• Journal of The Korean Association For Science Education
• /
• v.40 no.3
• /
• pp.321-336
• /
• 2020

We explore automated scoring models of scientific argumentation. We consider how a new analytical approach using a machine learning technique may enhance the understanding of spoken argumentation in the classroom. We sampled 2,605 utterances that occurred during a high school student's science class on molecular structure and classified the utterances into five argumentative elements. Next, we performed Text Preprocessing for the classified utterances. As machine learning techniques, we applied support vector machines, decision tree, random forest, and artificial neural network. For enhancing the identification of rebuttal elements, we used a heuristic feature-engineering method that applies experts' classification of morphemes of scientific argumentation.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.7
• /
• pp.1680-1686
• /
• 1996

The deterministic update method of intensional predicates in a parallel deductive database that deductive database is distributed in a parallel computer architecture in needed. Using updated data from the deterministic update method, a strategy for parallel evaluation of intensional predicates is required. The paper is concerned with an approach to updating parallel deductive database in which very insertion or deletion can be performed in a deterministic way, and an extended parallel semi-naive evaluation algorithm in a parallel computer architecture. After presenting an approach to updating intensional predicates and strategy for parallel evaluation, its implementation is discussed. A parallel deductive database consists of the set of facts being the extensional database and the set of rules being the intensional database. We assume that these sets are distributed in each processor, research how to update intensional predicates and evaluate using the update method. The parallel architecture for the deductive database consists of a set of processors and a message passing network to interconnect these processors.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.9 no.2
• /
• pp.83-90
• /
• 1989

A runoff model was estabilished for the direct runoff hydrograph at each subareas by obtaining the storage coefficient based on stream magnitudes of geomorphic parameters. For this, the relationship between flowsection and channel distance from the outlet of each subareas was assumed as nonlinear equation, and compared with linear one. The applicability of the runoff model to the real watershed was tested for the Bochung river basin. The results of the analysis show that the model was approved to be used for the prediction of small watershed having no runoff records and a linear equation between flowsection and channel distance from the outlet of each subareas was more similar to the observed data for the upper subarea with a steep slope and small area, on the other hand, nonlinear equation for the lower subarea with mild slope and relatively large area.

• Journal of KIISE:Databases
• /
• v.31 no.1
• /
• pp.1-12
• /
• 2004

As network systems are developed rapidly and network architectures are more complex than before, it needs to use PBNM(Policy-Based Network Management) in network system. Generally, architecture of the PBNM consists of two hierarchical layers: management layer and enforcement layer. A security policy server in the management layer should be able to generate new policy, delete, update the existing policy and decide the policy when security policy is requested. And the security policy server should be able to analyze and manage the alert messages received from Policy enforcement system in the enforcement layer for the available information. In this paper, we propose an alert analyzer using data mining. First, in the framework of the policy-based network security management, we design and implement an alert analyzes that analyzes alert data stored in DBMS. The alert analyzer is a helpful system to manage the fault users or hosts. Second, we implement a data mining system for analyzing alert data. The implemented mining system can support alert analyzer and the high level analyzer efficiently for the security policy management. Finally, the proposed system is evaluated with performance parameter, and is able to find out new alert sequences and similar alert patterns.

• The Journal of the Korea Contents Association
• /
• v.9 no.11
• /
• pp.1-9
• /
• 2009

In virtual environments, such as computer game and animation, we need to enhance naturalness of crowd simulation. So, we propose a method to generate dynamically moving crowd patterns by applying emotional factors to the individual characters of a crowd in the determination of their behavior. The proposed method mimics human behavior and controls each character in a group to decide its own path according to its individual status. And it is able to generate various moving patterns as a result of letting the individuals go to another group depending upon their conditions. In this paper, some temperament and feeling factors are defined and determination rules for calculating the emotional status are also proposed. Moreover we use a fuzzy theory for accurate representation of the ambiguous expressions such as feeling bad, feeling good and so on. Our experiments show that the suggested method can simulate virtual crowd in more natural and diverse ways.

• Journal of Korea Multimedia Society
• /
• v.13 no.7
• /
• pp.1016-1022
• /
• 2010

Far-talking recognition and distributed speech recognition networking techniques are essential to control various and complex home services conveniently with voices. It is possible to control devices everywhere at home by using only voices. In this paper, we have developed the server-client DSP module for distributed speech recognition network system and proposed a new decision rule to decide intelligently whether to accept the recognition results or not by the transferred confidence rate. Simulation results show that the proposed decision rule delivers better performances than the conventional decision by majority rule or decision by first-arrival. Also, we have proposed the new interrupt-polling technique to remedy the defect of existing delay technique which always has to wait several clients' results for a few seconds. The proposed technique queries all client's status after first-arrival and decides whether to wait or not. It can remove unnecessary delay-time without any performance degradation.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.18 no.2
• /
• pp.57-61
• /
• 2008

Non-nucleus Abalone half pearls were cultured by a new technique and their structural characteristics were analyzed using an electron microscopy. This technique was found to grow the pearls depending on the shape of the internal organ of an abalone because this technique induces the pearl layers without adding any nucleus on the specified damage region of a shell. The obtained pearls exhibit natural shapes with a specific luster. The SEM analysis shows that the pearl layers are about $0.34{\mu}m$ with an uniform thickness and the surface of the shell is characterized by the pyramid-shaped bulge with a regular arrangement, which is a typical feature of single-shell. These characteristics of the pearls are thought to develop in the highly-valued Korean gems.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.8
• /
• pp.2528-2535
• /
• 2000

Technology mapping is a part of VLSI CAD system, where circuits in logical level are mapped into circuits in physical level. The performance of technology mapping system is evaluatecJ by the delay and area of the resulting circuits. In the sequential circuits, the delay of the circuit is decided by the maximal delay between registers. In this work, we introduce an FPGA mapping algorithm improved by retiming technique used in constructive level and iterative level, and by fuzzy logic technique. Initial circuit is mapped into an FPGA circuit by constructive manner and improved by iterative retiming. Criteria given to the initial circuit are structured hierarchically by decision-making functions of fuzzy logic. The proposed system shows better results than previous systems by the experiments with MCNC benchmarkers.

• The Journal of the Korea Contents Association
• /
• v.10 no.2
• /
• pp.372-380
• /
• 2010

Generally, data mining is the process of analyzing data from different perspectives and summarizing it into useful information that can be used to increase revenue, cuts costs, or both. It allows users to analyze data from many different dimensions or angles, categorize it, and summarize the relationships identified. Technically, data mining is the process of finding correlations or patterns among dozens of fields in large relational databases. Data mining is one of the fastest growing field in the computer industry. Because of According to computer technology has been improving, Massive customer data has stored in database. Using this massive data, decision maker can extract the useful information to make a valuable plan with data mining. Data mining offers service providers great opportunities to get closer to customer. Data mining doesn't always require the latest technology, but it does require a magic eye that looks beyond the obvious to find and use the hidden knowledge to drive marketing strategies. Automotive market face an explosion of data arising from customer but a rate of increasing customer is getting lower. therefore, we need to determine which customer are profitable clients whom you wish to hold. This paper builds model of customer loyalty detection and analyzes customer buying patterns in automotive market with data mining using decision tree as a quinlan C4.5 and basic statics methods.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.3
• /
• pp.411-425
• /
• 2013

The importance and necessity of the credit loan are increasing over time. Also, it is a natural consequence that the increase of the risk for borrower increases the risk of non-performing loan. Thus, we need to predict accurately in order to prevent the loss of a credit loan company. Our final goal is to build reliable and accurate prediction model, so we proceed the following steps: At first, we can get an appropriate sample by using several resampling methods. Second, we can consider variety models and tools to fit our resampling data. Finally, in order to find the best model for our real data, various models were compared and assessed.