• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.852-855
• /
• 2010

Tree type of Rule Case will be processed by the method that provide practical Rule Case to Rule Engine that is made with procedural language beforehand, then the Rule Engine according to the condition of the special Rule Case to return result in current Rule-Based System. There are two disadvantages in the method; the first is according to specific business rule after construct the Rule Engine when the business rule changing the Rule Engine also must be changed. The second is when Rule have many conditions the Rule Engine will become very complex and the speed of processing Rule Case will become very slow. In this paper, we will propose a simplified algorithm that according to the theory of ID Tree to produce Rules which be used in Rule-Based System. The algorithm can not only produce Rules but also make sure of satisfying change of business rule by execute the algorithm. Because it is not necessary to make a Rule Engine, we will anticipate effect of increasing speed and reducing cost from Rule-Based System of applying the algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.6
• /
• pp.764-770
• /
• 2004

This paper presents a hybrid data mining mechanism to extract expert knowledge from historical data and extend expert systems' reasoning capabilities by using fuzzy neural network (FNN)-based learning & rule extraction algorithm. Our hybrid data mining mechanism is based on association rule extraction mechanism, FNN learning and fuzzy rule extraction algorithm. Most of traditional data mining mechanisms are depended ()n association rule extraction algorithm. However, the basic association rule-based data mining systems has not the learning ability. Therefore, there is a problem to extend the knowledge base adaptively. In addition, sequential patterns of association rules can`t represent the complicate fuzzy logic in real-world. To resolve these problems, we suggest the hybrid data mining mechanism based on association rule-based data mining, FNN learning and fuzzy rule extraction algorithm. Our hybrid data mining mechanism is consisted of four phases. First, we use general association rule mining mechanism to develop an initial rule base. Then, in the second phase, we adopt the FNN learning algorithm to extract the hidden relationships or patterns embedded in the historical data. Third, after the learning of FNN, the fuzzy rule extraction algorithm will be used to extract the implicit knowledge from the FNN. Fourth, we will combine the association rules (initial rule base) and fuzzy rules. Implementation results show that the hybrid data mining mechanism can reflect both association rule-based knowledge extraction and FNN-based knowledge extension.

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1149-1157
• /
• 2017

The satisfiability problem is always a core problem in artificial intelligence (AI). And how to improve the efficiency of algorithms solving the satisfiability problem is widely concerned. Algorithm IER (Improved Extension Rule) is based on extension rule. The number of atoms and the number of clauses affect the efficiency of the algorithm IER. DPLL rules are helpful to reduce these numbers. Then a complete algorithm CIER based on splitting rule and extension rule is proposed in this paper in order to improve the efficiency. At first, the algorithm CIER (Complete Improved Extension Rule) reduces the scale of a clause set with DPLL rules. Then, the clause set is split into a group of small clause sets. In the end, the satisfiability of the clause set is got from these small clause sets'. A strategy MOAMD (maximum occurrences and maximum difference) for the algorithm CIER is given. With this strategy, a better arrangement of atoms could be got. This arrangement could make the number of small clause sets fewer and the scale of these sets smaller. So, the algorithm CIER will be more efficient.

• The KIPS Transactions:PartB
• /
• v.10B no.1
• /
• pp.27-32
• /
• 2003

The rule induction system generates a set of inductive rules, and the task of selecting an optimal rule subset is one of the important problem in the area of rule induction. This paper proposes a new learning method which combines rule induction system with the paradigm of genetic algorithm. This paper shows that genetic algorithm can be effectively applied to optimal rule selection problem. The proposed system was evaluated using a set of different machine learning data sets and, showed better performance in all cases than other traditional methods.

• Journal of the Korean Ceramic Society
• /
• v.40 no.4
• /
• pp.371-374
• /
• 2003

Various types of equation for mixing rule on permittivity of mixture have been proposed, but none of these is not perfect because of the inconsistency between the actual geometrical configuration and the basic model for calculation. Serial model and parallel model are lower and upper extremes of mixing manner, the apparent permittivity of any other type of mixture stay between these two extreme states. For the random mixture of the stumpy fine particles, customarily the logarithmic mixing rule has been applied. But, the logarithmic mixing rule does not give the proper value of permittivity in low or high mixing rate of constituent. The author proposed the new mixing rule that gives better consistency with measured value in whole mixing range compared to the logarithmic rule. In this paper, a desirable refinement on the equation proposed in the previous paper is made to adapt to thr configuration image of actual compound and then the equation has been expanded to the complex permittivity to apply the mixing rule on the dissipative materials cases.

• The Journal of Asian Finance, Economics and Business
• /
• v.6 no.4
• /
• pp.297-307
• /
• 2019

Despite the fact that the implementation of 5% rule is widely recognized to enhance the transparency of capital market and fairness of corporate governance market, a few evidences present information effect of 5% rule. Using 7,088 non-financial firm-year observations listed on the Korea Stock Exchange from 2006 to 2012, we analyze the relation between trading volume and 5% rule disclosure. The results show that the daily and abnormal trading volume is increased when 5% rule disclosure is released. Moreover, the trading volume is significantly increased during cooling period. Specifically, trading volume is significantly greater when one day before cooling period or the expiration day of cooling period. We also find the information effect of firms with stable ownership structure before 5% rule disclosure is relatively smaller than the firms with unstable ownership structure with unstable ownership structure. These results imply that capital market participants use the information from 5% rule disclosure and reflect in their real economic decision.

• Molecules and Cells
• /
• v.39 no.3
• /
• pp.169-178
• /
• 2016

Although $N{\alpha}$-terminal acetylation (Nt-acetylation) is a pervasive protein modification in eukaryotes, its general functions in a majority of proteins are poorly understood. In 2010, it was discovered that Nt-acetylation creates a specific protein degradation signal that is targeted by a new class of the N-end rule proteolytic system, called the Ac/N-end rule pathway. Here, we review recent advances in our understanding of the mechanism and biological functions of the Ac/N-end rule pathway, and its crosstalk with the Arg/N-end rule pathway (the classical N-end rule pathway).

• International Journal of Contents
• /
• v.5 no.3
• /
• pp.79-85
• /
• 2009

Emergent requests or urgent information among enterprises require their intimate collaboration in B2B EC (electronic commerce). This paper analyzes the needs of intimate cooperation of distributed EC systems in terms of business contracts and presents an active rule-based methodology of close cooperation among EC systems and an active rule component to support it. Since the rule component provides high level rule patterns and event-based immediate processing, system administrators and programmers can easily program and maintain intimate cooperation of distributed EC systems independently to the application logic. The proposed active rule component facilitates HTTP protocol. Its prototype is implemented in B2B EC environment and evaluated using basic trigger facility of a commercial DBMS.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.4
• /
• pp.353-359
• /
• 2005

In this research, we propose a Unified Fuzzy rule-based knowledge Inference Systems (UFIS) to help the expert in cosmetic brand detection. Users' preferred cosmetic product detection is very important in the level of CRM. To this purpose, many corporations trying to develop an efficient data mining tool. In this study, we develop a prototype fuzzy rule detection and inference system. The framework used in this development is mainly based on two different mechanisms such as fuzzy rule extraction and RDB (Relational DB)-based fuzzy rule inference. First, fuzzy clustering and fuzzy rule extraction deal with the presence of the knowledge in data base and its value is presented with a value between 0 -1. Second, RDB and SQL (Structured Query Language)-based fuzzy rule inference mechanism provide more flexibility in knowledge management than conventional non-fuzzy value-based KMS (Knowledge Management Systems).

• International journal of advanced smart convergence
• /
• v.8 no.2
• /
• pp.94-101
• /
• 2019

Building a stable knowledge base is an important issue in the application of knowledge engineering. In this paper, we present an algorithm for detecting and locating discrepancies in the line of the reasoning process especially when discrepancies occur on belief values. This includes backtracking the rule firing from a goal node of the rule network. Retracting a belief function allows the current belief state to move back to another belief state without the rule firing. It also gives an estimate, called contribution measure, of how much the rule has an impact on the current belief state. Examining the measure leads the expert to locate the possible cause of problem in the rule. For non-monotonic reasoning, the belief retraction method moves the belief state back to the previous state. A tracing algorithm is presented to identify and locate the cause of problem. This also gives repair suggestions for rule refinement.