• Journal of Korea Society of Digital Industry and Information Management
• /
• v.5 no.1
• /
• pp.9-22
• /
• 2009

This paper is an explanation of a design and an implementation of Web 2.0 online travel agency system for frequent decision-making. On the Web 2.0 travel agency system, optimized information is obtained by applying data mining technology such as association rules, decision trees, and neural networks, and this system is a unified system that consists of the block systems of hotels, ground traffic, and flights in tour packages of a travel agency system. Furthermore, it is implemented to manage the system that is not for the administrator of a travel agency system, but for users or communities that use the system need their own information. The expected effect of this system is to maximize the investment company's efficiency through a new-concept interest model created by B2C customers, and also B2B small and medium-sized travel agencies adopting the system. As a result, it is a system that stimulates dormant customer activity and prevents good customers from leaving by maximizing the merit and capacity of the existed web site for marketing. Moreover, this system is also a model for people who plan customized travel agency business, and will show a way for the domestic and international travel agency industry's globalization.

• IE interfaces
• /
• v.12 no.4
• /
• pp.551-556
• /
• 1999

In this paper, we compare the performance of three data mining classification algorithms(neural network, decision tree, logistic regression) in consideration of various characteristics of categorical input and output data. $2^{4-1}$. 3 fractional factorial design is used to simulate the comparison situation where factors used are (1) the categorical ratio of input variables, (2) the complexity of functional relationship between the output and input variables, (3) the size of randomness in the relationship, (4) the categorical ratio of an output variable, and (5) the classification algorithm. Experimental study results indicate the following: decision tree performs better than the others when the relationship between output and input variables is simple while logistic regression is better when the other way is around; and neural network appears a better choice than the others when the randomness in the relationship is relatively large. We also use Taguchi design to improve the practicality of our study results by letting the relationship between the output and input variables as a noise factor. As a result, the classification accuracy of neural network and decision tree turns out to be higher than that of logistic regression, when the categorical proportion of the output variable is even.

• Journal of the Society of Naval Architects of Korea
• /
• v.42 no.5 s.143
• /
• pp.534-541
• /
• 2005

Until now, Korean shipyards have accumulated a great amount of data. But they do not have appropriate tools to utilize the data in practical works. Engineering data contains experts' experience and know-how in its own. It is very useful to extract knowledge or information from the accumulated existing data by using data mining technique This paper treats an evolutionary computation based on genetic programming (GP), which can be one of the components to realize data mining. The paper deals with linear models of GP for the regression or approximation problem when given learning samples are not sufficient. The linear model, which is a function of unknown parameters, is built through extracting all possible base functions from the standard GP tree by utilizing the symbolic processing algorithm. In addition to a standard linear model consisting of mathematic functions, one variant form of a linear model, which can be built using low order Taylor series and can be converted into the standard form of a polynomial, is considered in this paper. The suggested model can be utilized as a designing tool to predict design parameters with small accumulated data.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.18 no.2
• /
• pp.1-11
• /
• 2019

The purpose of this study is to make objective decisions in the use of closed schools through the development of utilization indicators for the efficient use of closed schools, which is expected to increase continuously. The research phase was largely carried out by drawing preliminary indicators for use in closed schools, drawing final indicators using big data, and quantifying indicators, and finally objectifying them through quantification. The institution intends to apply and verify the facility based on future indicators. This study has implications for the application of big data analysis methods that have not been attempted in planning and research for the use of closed school facilities to date.

• International Journal of Computer Science & Network Security
• /
• v.22 no.8
• /
• pp.404-412
• /
• 2022

The development in the field of the internet of things (IoT) have improved the quality of the life and also strengthened different areas in the society. All cities across the world are seeking to become smarter. The creation of a smart parking system is the essential use case in smart cities. In recent couple of years, the number of vehicles has increased significantly. As a result, it is critical to make the use of technology that enables hassle-free parking in both public and private spaces. In conventional parking systems, drivers are not able to find free parking space. Conventional systems requires more human interference in a parking lots. To manage these circumstances there is an intense need of IoT enabled parking solution that includes the well defined architecture that will contain the following components such as smart sensors, communication agreement and software solution. For implementing such a smart parking system in this paper we proposed a design of smart parking system and also compare it with convetional system. The proposed design utilizes sensors based on IoT and Data Mining techniques to handle real time management of the parking system. IoT enabled smart parking solution minimizes the human interference and also saves energy, money and time.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.47 no.5
• /
• pp.943-958
• /
• 2023

This study explores the sneakerhead subculture through the lens of subcultural capital, primarily focusing on online community interactions. The analysis utilizes text mining techniques and netnographic research methods to examine textual data extracted from the online sneakerhead community and aims to elucidate manifestations of subcultural capital within the subculture. The findings underscore several key points: Firstly, shared experiences cultivated by the collective consciousness of subcultural capital foster solidarity among members. Secondly, ongoing validation of authenticity and comprehension of sneakers' cultural significance are member requirements. Subsequently, exhibiting greater levels of subcultural capital empowers members, resulting in hierarchical structures both within and beyond the community. Fourthly, resale-driven sneaker commercialization yields positive outcomes, including individual profit and cultural expansion, yet also brings negative consequences, such as market distortion and intra-community conflict. Lastly, the online community fills a pivotal role in dictating subcultural trends, effectively functioning as an institutional network. Given sneakers' enduring status as a fashion phenomenon, further examination of in this realm is warranted.

• Journal of Information Technology Services
• /
• v.19 no.4
• /
• pp.1-11
• /
• 2020

Through text mining, sentiment analysis, and semiotics analysis, this study aims to reinterpret the meaning of user emotional words and related words to derive strategic elements of brand and design. After selecting a local car manufacturer whose user opinion on the brand is a clear topic, web-crawl the car comments of the manufacturer directly created by the users online. Then, analyze the extracted morphology and its associated words and convert them to fit the marketing mix theory. Through this process, propose a methodology that allows consumers to supplement and improve brand elements with negative sensibilities, and to inherit elements with positive sensibilities and manage brands reasonably. In particular, the Map presented in this study are considered to be fully utilized as information for overall brand management.

• Geomechanics and Engineering
• /
• v.11 no.2
• /
• pp.269-288
• /
• 2016

The jointed rock mass behavior often plays a major role in the design of underground excavation, and their failures during excavation and in operation, are usually closely related to joints. This research attempts to evaluate the effects of two basic geometric factors influencing tunnel behavior in a jointed rock mass; joints spacing and joints orientation. A hybridized indirect boundary element code known as TFSDDM (Two-dimensional Fictitious Stress Displacement Discontinuity Method) is used to study the stress distribution around the tunnels excavated in jointed rock masses. This numerical analysis revealed that both the dip angle and spacing of joints have important influences on stress distribution on tunnel walls. For example the tensile and compressive tangential stresses at the boundary of the circular tunnel increase by reduction in the joint spacing, and by increase the dip joint angle the tensile stress in the tunnel roof decreases.

• Journal of Korea Multimedia Society
• /
• v.6 no.4
• /
• pp.707-713
• /
• 2003

Convenience and promptness of the internet have been not only making the electronic commerce grow rapidly in case of website, analyzing a navigation pattern of the users has been also making personalization and customization techniques develop rapidly for providing service accordant to individual interestingness. Web personalization and customization skill has been utilizing various methods, such as web log mining to use web log data and web mining to use the transaction of users etc, especially e-CRM analyzing a navigation pattern of the users. In this paper, We measure exact duration time of the users in web page and web site, compute weight about duration time each page, and propose a way to comprehend e-loyalty through the computed weight.

• The Journal of Information Systems
• /
• v.26 no.4
• /
• pp.327-353
• /
• 2017

Purpose Social media such as social network services, online forums, and customer reviews have produced a plethora amount of information online. Yet, the information deluge has created both opportunities and challenges at the same time. This research particularly focuses on the challenges in order to discover and track the service defects over time derived by mining publicly available online customer reviews. Design/methodology/approach Synthesizing the streams of research from text analytics, we apply two stages of methods of sentiment analysis and structural topic model incorporating meta-information buried in review texts into the topics. Findings As a result, our study reveals that the research framework effectively leverages textual information to detect, prioritize, and categorize service defects by considering the moving trend over time. Our approach also highlights several implications theoretically and practically of how methods in computational linguistics can offer enriched insights by leveraging the online medium.