• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.3
• /
• pp.401-410
• /
• 2021

Recently, as cyber attacks targeting industrial control systems increase, various studies are being conducted on the detection of abnormalities in industrial processes. Considering that the industrial process is deterministic and regular, It is appropriate to determine abnormality by comparing the predicted value of the detection model from which normal data is trained and the actual value. In this paper, HAI Datasets 20.07 and 21.03 are used. In addition, an ensemble model is created by combining models that have applied different time steps to Gated Recurrent Units. Then, the detection performance of the single model and the ensemble recurrent neural networks model were compared through various performance evaluation analysis, and It was confirmed that the proposed model is more suitable for abnormal detection in industrial control systems.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.225-230
• /
• 2020

Machine learning is an algorithm which learns a computer based on the data so that the computer can identify the trend of the data and predict the output of new input data. Machine learning can be classified into supervised learning, unsupervised learning, and reinforcement learning. Supervised learning is a way of learning a machine with given label of data. In other words, a method of inferring a function of the system through a pair of data and a label is used to predict a result using a function inferred about new input data. If the predicted value is continuous, regression analysis is used. If the predicted value is discrete, it is used as a classification. A result of analysis, no. 8 (5, 3.4, setosa), 27 (5, 3.4, setosa), 41 (5, 3.5, setosa), 44 (5, 3.5, setosa) and 40 (5.1, 3.4, setosa) in Table 3 were classified as the most similar Iris flower. Therefore, theoretical practical are suggested.

• Journal of Internet of Things and Convergence
• /
• v.6 no.1
• /
• pp.23-30
• /
• 2020

This paper proposes energy management directions to discover the factors of energy loss in homes and buildings and to find ways to improve them. We designed a diagnostic content app for everyday life so that not only housing experts but also the general public can use the detachable thermal imaging camera, which is a strong point of popularity and convenience. The diagnostic results using the app were analyzed using Energy Finder, an energy efficiency diagnostic solution. The survey was conducted on the senior center which is in the blind spots and facilities of the energy welfare area. The target of diagnosis was energy efficiency diagnosis by selecting 30 senior centers for over 15 years from 600 locations located in Naju City, Jeollanam-do. The overall diagnosis was good, but it is considered that the place classified as 7th grade needs to be supplemented to improve energy efficiency.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.1-21
• /
• 2003

As electronic commerce(EC) has grown rapidly, agents that work on the behalf of humans on the Internet are being used actively. However, most of the EC agents have some problems. They fail to fully support buyers' decision making behaviors and sellers' information supply activities. Further, they are not suited for mobile computing environment. In this paper, we introduce a Multi-Mobile Agents System(MMAS) that has been developed according to a conceptual framework that corrects the aforementioned problems. Built by using Tokyo IBM ASDK(Aglets Software Development Kit) for the area of hotel reservation, the system consists of buyer- and seller-side agents that interact with each other; buyer-side agents help buyers to make purchasing decisions by collecting and analyzing information through applying a multi-criteria decision making method, while seller-side agents substitute fur sellers by managing databases and providing real-time information to the buyer-side agents. In this system, multiple agents perform their shared tasks at the same time in order to increase efficiency. Users do not have to keep the connection with the system because they are notified when tasks are done.

• Journal of the Korea Convergence Society
• /
• v.6 no.4
• /
• pp.205-212
• /
• 2015

This paper aims to investigate key factors affecting customer adoption of the online review from the three perspectives such as customer review characteristics, reviewer characteristics, and customer characteristics. We collected data on customers who have experience in purchasing products in Taobao. The major findings are as follows. First, the customer review amount and vividness are not directly related to customer adoption of the online review. Second, the trust of reviewer and perceived similarity have positive effects on customer adoption of the online review. Third, the prior knowledge and product involvement increase customer adoption of the online review. Finally, customers' purchase intention is greatly determined by customer adoption of the online review. This paper presents the importance of the management of customer reviews and management method for the stakeholders of shopping mall to advancing Chinese market.

• Journal of Intelligence and Information Systems
• /
• v.10 no.1
• /
• pp.27-45
• /
• 2004

While on-line shopping is increasing, the "Consumer Protection Law in Electronic Commerce" obliges each internet shopping mall to provide its business information. Although most internet shopping malls provide their business information in the semi-structured format on the bottom of their homepages, the attributes and expression forms of business information are different each other. It makes consumers difficult to identify their business information and lowers public confidence. Hence this study proposes three approaches - HTML-based structure, XML-based structure, and XML data island-based structure - to structuralizing business information for correct expression. The experiment results showed that the business information extraction time by XML data island-based structure is independent of the size of the web document, while the time by HTML-based structure is dependent on the size. By comparing the business information extraction times, we show that XML data island-based structure is more efficient and effective than HTML-based structure.structure.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.04a
• /
• pp.371-377
• /
• 2004

In an effort to simplify, standardize, and make effective use of information on arrival／departure through electronic means developed up to now, this paper suggests ebXML based Global Port B2B Framework, which makes it possible not only to realize e-commerce transactions between ports, but also simultaneously realize standardization and integration. In addition, due to its reusability of information, various reports are to be simplified and automated

• The Journal of Society for e-Business Studies
• /
• v.14 no.1
• /
• pp.13-34
• /
• 2009

As ubiquitous computing technology is proliferating, a wider range of u-services applying ubiquitous computing technology has been implemented and some of the u-services have been actively considered for commercialization. Accordingly, establishing corresponding business models based on u-services also have been increased. However, structured methodologies to build u-service business models are still in its very early age. Moreover, since most of the legacy business model formulation and analysis methodologies have stressed on conventional or digital services, not u-services. Hence, the purpose of this paper is to propose a structured methodology of formulating and analyzing business models for u-services. An illustrative example is described to show the feasibility of the proposed methodology. To do so, Business Model Diagram (BMD), which adopts model components for u-services, is newly developed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1202-1209
• /
• 2003

With explosive growth of Internet users, the market share of electronic commerce becomes wider. Therefore the Internet is standing in the spotlight of a new medium of advertisement, and several Internet advertising methods have been implemented. However the banner advertising that is the typical internet advertising method is showing low click rate because of user's unconcern. Accordingly we propose a new Internet advertising method that makes expose advertising content on the background of web browser when user puts mouse pointer over a specified text. Internet users are willing to click a interesting text, just at that moment the advertising content is appeared on the background of web browser. Therefore we could expect high effectiveness of advertising and moreover after clicking the text, the advertising content is shown continually on the web browser. The proposed method, unlike banner advertising, various shapes of image can be applied and makes use of whole background of web page.

• The KIPS Transactions:PartA
• /
• v.9A no.3
• /
• pp.341-350
• /
• 2002

As network environments have been improved and the use of internet has been increased, mobile agent technologies are widely used in the fields of information retrieval, network management, electronic commerce, and parallel/distributed processing. Recently, a lot of researchers have studied the concepts of parallel/distributed processing based on mobile agents. SPMD is the parallel processing method which transmits a program to all the computers participated in parallel environment, and performs a work with different data. Therefore, to transmit fast a program to all the computers is one of important factors to reduce total execution time. In this paper, we consider the parallel environment consisting of mobile agents system, and propose a new method which transmits fast a mobile agent code to all the computers using binomial trees in order to efficiently perform the SPMD parallel processing. The proposed method is compared with another ones through experimental evaluation on the IBM's Aglets, and gets greatly better performance. Also this paper deals with fault tolerances which can be occurred in transmitting a mobile agent using binomial trees.