• Journal of KIISE
• /
• v.45 no.1
• /
• pp.22-29
• /
• 2018

Over the decades, neural networks have been successfully used in numerous applications from speech recognition to image classification. However, these neural networks cannot explain their results and one needs to know how and why a specific conclusion was drawn. Most studies focus on extracting binary rules from neural networks, which is often impractical to do, since data sets used for machine learning applications contain continuous values. To fill the gap, this paper presents an algorithm to extract logic rules from a trained neural network for data with continuous attributes. It uses hyperplane-based linear classifiers to extract rules with numeric values from trained weights between input and hidden layers and then combines these classifiers with binary rules learned from hidden and output layers to form non-linear classification rules. Experiments with different datasets show that the proposed approach can accurately extract logical rules for data with nonlinear continuous attributes.

• Journal of KIISE
• /
• v.43 no.3
• /
• pp.370-379
• /
• 2016

Recently personal media were produced in a variety of ways as a lot of smart devices have been spread and services using these data have been desired. Therefore, research has been actively conducted for the media analysis and recognition technology and we can recognize the meaningful object from the media. The system using the media ontology has the disadvantage that can't classify the media appearing in the video because of the use of a video title, tags, and script information. In this paper, we propose a system to automatically classify video using the objects shown in the media data. To do this, we use a description logic-based reasoning and a rule-based inference for event processing which may vary in order. Description logic-based reasoning system proposed in this paper represents the relation of the objects in the media as activity ontology. We describe how to another rule-based reasoning system defines an event according to the order of the inference activity and order based reasoning system automatically classify the appropriate event to the category. To evaluate the efficiency of the proposed approach, we conducted an experiment using the media data classified as a valid category by the analysis of the Youtube video.

• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1410-1422
• /
• 2015

In order to design a system, software developers use an object model such as the UML class diagram. Object-Relational Transformation Methodology (ORTM) is a methodology to transform the relationships that are expressed in the object model into relational database tables, and it is applied for the implementation of the designed system. Previous ORTM studies have suggested a number of transformation methods to represent one relationship. However, there is an implementation problem that is difficult to apply because the usage criteria for each transformation method do not exist. Therefore, this paper proposes a binary decision diagram-based modeling rule for each relationship. Hence, we define the conditions for distinguishing the transformation methods. By measuring the query execution time, we also evaluate the modeling rules that are required for the verification. After evaluation, we re-define the final modeling rules which are represented by propositional logic, and show that our proposed modeling rules are useful for the implementation of the designed system through a case study.

• Journal of the Korean Data and Information Science Society
• /
• v.6 no.2
• /
• pp.17-27
• /
• 1995

We propose a framework for representing and processing uncertain knowledge on the basis of constraint satisfaction. A system of equations and/or inequalities can be considered as a set of constraints that should be solved, and each constraint in the set is transformed into a corresponding logical formula which can be solved through a constraint solving program. Most of rule-based systems, for instance, use a simple probabilistic theory in order to maintain uncertain knowledge, therefore uncertain knowledge can be represented and processed in the constraint satisfaction program quite efficiently.

• Journal of Internet Computing and Services
• /
• v.2 no.2
• /
• pp.117-126
• /
• 2001

This paper presents fuzzy Pr/T nets to represent the fuzzy production rules of a knowledge-based system in the level of first-order predicate logic. The fuzzy Pr/T nets are fuzzy extension of the Pr/T nets. Based on the fuzzy Pr/T net, we propose a fuzzy reasoning algorithm. This algorithm is much closer to human intuition and reasoning than other methods because of using the proper belief functions according to fuzzy concepts in fuzzy production rules.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.58-60
• /
• 2005

대표적인 데이터마이닝 문제중의 하나인 연관규칙 탐사에는 지금까지 Apriori 기반의 많은 알고리즘들이 개발되어 왔다. 본 논문에서는 비트맵을 이용한 Apriori 알고리즘 구현방안을 제시한다. 우선, 핵심연산인 비트맵 논리곱(Bitmap AND)과 비트 카운팅(bit-counting)을 컴퓨터 CPU의 고급 기술을 이용해서 효과적으로 구현할 수 있음을 보인다. 또한, 트랜잭션 데이터를 비트맵으로 표현함으로써, 기존 Apriori와는 달리, 비트맵 논리곱 연산을 획기적으로 줄일 수 있는 방법을 제시한다. BAR의 이러한 구현기법을 통해, Apriori 기반의 최신 구현 방법에 비해, 성능이 최대 30배 정도 향상됨을 보인다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.205-207
• /
• 2005

최근 수많은 정보를 통해서 증명 되듯이 비즈니스 프로세스 관리(Business Process Management, BPM)는 기업의 소프트웨어 시장의 가장 중요한 부분을 차지하고 있다. 비즈니스 프로세스 관리는 프로세스 전 라이프 사이클을 지원하고자 하는 개념으로 급변하는 경영 환경의 변화에서 기업의 경쟁력을 재고 하기위하여 필요로 되는 새로운 기업 컴퓨팅 패러다임이다. 비즈니스 프로세스 관리의 핵심적인 정보시스템 역할을 수행하는 워크플로우(Workflow)에서의 스케줄링은 정확한 업무 순서를 명세하기 위한 시간적인 제약들에 집중되어 있다. 워크플로우와 BPM과 같은 비즈니스 프로세스에서의 또 하나의 중요한 측면은 자원할당관리이다. 현재 대부분 다양한 자원들을 모델링하는데 초점을 맞추어 왔으며 자원들과 연관된 제약에서의 스케줄링에 대한 관심은 많지 않은 편이었다. 본 논문에서는 First Order Logic 기반의 CTR(Concurrent Transaction Logic)을 이용하여 각 비즈니스 프로세스 스케줄링을 위한 자원할당에 따른 제약들을 논리적인 모형으로 구체화하고, 모형에 필요한 변환 규칙을 소개하고자 한다.

• Korean Journal of Logic
• /
• v.19 no.2
• /
• pp.233-251
• /
• 2016

In their recent paper published in this journal Shin Kim and Jinyong Lee have attacked some previous studies on the counterexample to modus ponens. Among their arguments I would like to discuss the following two; first, those attempts to explain van McGee's example by reference to conditional probability do not accord with van McGee's position, second, van McGee'e example is to be best seen as an argument containing the fallacy of equivocation. I show that the first argument is not correct, the second one is not so persuasive as it seemed first.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10a
• /
• pp.148-150
• /
• 2004

부정행위 탐지는 개별 사용자의 행동 기록과 그 사용자와 유사한 프로필을 갖고 있는 사용자들의 행동 기록을 바탕으로 행동 패턴 혹은 행동 규칙을 찾아내, 이 패턴/규칙과의 비교를 통해 현재 행위가 부정한 것인지를 결정하는 방법을 주로 사용한다. 그러나, 특정 사용자의 행위패턴이 급격하게 바뀌는 경우, 과거의 기록을 바탕으로 생성된 패턴의 유효성은 보장받을 수 없다. 더구나 기존 기록과 상이한 행위에 대한 새로운 패턴이 생성되기 위해서는 계속해서 그런 행위가 쌓여야만 하고, 그 쌓이는 양은 기존 패턴의 견고성에 비례된다. 또한 동일 사용자에게 털러 패턴을 적용시키는 방법 역시 패턴간의 충돌이 일어나는 등의 한계가 존재한다. 본 논문에서는 시간 논리(Temporal Logic)를 적용하여, 과거의 패턴의 유효성을 검증하고 신규패턴을 빠르게 찾아내는 방법을 제안하고자 한다.

• The KIPS Transactions:PartA
• /
• v.12A no.5 s.95
• /
• pp.385-390
• /
• 2005

Set constraints logic language is a language that adopts `set theory` in programming. In this paper, we introduce the procedure for solving set constraints proposed by A. Dovier and show how the procedure can be implemented in logic language Prolog. The procedure is represented in `rewriting rules` and this representation is characterized by having nondeterministic rule applicationsand mathematical variables that is difficult to be implemented in general programming languages. In this paper, we show that the representation can be easily implemented by using nondeterministic control, logical variables and data structure `list` provided in Prolog. Our implementation has following advantages.First we have implemented the full features of the language. Second we have described the implementation detail in thisresearch. Third other used the commercial Prolog called SICStus, but we are using CIAO Prolog with GNU GPL(General Public License) and anyone can use it freely. Forth the software of our implementation is open source so anyone can use, modify, and distribute it freely.