• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.2
• /
• pp.91-95
• /
• 2007

Main goal of web recommendation system is to study how user behavior on a website can be predicted by analyzing web log data which contain the visited web pages. Many researches of the web recommendation system have been studied. To construct web recommendation system, web mining is needed. Especially, web usage analysis of web mining is a tool for recommendation model. In this paper, we propose web recommendation system using grid based support vector machines for improvement of web recommendation system. To verify the performance of our system, we make experiments using the data set from our web server.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.58-64
• /
• 2010

These days, the Internet networks have rapidly expanded and used in various fields and been recognized as essential in our daily life. However, there are users who have difficulties in access to web sites like those with physical disabilities. Therefore, our country as well as developed countries have paid more attention to web access, and organized investigation and research are needed. This study presents how to reduce the number of access for efficient web access by the visually disabled and designs user interface.

• The Korean Journal of Applied Statistics
• /
• v.14 no.2
• /
• pp.261-271
• /
• 2001

정보 공유와 비즈니스 수행 등의 매체로서 World Wide Web의 이용이 보편화됨에 따라 다양하고 방대한 데이터를 웹을 통하여 얻을 수 있게 되었으며, 이러한 데이터로부터 유용한 정보를 추출하기 위한 데이터 분석과 활용은 많은 분야에서 중요한 사안으로 인식되고 있다. 본 연구에서는 웹 로그(web log)데이터로부터 정보를 추출하기 위한 과정 및 방안에 대해 살펴보고자 한다. 로그 데이터의 특징과 통계 데이터와의 차이점, 데이터 수집 및 사전 처리 과정, 추출할 수 있는 정보 및 분석 방법 등을 제시하고 로그 데이터 분석 예제를 제시한다.

• Journal of the Korean Data and Information Science Society
• /
• v.10 no.2
• /
• pp.501-510
• /
• 1999

We have seen a rapid development of multimedia intustry as computer evolves and the internet has changed our way of life dramatically in these days. There we several attempts to teach elementary statistics on the web but most of them are based on commercial products. The need for statistical data analysis and decision making based on those analysis is growing. In this article we try to show one way of reaching that goal by using a server side scripting language PHP3 toghether with extra graphical module and statistical distribution module on the web. We showed some elementary exploratory graphical data analysis and statistical inferences. There are plenty of room of improvements to make it a full blown statistical analysis tool on the web in the new future. All the programs and databases used in our article we public programs. The main engine PHP3 is included as an apache web server module so it is very light and fast. It will be much better when the PHP4(ZEND) will be officially out in terms of processing speed.

• Journal of Korea Multimedia Society
• /
• v.7 no.1
• /
• pp.126-131
• /
• 2004

Students, who are studying the field of accounting, have to learn and practice statistics in order to analyze the current social status and to predict the Suture trend. however, students have a strong tendency to avoid the statistics lessons, which are dealing with complicated numbers, mathematics, various equations, and so on. This paper aims to construct a stimulating environment for learning statistics and develop an actual lesson on the Internet, Which students can study by practicing directly. The lesson is fully interactive and visualized by using multimedia technologies. The effectiveness of the experiment is measured by survey questions to the students who used the lesson.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.2
• /
• pp.395-400
• /
• 2006

For lab statistics the statistical package SAS is usually used in PC environment. But most Universities in Korea have bought 'Academic Initiative Package chair licence', which allows to install SAS to student lab PCs only. Most students are hardly able to afford to purchase a licence for use of SAS in their PCs at home or other places than school. It would be very convenient to have a web-based SAS system, physically located inside a campus, which university students can use through internet. In this paper we report the web-based SAS system implemented for the lab purpose of Yeungnam University using SAS/Intrnet module. We overcome some Server-Client environmental difficulties not allowing use of the SAS command 'infile' by implementing modules with PHP language. In the system, users can see and execute some basic SAS sample codes by clicking buttons, which makes students feel comfy in SAS programming.

• The Korean Journal of Applied Statistics
• /
• v.15 no.2
• /
• pp.423-432
• /
• 2002

Web Based electronic texts are studied on the statistics education fields. In this paper, we discuss the current problems encountered by many statistics electronic texts. We also suggest a new design concept for the Web Based interactive material. In addition, we presented several examples to demonstrate.

• The Journal of Korean Association of Computer Education
• /
• v.5 no.4
• /
• pp.111-121
• /
• 2002

With advancement of computer and network, world wide web(WWW) as medium of information communication is generalized in many fields. In educational aspect, applications of WWW as alternative media for class teaching or printed matter are increasing. In this article, we demonstrate a web based electronic text on the 'probability and statistics' which is one of six fields of mathematics in 7th curriculum. This text places importance on comprehension of concepts and fundamentals of probability and statistics as applied sciences and not on simple calculations of probability and statistics.

• Journal of the Korea Computer Industry Society
• /
• v.4 no.4
• /
• pp.455-466
• /
• 2003

A self-selected web survey was utilised to Investigate the preference of online holiday travellers to the Internet functions applied to the extensive decision-making process by adoptingthe Canberra tourism website as a case study in Australia. The use of web-based surveys is not at a mature stage, compared to other traditional surveys such as mail survey and telephone survey that have already-known home addresses and phone numbers as a frame population. The adopted web survey relies on non-probability sampling without a known frame population thatcan cause serious research errors. Therefore, the results of this study need to be compared to other official published statistics in order toverify reliability or credibility of the self-selected web survey. This study discusses the extent to which the self-selected web survey can be validated by finding the significant difference not only between the demographic results of web survey and those of official statistics released by several articles including the Graphic, Visualizations and Usability Center (GVU) at Georgia Tech research but also between the travel background features and those of ‘ACT Tourism Masterplan 2001-2005’published by the Canberra Tourism ＆ Event Corporation (CTEC) located in Australian Capital Territory (ACT).

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.11a
• /
• pp.408-411
• /
• 2006

Currently, the nano economy threatens the mass economy. This is based on the internet business models. In the nano business models based on internet, the diversely personalized services are needed. Many researches of the personalization on the web have been studied. The web usage mining using click stream data is a tool for personalization model. In this paper, we propose an internet business model using evolutionary support vector machine and web response survey as a web usage mining. After analyzing click stream data for web usage mining, a personalized service model is constructed in our work. Also, using an approach of web response survey, we improve the performance of the customers' satisfaction. From the experimental results, we verify the performance of proposed model using two data sets from KDD Cup 2000 and our web server.