to subjects online using a mock online web posting. The scenario described a service failure associated with non-acceptance of a gift card in a brick-and-mortar retail establishment. A national sample was recruited through an online research firm. A total of 113 subjects participated in the study. A total of 104 surveys were analyzed. The scenario was perceived to be realistic with 92.3% giving the scenario a greater than average response. Manipulations were satisfactory. Measures were pre-tested and validated. Items were analyzed and found reliable and valid. MANOVA results found the multivariate interaction was not significant, allowing our interpretation to proceed to the main effects. Significant main effects were found for post intent and service failure severity. The post intent main effect was attributable to attitude toward the firm, positive word of mouth and behavioral intention. The service failure severity main effect was attributable to all four dependent variables: firm competence, attitude toward the firm, positive word of mouth and behavioral intention. Specifically, firm competence for electronic NWOM describing high severity of service failure was lower than electronic NWOM describing low severity of service failure. Attitude toward the firm for electronic NWOM describing high severity of service failure was lower than electronic NWOM describing low severity of service failure. Positive word of mouth for electronic NWOM describing high severity of service failure was lower than electronic NWOM describing low severity of service failure. Behavioral intention for electronic NWOM describing high severity of service failure was lower for electronic NWOM describing low severity of service failure. Therefore, H1a, H1b, H1c and H1d were all supported. In addition, attitude toward the firm for electronic NWOM with a warning intent was lower than electronic NWOM with a vengeful intent. Positive word of mouth for electronic NWOM with a warning intent was lower than electronic NWOM with a vengeful intent. Behavioral intention for electronic NWOM with a warning intent was lower than electronic NWOM with a vengeful intent. Thus, H2b, H2c and H2d were supported. However, H2a was not supported though results were in the hypothesized direction. Otherwise, there was no significant multivariate service failure severity by post intent interaction, nor was there a significant univariate service failure severity by post intent interaction for any of the three hypothesized variables. Thus, H3 was not supported for any of the four hypothesized variables. This study has research and managerial implications. The findings of this study support prior research that service failure severity impacts consumer perceptions, attitude, positive word of mouth and behavioral intentions (Weun et al. 2004). Of further relevance, this response is evidenced in the online context, suggesting the need for firms to engage in serious focused service recovery efforts. With respect to perceived intention of electronic NWOM, the findings support prior research suggesting reader's attributions of the intentions of a source influence the strength of its impact on perceptions, attitude, positive word of mouth and behavioral intentions. The implication for managers suggests while consumers do find online communications to be credible and influential, not all communications are weighted the same. A benefit of electronic WOM, even when it may be potentially damaging, is it can be monitored for potential problems and additionally offers the possibility of redress.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.47 no.6
• /
• pp.53-66
• /
• 2019

The purpose of this study was to suggest indicator-based selection and improvement plans for evaluating urban regeneration projects. First, we selected the indicators by conducting expert surveys and analysis of the responses received. Additionally, using the selected indicators, we analyzed the residents' opinions in Wongogae Village, where urban regeneration projects were in progress. Based on these, we suggested a plan to improve Wongogae Village. According to the study, we classified the urban regeneration evaluation indicators into 'Physical environment', 'Social environment' and 'Economic environment' according to their characteristics. We selected urban regeneration evaluation factors through the first expert survey and MCB analysis. As a result, we selected six factors for the 'Physical environment' category: 'Traffic and pedestrian environment', 'Residential (housing) environment', 'Safety and security environment', 'Greenspace', 'Landscape improvement' and 'Public space', In the 'Social environment' category, four factors were chosen: 'Resident participation', 'Community activation', 'Role of the local government and support centers' and 'Resident education' while for the 'Economic environment' category three factors were selected: 'Local economic revitalization', 'Creating an economy-based environment', 'Job creation'. Next, we conducted a second expert survey and carried out an AHP analysis using the selected evaluation factors to derive the overall weight for each. Among the evaluation factors for urban regeneration, the 'Residential (housing) environment' has the highest weighted value of 0.108, followed by 'Local economic revitalization' and 'Resident participation'. Lastly, the analysis of the residents' opinions of Wongogae Village using the urban regeneration evaluation factors, Parking environment', 'Maintenance of old houses and living environment', 'Environment for founding town and social enterprises', 'Improve commercial and business environment', 'Maintain and activate existing business' and 'Vitalizing small regional economies such as domestic handicrafts and side-job' had high overall importance, but low satisfaction, which means that it is necessary to improve the focus. Therefore, in order to improve the urban regeneration project in villages, it is necessary to improve the parking environment by expanding public parking lots, eliminate close houses, and idle lands, or open a school playground in the village for the residents. In addition, it is essential to encourage economic activities, such as fostering village enterprises and social enterprises in connection with cooperatives and allow for the selling of the products through resident activities, such as neighboring markets.