• Journal of Information Technology Services
• /
• v.2 no.2
• /
• pp.87-95
• /
• 2003

With the increasing proliferation of World Wide Web, electronic mail systems have become very widely used communication tools. Researches on e-mail classification have been very important in that e-mail classification system is a major engine for e-mail response management systems which mine unstructured e-mail messages and automatically categorize them. in this research we develop e-mail classifiers for e-mail Response Management Systems (ERMS) using naive bayesian learning and centroid-based classification. We analyze which method performs better under which conditions, comparing classification accuracies which may depend on the structure, the size of training data set and number of classes, using the different data set of an on-line shopping mall and a credit card company. The developed e-mail classifiers have been successfully implemented in practice. The experimental results show that naive bayesian learning performs better, while centroid-based classification is more robust in terms of classification accuracy.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.17-20
• /
• 2005

In this work, we compared several feature selection methods in the field of spam mail filtering. The proposed fuzzy inference method outperforms information gain and chi squared test methods as a feature selection method in terms of error rate. In the case of junk mails, since the mail body has little text information, it provides insufficient hints to distinguish spam mails from legitimate ones. To address this problem, we follow hyperlinks contained in the email body, fetch contents of a remote web page, and extract hints from both original email body and fetched web pages. A two-phase approach is applied to filter spam mails in which definite hint is used first, and then less definite textual information is used. In our experiment, the proposed two-phase method achieved an improvement of recall by 32.4% on the average over the $1^{st}$ phase or the $2^{nd}$ phase only works.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11a
• /
• pp.451-454
• /
• 2003

WWW(Word Wide Web)은 인터넷 상에서 광범위하게 분산된 다양한 형식의 데이터를 손쉽게 검색할 수 있도록 하며, 모든 응용의 사용자 환경을 손쉽게 포함시킴으로서 새로운 미디어 타입의 통합을 위한 가장 성공적인 기술로 평가받고 있다. E-Mail 서비스는 WWW 시스템의 가장 기본적인 기능으로, 인터넷 기술이 발전하고 사용자가 기하급수적으로 증가함에 따라 E-Mail 사용자도 늘고있다. 그러나 기존의 서비스는 HTML의 텍스트 기반 구조를 통한 비동기적인 형태의 서비스를 계속 유지하고 있어, 최근 인터넷상의 상당수를 차지하는 오디오, 비디오와 같은 실시간 환경의 멀티미디어 데이터들을 통합하는 좀더 동기적인 표현방법이 요구되고 있다. 본 논문에서는 E-Mail 서비스에 대한 동기적 방법론을 제안하고 구현하고자 한다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.1
• /
• pp.16-26
• /
• 2002

A web based mail system consists of servers and clients. A server side takes charge of making rail accounts and service, a client side does interfacing with users. In this paper, we designed the mail system with multi-domain facility. Also we implemented both a ussr environment based on the internet explorer and management environment based on the windows server 2000. Using the service engine of rail system, we could provide the user efficiency through responding user absence, automatic mail sorting, verifying receipt and refusing messages, and implemented the rail system which provides the reliable system.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2636-2638
• /
• 2003

WWW(World Wide Web)은 인터넷상에 광범위하게 분산된 다양한 형식의 데이터를 손쉽게 검색할 수 있도록 하며, 모든 응용의 사용자 환경을 손쉽게 포함시킴으로써 새로운 미디어 타입의 통합을 위한 가장 성공적인 기술로 평가받고 있다. 처음 Tim Berners-Lee에 의해 처음 개발될 당시 WWW는 텍스트 기반의 구조에 맞추어 비동기적인 형태의 검색과 상호작용을 지원하도록 설계되었다. 반면 최근 인터넷상의 상당수를 차지하는 오디오, 비디오와 같은 실시간 환경의 멀티미디어 데이터들은 연속적, 동기적이며, 대화형 특징을 포함하고 있어 WWW에서 이러한 미디어들을 통합하기 위해서는 구조적인 확장이 요구된다. 본 논문에서는 현재 가장 많이 쓰이는 WWW 기능인 e-Mail 서비스에 대한 동기적 방법론을 제안하고자 한다. e-Mail 사용자가 HTML tag에 대한 사전 지식이 없이도 사전을 기반으로 e-Mail의 형식을 지정할 수 있도록 하며 이렇게 함으로써 보다 동기적인 형태의 서비스를 구현하도록 한다.

• The Journal of Engineering Research
• /
• v.4 no.1
• /
• pp.5-22
• /
• 2002

With the rapid advance of internet service and the corresponding migration of service environment from the text-based one to WWW (World Wide Web) environment, the number of internet users is growing rapidly due to its easy usage. Accordingly, usage of internet as services for sending electronic mails to the other party over the network is becoming increasingly prevalent. Web-based electronic mailing system is comprised of a server and a client. The former provides the users with e-mail accounts and services, while the latter serves as a user interface. In other words, it enables those public users who dos not own e-mail accounts on the existing mail server to have an access to the mailing service through the web. In this paper, we designed a effective web-based electronic mailing system which is based on the internet explorer and linux operating system, which overcomes limitations of the existing e-mail systems and meets the need of a cost-efficient alternative. Our electronic mailing system also supports the convenience of users through appropriate handling of preregistered spam e-mails and multiple e-mails, and this facilitates the development of a stable e-mail system by being able to avoiding the low system performance due to the bursty characteristics of e-mail messages and the increasing number of users

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.592-595
• /
• 2009

We propose an automatic spam mail classifier for e-mail data using Support Vector Machines (SVM). We use a lexical form of a word and its part of speech (POS) tags as features. We select useful features with ${\chi}^2$ statistics and represent each feature using text frequency (TF) and inversed document frequency (IDF) values for each feature. After training SVM with the features, SVM classifies each email as spam mail or not. In experiment, we acquired 82.7% of accuracy with e-mail data collected from a web mail system.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.172-175
• /
• 2003

The enterprise find a solution to the problems such as a reduction of manufacturing period, accurate analysis for customer demand, improvement for customer service and rise of manufacture accomplishment. Internet is a good solution to such problems. Internet offers WWW(World Wide Web), remote control, file transfer and e-mail service. Among the services, WWW takes large portion because of convenient GUI, easy information search and unlimited information registration. Remote Monitoring Server(RMS) system that uses network service is constructed for chip mounter. Hardware base consists of RMS, chip mounter and C/S(Customer Service) server. Software includes DBMS and various modules in server home page. This provide product number, bad product number, trouble code, content and countermeasure in real-time information module, user information in setup module, detailed error information in fault diagnosis module, fault history in fault history module and customer information in customer service management module.

• IE interfaces
• /
• v.18 no.1
• /
• pp.10-21
• /
• 2005

With the increasing proliferation of World Wide Web, electronic mail systems have become very widely used communication tools. Researches on e-mail classification have been very important in that e-mail classification system is a major engine for e-mail response management systems which mine unstructured e-mail messages and automatically categorize them. In this research we compare the performance of Naive Bayesian learning and Centroid-Based Classification using the different data set of an on-line shopping mall and a credit card company. We analyze which method performs better under which conditions. We compared classification accuracy of them which depends on structure and size of train set and increasing numbers of class. The experimental results indicate that Naive Bayesian learning performs better, while Centroid-Based Classification is more robust in terms of classification accuracy.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04a
• /
• pp.421-423
• /
• 2000

인터넷 사용자가 급증히 증가함에 따라 인터넷을 통한 멀티미디어 서비스에 관심이 집중되고 있다. 인터넷을 통한 화상회의나 인터넷 폰, 음성 메일 등이 그 대표적인 예이다. 그 중에서도 대부분의 사람들은 전자 메일을 통해 정보를 공유한다. 현재 대부분의 메일 Agent 프로그램들은 음성 메일을 보낼 수 없으며, 또한 웹을 기반으로 구축된 메일 시스템도 그러하다. 본 논문에서는 Web을 기반으로 하여 음성 메일을 전송하는 시스템을 설계하였다. 현재 웹 응용 시스템을 구축하는 핵심 기술로서 부상하고 있는 서블릿을 사용하여 사용자를 대신해 메일을 전송하는 Mail Agent를 구현하였다. 실시간의 음성처리가 필요하므로 이를 위해 RIP를 사용하였으며, 사용자의 음성을 Capture하고 RIP를 통해 Mail Agent로 보내기 위해 애플릿을 사용하였다. 본 시스템의 모든 컴포넌트들을 자바로 구현함으로써 최대한의 이식성을 얻을 수 있었다.