• The Journal of the Korea Contents Association
• /
• v.21 no.6
• /
• pp.552-560
• /
• 2021

With the recent development of the art distribution system, interest in art investment is increasing rather than seeing art as an object of aesthetic utility. Unlike stocks and bonds, the price of artworks has a heterogeneous characteristic that is determined by reflecting both objective and subjective factors, so the uncertainty in price prediction is high. In this study, we used LSTM Recurrent Neural Network deep learning model to predict the auction winning price by inputting the artist, physical and sales charateristics of the Korean artist. According to the result, the RMSE value, which explains the difference between the predicted and actual price by model, was 0.064. Painter Lee Dae Won had the highest predictive power, and Lee Joong Seop had the lowest. The results suggest the art market becomes more active as investment goods and demand for auction winning price increases.

• International Journal of Computer Science & Network Security
• /
• v.22 no.8
• /
• pp.35-44
• /
• 2022

The Internet is extremely important to accomplish numerous items, from education to businesses and entertainment. Therefore, the quality of its performance must be efficient. Nowadays, there is a lack of information available for users to choose a suitable Internet service. What information is available might be insufficient, inaccurate, or regularly updated. Accordingly, there is a need to develop an electronic system that enables users to evaluate their current Internet service subscription. Several factors are used as evaluation criteria in the system that affect users' decisions. In this paper, a prototype of a design science research project is proposed to address a few objectives. First, it can help Internet service users in Saudi Arabia to make the best decision for themselves regarding Internet services subscriptions. Second, it can assist the Saudi government to seek one of the 2030 vision goals: the digital transformation that depends on having a good Internet connection. The proposed solution is a promising one that would help Internet service users to make the best decision for themselves and choose the best Internet service that fits their needs. A qualitative method has been used to evaluate the efficiency and the utility of the proposed system prototype. The results showed the extent of participants' acceptance of the Internet Service Evaluation System.

• Ocean and Polar Research
• /
• v.39 no.3
• /
• pp.233-244
• /
• 2017

This study seeks to analyze the needs of biotechnology companies in relation to their entry into the marine biotechnology industry and to discuss the policy implications associated with empirical tasks based on issues raised from empirical results gathered from a survey data of 200 biotechnology companies in Korea. This study made a comparison between marine and non-marine biotechnology companies and analyzed non-marine biotechnology companies' needs related to their entry into the marine biotechnology companies by using Social Network Analysis (SNA). Empirical results indicate that 23.5% of biotechnology companies produce goods using marine bio-resources. Once the utility of marine bio-resources is established, 58.8% of non-marine biotechnology companies intend to enter the marine biotechnology industry. This study also shows that non-marine biotechnology companies need technical support, information sharing, and the acquisition of raw materials to enter the marine biotechnology industry. The findings in this study provide important pointers for the direction of policies and future research in the area of marine biotechnology industry.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.11
• /
• pp.771-778
• /
• 2014

We propose Femto-cell power control scheme in HeNet with Game Theory. The Femto-cell which provide high quality with low power is issued by many benefits, however there is a bunch of interferences when many Femto-cells use overlapped bandwidth with Macro-cell. We defined base station of cellular networks and mobile users as players of Game Theory, and configured interference effect among each other as power utility function. Futhermore, we showed enhanced overall system performance, lower power usage and interference decrease by using optimal power.

• Journal of Information Technology Application
• /
• v.1
• /
• pp.173-211
• /
• 1999

The task of classification permeates all walks of life, from business and economics to science and public policy. In this context, nonlinear techniques from artificial intelligence have often proven to be more effective than the methods of classical statistics. The objective of knowledge discovery and data mining is to support decision making through the effective use of information. The automated approach to knowledge discovery is especially useful when dealing with large data sets or complex relationships. For many applications, automated software may find subtle patterns which escape the notice of manual analysis, or whose complexity exceeds the cognitive capabilities of humans. This paper explores the utility of a collaborative learning approach involving integrated models in the preprocessing and postprocessing stages. For instance, a genetic algorithm effects feature-weight optimization in a preprocessing module. Moreover, an inductive tree, artificial neural network (ANN), and k-nearest neighbor (kNN) techniques serve as postprocessing modules. More specifically, the postprocessors act as second0order classifiers which determine the best first-order classifier on a case-by-case basis. In addition to the second-order models, a voting scheme is investigated as a simple, but efficient, postprocessing model. The first-order models consist of statistical and machine learning models such as logistic regression (logit), multivariate discriminant analysis (MDA), ANN, and kNN. The genetic algorithm, inductive decision tree, and voting scheme act as kernel modules for collaborative learning. These ideas are explored against the background of a practical application relating to financial fraud management which exemplifies a binary classification problem.

• Journal of Information Technology Services
• /
• v.11 no.2
• /
• pp.107-118
• /
• 2012

Recently, as the clouding computing begins to receive a great attention from people all over the world, it became the most popular buzz word in recent IT magazines or journal and heard it in many different services or different fields. However, a notion of the cloud service is defined vaguely compared to increasing attentions from others. Generally the cloud service could be understood as a specific service model base on the clouding computing, but the cloud, the cloud computing, the cloud computing service and cloud service, these four all terms are often used without any distinction of its notions and characteristics so that it's difficult to define the exact nature of the cloud service. To explore and analyze the cloud service systematically, an accurate conception and scope have to be preceded. Therefore this study is to firstly clarify its definition by Delpi method using expert group and then tries to provide the foundation needed to enable relative research such as establishing business model or value chain and policies for its activation to set off. For the Delpi, 16 experts participated in several surveys from different fields such industry, academy and research sector. As a result of the research, Characteristics of the Cloud Service are followings : Pay per use, Scalability, Internet centric Virtualization. And the scope as defined including Grid Computing, Utility Computing, Server Based Computing, Network Computing.

• Journal of Korean Society of Rural Planning
• /
• v.12 no.2 s.31
• /
• pp.87-96
• /
• 2006

The purpose of this study is to increase the utility in terms of the elderly's welfare. The data introduced in this paper were collected by the constructed interview method, and 192 aged interviewees were selected from 4 rural areas: Namhaegun, Uiryeong-gun Imsil-gun and Sunchang-gun. From the descriptive analysis of the data, the results derived are as follows: 1) The financial supports are needed to remodel rural village community facilities as senior centers. 2) It is expected that the facility be a center for the aged people's living in a village, and that have multiple functions of general care service network health care, meal support and making friendship spaces for them. 3) Share housing function is also added to the facility in emergency conditions.

• The Journal of Information Technology
• /
• v.7 no.2
• /
• pp.77-92
• /
• 2004

Global Electronic Trading means that trading partners trade each other via Global Electronic Trading Network, that is, global business to business electronic commerce. Electronic payment systems are how to make payment electronically in manner that is efficient, reliable, and secure. I suggest the Electronic payment systems such as TradeCard and SWIFT enable seller and buyer to conduct and settle international B2B electronic commerce in case of solving the above problems. And, where the cargo arrives ahead of the B/L, the importer cannot take delivery of the cargo without the B/L. This situation is referred to as the B/L dilemma. But the BOLERO system will resolve this B/L dilemma. Bolero Project is developing a cross industry utility platform for the secure, electronic transfer of commercial trade information world wide.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.95_96
• /
• 2009

In this paper, a new algorithm of Integrated Volt/Var Control (IVVC) is proposed using Volt/Var control for the Distribution Automation System (DAS) based on the modeling of the distributed load and the distributed current. In the proposed, the load flow based on the modeling of the distributed load with Distributed Generation and the distributed current are estimated from constants of four terminals using the measurement of the current and power factor from a Feeder Remote Terminal Unit (FRTU). For Integrated Volt/Var Control (IVVC), the gradient method is applied to find optimal solution for tap and capacity control of OLTC (On-Load Tap Changers), SVR (Step Voltage Regulator), and SC (Shunt Condenser). What is more Volt/Var control method is proposed using moving the tie switch as well as IVVC algorithm using power utility control. In the case studies, the estimation and simulation network have been testified in Matlab Simulink.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.12 no.1
• /
• pp.157-157
• /
• 1987

Hydro-electric power generation from multi-purpose dams has been playing important roles in the electric power supply network in Korea. Although the total share of hydro power in national electricity supply now becomes very small, the peak-shaving and frequency control capability of hydro power helps the power company enormously in maintaining the quality of power. But since the company that builds and operates the multi-purpose dams in Korea has to sell all the electricity produced to the monopolistic utility, there have been various problems in justifying the investment, designing pricing mechanism, and controlling operations of the power plants. In addition, economic evaluation of the hydro power has been distorted by a variety of reasons and hence it has been very difficult to encourage effective development and utilization of national water resources. To make the problem worse, both parties are public companies with X-inefficiency problems. Thus, changing environment requires to reengineer the system that governs hydro power generation. We address the problems of Korean hydro-electric power generation system in four areas: the investment justification process, the operations decison right of the hydro power plants, the pricing of the purchased-power, and the negotiation of contract revision. Then we propose improvement directions of new hydro-electric power system in view of static and dynamic efficiency, X-inefficiency and equity.