• Journal of KIISE:Software and Applications
• /
• v.27 no.11
• /
• pp.1082-1087
• /
• 2000

신경회로망 구조의 정제(精製)는 회로망의 일반화능력이나 효율성의 관점에서 중요한 문제이다. 본 논문에서는 feed-forward neural networks로부터 은닉지식을 추출하는 방법을 사용하여 네트워크 재구성을 통한 정제방법을 제안한다. 먼저, 효율적인 if-then rule 추출방법을 제시하고 그 추출된 룰들을 사용하여 룰기반 네트워크로 변환하는 과정을 보여준다. 생성된 룰기반 네트워크 fully connected network에 비하여 상당히 축소된 연결 복잡도를 가지게 되며 일반적으로 더 우수한 일반화능력을 가지게 된다. 본 연구는 도메인 지식이 없이 데이타만 사용하여 어떻게 정제된 룰기반 신경망회로를 생성하고 있는가를 보여준다. 도메인 데이타들에 대한 실험결과도 제시하였다.

• 한국HCI학회:학술대회논문집
• /
• 2008.02b
• /
• pp.540-545
• /
• 2008

게임의 룰은 게임의 메커니즘을 구현하는데 필요한 모든 것을 포함하는 것이다. 또한, 게임의 스토리를 이끌며 지탱하는 중요한 요소이기도 하다. 본고에서는 동서양 모두에서 성공하고 있는 대표적 MMORPG 온라인 게임인 월드오브워크래프트를 중심으로 게임 스토리텔링에서의 룰이 지닌 중요한 요소와 특징, 또한, 이것이 지닌 창조적이며 재미와 몰입, 덧붙여 게임 스토리 전개상에서 만들어내는 생산적인 요소들을 찾아서 특성을 찾고자 한다. 이는 게임 개방시 게임 내의 룰 생성과 스토리 전개에 중요한 요건으로서 연구되어질 수 있으며, 온라인 게임 스토리텔링 창작 및 개발에 적용하는데 연구의 의의가 있다 하겠다. 본고의 논의가 이뤄지기 전, 먼저 게임에 대한 룰의 정의에 대해 지금까지의 논의들을 살펴보고, 이들 속에서 발견되고 논의될 요소들을 얻고자 한다. 이론적 요소를 바탕으로 본고의 연구대상인 월드오브워크래프트의 서사에 나타난 룰과 스토리텔링과의 상호작용을 분석할 것이다. 본고에서 논의 되는 MMORPG게임의 룰과 스토리텔링의 연구는 아직 체계적이지 못하고, 이론적으로 미흡한 게임 스토리텔링 및 룰 연구에 기반 연구가 되고자 한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.17-21
• /
• 2004

본 논문에서는 실시간으로 상수 및 변수의 병렬 매칭이 가능한 새로운 구조의 하드웨어 기반 룰-베이스시스템 구조를 제안한다. 이 시스템은 context-aware computing 시스템에서 상황 인식을 위한 기법으로 적용될 수 있다. 제안된 구조는 기존의 하드웨어 기반의 구조가 가지는 룰의 표현 및 룰의 구성에서 발생하는 제약을 상당히 감소시킬 수 있다. 이를 위해 변형된 형태의 content addressable memory(CAM)와 crossbar switch network(CSN)가 사용되었다. 변형된 형태의 CAM으로 구성된 지식-베이스는 동적으로 데이터의 추가 및 삭제가 가능하다. 또한 CSN은 input buffer와 working memory(WM) 사이에 위치하여, 시스템 외부 및 내부에서 동적으로 생성되거나, 시스템 설정에 의해 지정된 데이터들의 조합 및 pre-processing module(PPM)을 이용한 연산을 통하여 WM을 구성하는 데이터를 생성시킨다. 이 하드웨어 룰-베이스 시스템은 SystemC 2.0을 이용하여 설계하였으며 시뮬레이션을 통하여 그 동작을 검증하였다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.12 no.2
• /
• pp.129-140
• /
• 2006

The existing CBD development methods deal with the analysis phase in a superficial manner. Applying such a superficial analysis to business applications with a number of subsystems makes analysis models be inconsistent with levels and styles, only depending on experiences of the analysts. This inconsistent analysis might cause more serious problems during the subsequent development phases, resulting in the failure of the projects. In this paper, we propose a rule-based analysis pattern that provides an analysis template for business applications. This pattern analyzes the concepts of business applications by using external events and internal rules that process the events. Employing this pattern, a huge business application can be developed by a couple of co-analysts who work together in a consistent and systematic manner. This paper also describes an efficient way to develop business components with the suggested analysis pattern using banking deposit case study through UML Components development process.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.3B
• /
• pp.339-348
• /
• 2004

Packet classification is an important factor to support various services such as QoS guarantee and VPN for users in Internet. Packet classification is a searching process for best matching rule on rule tables by employing multi-field such as source address, protocol, and port number as well as destination address in If header. In this paper, we propose hardware based packet classification algorithm by employing tree bitmap of multi-bit trio. We divided prefixes of searching fields and rule into multi-bit stride, and perform a rule searching with multi-bit of fixed size. The proposed scheme can reduce the access times taking for rule search by employing indexing key in a fixed size of upper bits of rule prefixes. We also employ a marker prefixes in order to remove backtracking during searching a rule. In this paper, we generate two dimensional random rule set of source address and destination address using routing tables provided by IPMA Project, and compare its memory usages and performance.

• The KIPS Transactions:PartC
• /
• v.12C no.2 s.98
• /
• pp.191-200
• /
• 2005

The brilliant achievements in computers and the internet technology make it easy for users to get useful information. But at the same time, the damages caused by intrusions and denial of service attacks are getting more worse. Specially because denial of service attacks by internet worm incapacitate computers and networks, we should draw up a disposal plan against it. So far many rule-based intrusion detection systems have been developed, but these have the limits of these ability to detect new internet worms. In this paper, we propose a system to detect intrusion and generate detection rule against scan-based internet worm, paying attention to the fact that internet worms scan network to infect hosts. The system detects internet worms using detection rule. And if it detects traffic causing by a new scan-based internet worm, it generates new detection nile using traffic information that is gathered. Therefore it can response to new internet worms early. Because the system gathers packet payload, when it is being necessary only, it can reduce system's overhead and disk space that is required.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.121-129
• /
• 2006

Rule-based Expert system using Fuzzy technique inferences various rules by user's input condition and the most proper control signal. This system can lose objectivity by input condition which depends on user's decision. This paper can solve those problems by adding case-based system's technique. The traffic signal control expert system is proposed to store the cases based on the statistics, days, seasons and various circumstances and use them.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.4
• /
• pp.379-387
• /
• 2018

In order to make the IoT ecosystem more usable and friendly to general users, the interaction between the users and platforms/devices and its UX must be improved. In this study, a web-based rule engine system to help users intuitively interact with the various devices and services in IoE (Internet of Everything) platform is proposed. The proposed system consists of web interfaces and UI components for creating and managing rule-based scenarios using sensors, actuators, and external services in an intuitive way. Also, a rule management module for automatically translating the rules from the web interface into Nools rule engine compatible ones is proposed. Finally, we show the usability and feasibility of the proposed system by demonstration of rule-based use cases of IoT devices and external services.

• The KIPS Transactions:PartD
• /
• v.12D no.2 s.98
• /
• pp.275-282
• /
• 2005

In order to increase extendibility and reusability of components during component design, the variability discovered in a business application development needs to be defined to separate rules. That is because component adaptation techniques through redefinition of implementation classes and interface wrapping have limits to support the component reusability. Therefore, It's essential to design the component which takes into account the future reusability in the component development. In this paper, we extended the existing component architecture to incorporate rule components by separating variable properties from the components and defined the necessary syntax for the rule definition. In the case study, we built the business components for an insurance sales application and verified the component reusability through the rule redefining.

• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1593-1601
• /
• 2017

In a big data platform, association rule mining applications could bring some benefits. For instance, in a agricultural big data platform, the association rule mining application could recommend specific products for farmers to grow, which could increase income. The key process of the association rule mining is the frequent itemsets mining, which finds sets of products accompanying together frequently. Former researches about this issue, e.g. Apriori, are not satisfying enough because huge possible sets can cause memory to be overloaded. In order to deal with it, SON algorithm has been proposed, which divides the considered set into many smaller ones and handles them sequently. But in a single machine, SON algorithm cause heavy time consuming. In this paper, we present a method to find association rules in our Hadoop based big data platform, by parallelling SON algorithm. The entire process of association rule mining including pre-processing, SON algorithm based frequent itemset mining, and association rule finding is implemented on Hadoop based big data platform. Through the experiment with real dataset, it is conformed that the proposed method outperforms a brute force method.