• The KIPS Transactions:PartD
• /
• v.9D no.2
• /
• pp.215-226
• /
• 2002

Considering the rapid process of media's breakthrough and diverse patterns of consumptions's analysis, a uniform analysis might be much rooms to be desired for interpretation of new phenomena. In special, the products happening intensive sails on around an anniversary or fresh food have the restricted marketing hours. Moreover, traditional association rule discovery algorithms might not be appropriate for analysis of sales pattern given in a specific time because existing approaches require iterative scan operation to find association rule in large scale transaction databases. in this paper, we propose an incremental candidate set management model based on twin-hashing technique to find association rule in special sales pattern using database trigger and stored procedure. We also prove performance of the proposed model through implementation and experiment.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.1
• /
• pp.149-156
• /
• 2014

NGE(Nested Generalized Exemplar Method) can increase the performance of the noisy data at the same time, can reduce the size of the model. It is the optimal distance-based classification method using a matching rule. NGE cross or overlap hyperrectangles generated in the learning has been noted to inhibit the factors. In this paper, We propose the DHGen(Dominant Hyperrectangle Generation) algorithm which avoids the overlapping and the crossing between hyperrectangles, uses interval weights for mixed hyperrectangles to be splited based on the mutual information. The DHGen improves the classification performance and reduces the number of hyperrectangles by processing the training set in an incremental manner. The proposed DHGen has been successfully shown to exhibit comparable classification performance to k-NN and better result than EACH system which implements the NGE theory using benchmark data sets from UCI Machine Learning Repository.

• Preventive Nutrition and Food Science
• /
• v.7 no.2
• /
• pp.174-178
• /
• 2002

The influence of physical forms of gelatinized rice products on enzymatic hydrolysis in vitro and glycemic and insulinemic responses in normal subjects were studied. Densities of garaedu, bagsulgi, and cooked rice were 1.20, 1.18 and 1.11 g/mL, respectively, while moisture contents of garaeduk, bagsulgi, and cooked rice were 47.5, 43.1 and 66.0% (wt.), respectively. The highest initial rate of in vitro hydrolysis by porcine pancreatic $\alpha$-amylase was observed in bagsulgi followed by cooked rice and garaeduk. However, time for complete hydrolysis seemed to reach a plateau value. Postprandial glucose and insulin responses and satiety of rice products were studied in 12 normal subjects (mean age 23.2 $\pm$ 2.4 years, 6 men and 6 women). Postprandial serum glucose and insulin levels, after consumption of the rice products, reached a peak at 30 min. Garaeduk showed significantly less incremental responses for glucose (1627.5$\pm$134.9 mg.min/dL) and insulin (2041$\pm$287.0 uU.min/mL) than did bagsulgi for glucose (2407.4$\pm$208.3 mg.min/dL) and insulin (3582$\pm$264.4 uU.min/mL). Satiety responses to the rice products were not significantly different. Therefore, it can be concluded that garaeduk may be more beneficial in controlling postprandial hyperglycemia and hyperinsulinemia than bagsulgi. These results also suggest that physical properties of starch products, acquired by the specific processing methods, affect postprandial metabolism of carbohydrate foods.

• Elastomers and Composites
• /
• v.44 no.4
• /
• pp.384-390
• /
• 2009

Roll-to-roll forming process is one of important metal processing technology because the process is simple and economical. These days, with these merits, roll-to-roll forming process is tried to be employed in manufacturing the circuit board, barrier ribs and solar cell plate. The solar cell plate may have millions of patterns, and the analysis of forming considering all the patterns is impossible due to the computational costs. In this study, analyses are carried out for various numbers of patterns and the results are compared. It is shown that the analyses results with four row patterns and twelve row patterns are same. So, it is considered that the analysis can be carried out for only four rows of pattern for the design of incremental roll-to-roll forming process. Also formability is analysed for various number of mesh, protrusion shapes and forming temperature.

• The KIPS Transactions:PartD
• /
• v.11D no.3
• /
• pp.731-740
• /
• 2004

In this paper we propose a fast negotiation agent system that guarantees the reciprocity of the attendants in a bilateral negotiation on the e-commerce. The proposednegotiation agent system exploits the incremental learning method based on an artificial neural network in generating a counter-offer and is trained by the previous offer that has been rejected by the other party. During a negotiation, the software agents on behalf of a buyer and a seller negotiate each other by considering the multi-attributes of a product. The experimental results show that the proposed negotiation system achieves better agreements than other negotiation agent systems that are operated under the realistic and practical environment. Furthermore, the proposed system carries out negotiations about twenty times faster than the previous negotiation systems on the average.

• The KIPS Transactions:PartD
• /
• v.11D no.3
• /
• pp.519-532
• /
• 2004

With the explosion of bioinformatics data such proteins and genes, biologists need a integrated system to analyze and organize large datasets that interact with heterogeneous types of biological data. In this paper, we propose a integration system based on a mediated data warehouse architecture using a XML model in order to combine protein related data at biology laboratories. A fact constellation model in this system is used at a common model for integration and an integrated schema it translated to a XML schema. In addition, to track source changes and provenance of data in an integrated database employ incremental update and management of sequence version. This paper shows modeling of integration for protein structures, sequences and classification of structures using the proposed system.

• The KIPS Transactions:PartD
• /
• v.19D no.1
• /
• pp.29-38
• /
• 2012

Software globalization is becoming more important worldwide but little is known about how globalization technologies are actually carried out in the Korean software industry. In this paper, we have designed Globalization Quality Management (GQM) framework and applied the framework to the industry domestically for the first time. GQM provides a structured and effective way for software organizations to adopt globalization practices and evaluate the results. GQM consists of three main components: 1) software quality management process, 2) globalization support model and 3) globalization assessment model. This framework also supports both plan-driven and iterative/incremental development methods. On the basis of the GQM, a survey study was conducted among software engineering professionals, gathering the data from 31 IT companies across 7 large-scale projects in Korea. The result indicate that the evaluation score for globalization capability is 2.47 and global readiness is 2.55 out of 5 points. Also It said that internationalized product design (32.9%) and global/local product requirements analysis (28%) are needed to be taken care of first.

• The KIPS Transactions:PartD
• /
• v.14D no.2
• /
• pp.169-180
• /
• 2007

This paper discusses a new unsupervised XML document clustering technique based on the function transform and FFT(Fast Fourier Transform). An XML document is transformed into a discrete function based on the hierarchical nesting structure of the elements. The discrete function is, then, transformed into vectors using FFT. The vectors of two documents are compared using a weighted Euclidean distance metric. If the comparison is lower than the pre specified threshold, the two documents are considered similar in the structure and are grouped into the same cluster. XML clustering can be useful for the storage and searching of XML documents. The experiments were conducted with 800 synthetic documents and also with 520 real documents. The experiments showed that the function transform and FFT are effective for the incremental and unsupervised clustering of XML documents similar in structure.

• The KIPS Transactions:PartB
• /
• v.12B no.4 s.100
• /
• pp.429-436
• /
• 2005

A simple stereo matching algorithm using population-based incremental learning(PBIL) is proposed in this paper to decrease the general problem of genetic algorithms, such as memory consumption and inefficiency of search. PBIL is a variation of genetic algorithms using stochastic search and competitive teaming based on a probability vector. The structure of PBIL is simpler than that of other genetic algorithm families, such as serial and parallel ones, due to the use of a probability vector. The PBIL strategy is simplified and adapted for stereo matching circumstances. Thus, gene pool, chromosome crossover, and gene mutation we removed, while the evolution rule, that fitter chromosomes should have higher survival probabilities, is preserved. As a result, memory space is decreased, matching rules are simplified and computation cost is reduced. In addition, a scheme controlling the distance of neighbors for disparity smoothness is inserted to obtain a wide-area consistency of disparities, like a result of coarse-to-fine matchers. Because of this scheme, the proposed algorithm can produce a stable disparity map with a small fixed-size window. Finally, an alterative version of the proposed algorithm without using probability vector is also presented for simpler set-ups.

• The KIPS Transactions:PartB
• /
• v.10B no.3
• /
• pp.297-304
• /
• 2003

Nowdays, with the explosive growth of the web information, web users Increase requests of systems which collect and analyze web pages that are relevant. The systems which were develop to solve the request were used clustering methods to improve the duality of information. Clustering is defining inter relationship of unordered data and grouping data systematically. The systems using clustering provide the grouped information to the users. So, they understand the information efficiently. We proposed a hybrid clustering method to cluster a large quantity of data efficiently. By that method, We generate initial clusters using COBWEB Algorithm and refine them using Ezioni Algorithm. This paper adds two ideas in prior hybrid clustering method to increment accuracy and efficiency of clusters. Firstly, we propose the clustering method considering weight of attributes of data. Second, we redefine evaluation functions which generate initial clusters to increase efficiency in clustering. Clustering method proposed in this paper processes a large quantity of data and diminish of dependancy on sequence of input of data. So the clusters are useful to make user profiles in high quality. Ultimately, we will show that the proposed clustering method outperforms the pervious clustering method in the aspect of precision and execution speed.