• The Korean Journal of Applied Statistics
• /
• v.19 no.1
• /
• pp.149-161
• /
• 2006

The most important component in decision tree algorithm is the rule for split variable selection. Many earlier algorithms such as CART and C4.5 use greedy search algorithm for variable selection. Recently, many methods were developed to cope with the weakness of greedy search algorithm. Most algorithms have different selection criteria depending on the type of variables: continuous or nominal. However, ordinal type variables are usually treated as continuous ones. This approach did not cause any trouble for the methods using greedy search algorithm. However, it may cause problems for the newer algorithms because they use statistical methods valid for continuous or nominal types only. In this paper, we propose a ordinal variable selection method that uses Cramer-von Mises testing procedure. We performed comparisons among CART, C4.5, QUEST, CRUISE, and the new method. It was shown that the new method has a good variable selection power for ordinal type variables.

• Journal of the Korean Society for Library and Information Science
• /
• v.19
• /
• pp.113-149
• /
• 1990

The RAK has in general adopted the provisions of the paris principles to a far greater extent than many other cataloguing codes. And the analyses confirm that the determination of the main entries in German cataloging rules is a rather complex process and one which can result in inconsistent, arbitrary decisions. And the selection of the main entry requires a considerable amount of decision making which is time-consuming and costly. From the point of view of computers, all entries are equal as points of retrieval. In light of the above considerations the most important recommendation to be made is that the main entry principle be abandoned from cataloging theory and practice and be replaced by the title entry. It would eliminate the need for personal judgments required by the present rule. In so doing, it would bring uniformity and Standardization to cataloging practice. Use of the title entry would reduce the time and effort spent on the selection of the main entry which serves no important purpose in the catalog. Therefore title entry is more developed finding device than author entry in direct approach for document retrieval.

• Genomics & Informatics
• /
• v.14 no.4
• /
• pp.149-159
• /
• 2016

With the success of the genome-wide association studies (GWASs), many candidate loci for complex human diseases have been reported in the GWAS catalog. Recently, many disease prediction models based on penalized regression or statistical learning methods were proposed using candidate causal variants from significant single-nucleotide polymorphisms of GWASs. However, there have been only a few systematic studies comparing existing methods. In this study, we first constructed risk prediction models, such as stepwise linear regression (SLR), least absolute shrinkage and selection operator (LASSO), and Elastic-Net (EN), using a GWAS chip and GWAS catalog. We then compared the prediction accuracy by calculating the mean square error (MSE) value on data from the Korea Association Resource (KARE) with body mass index. Our results show that SLR provides a smaller MSE value than the other methods, while the numbers of selected variables in each model were similar.

• Journal of electromagnetic engineering and science
• /
• v.10 no.3
• /
• pp.190-198
• /
• 2010

This paper evaluates the performance of two methods of spectrum sensing: the linear combining method and the selection combining method which is based on maximum SNR of sensing channel. We proposed a rule for global detection for the purpose of combating hidden terminal problems in spectrum sensing. Our analysis considers a situation when sensing channels experience the non-identically, independently distributed(n.i.d) Rayleigh fading. The average probabilities of global detection in these methods are derived and compared. In the scope of this paper, the reporting channels are assumed to be the AWGN channel with invariant and identical gain during the system's operation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.279-282
• /
• 2001

This paper presents an image contrast enhancement technique for improving the low contrast images using the improved IAFC(Integrated Adaptive Fuzzy Clustering) Model. The low pictorial information of a low contrast image is due to the vagueness or fuzziness of the multivalued levels of brightness rather than randomness. Fuzzy image processing has three main stages, namely, image fuzzification, modification of membership values, and image defuzzification. Using a new model of automatic crossover point selection, optimal crossover point is selected automatically. The problem of crossover point selection can be considered as the two-category classification problem. The improved MEC can classify the image into two classes with unsupervised teaming rule. The proposed method is applied to some experimental images with 256 gray levels and the results are compared with those of the histogram equalization technique. We utilized the index of fuzziness as a measure of image quality. The results show that the proposed method is better than the histogram equalization technique.

• IE interfaces
• /
• v.7 no.2
• /
• pp.107-120
• /
• 1994

This study introduces a scheduling policy to achieve unmanned operations in machining shops representing the feature of both FMS and machining centers. The proposed policy considers the practical constraints in the machining shops such as lot sizes, multiple pallets, and jig/fixtures. In addition, rescheduling to cope with extraordinary events(eg., arrival of high-priority jobs and breakdown of machines) is included. Basically, the scheduling policy consists of four procedures; (1) selection of a job according to dispatching rule, (2) selection of a machine, (3) assignment of jobs to a multiple pallet for the unmanned operation during a certain shift, and (4) prevention of unexpected machine idle caused by constraints on jig/fixture.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.11
• /
• pp.3091-3097
• /
• 1994

An expert system for NC part programming of NC lathe (ESPP-1) is developed as a part of Computer-Adied Manufacturing system. Conventional computer-assisted part programming system essentially requires an NC part programmer who is an expert in NC part programming. But the developed ESSP-1 can allow an inexperienced person to make an excellent NC data for the NC Lathe without any problem, since the system has a knowledge base composed of EIA and ISO NC code, feed rate, spindle speed, machining coordinates selection, and tool selection etc., which were directly evoked from some skilled NC part programmers, and referenced some machining handbooks. This paper discusses the algorithm of the expert system for NC part programming of the NC lathe (ESPP-1) and the performance comparisons between the developed expert system and the conventional system.

• Journal of Arbitration Studies
• /
• v.23 no.3
• /
• pp.1-23
• /
• 2013

Form requirements particularly for arbitration clauses are widely perceived as an obstacle for efficiently resolving disputes on an international level. The paper discusses the recent suggestion that the freedom of form principle under Art. 11 CISG extended to arbitration, forum selection, or choice of law clauses in international sales contracts and thus superseded any and all formal requirements in this regard. After analysing national and international form requirements with regard to said clauses, the authors elaborate that while dispute clauses are indeed encompassed by the CISG's scope of application, freedom of form under the CISG was neither intended to nor should it apply to dispute clauses. This result is further confirmed by the interplay of the CISG with other international conventions, first and foremost the 1958 New York Convention, as well as a careful analysis of the so called most-favourable-law-approach.

• Proceedings of the KIEE Conference
• /
• 1990.07a
• /
• pp.167-170
• /
• 1990

This paper presents a preliminary study of introduction of the Dempster-Shafer inexact reasoning method to the expert system for the power system design problem. A brief review of Dempster-Shafer theory of evidence is presented and development of an inference engine adopting the Dempster-Sharer theory is reported. Developed inference engine has a ability of handling both the confirming and disconfirming knowledge represented in the production rule, and has a general purpose application in the design and diagnosis problems. Its applicability has been tested on the problem of the protection scheme selection, one of the typical design problem and we believe, it has shown the feasibility of adoption of the inexact reasoning methodology into the design problem.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1893-1896
• /
• 2002

Remediation Selection Expert System (RSES) is a rule-based expert system which is used far the selection of remediation techniques fur petroleum contaminated sites. In this paper, we describe a fuzzy logic-based sub-system: Site Characterization Sub-System (SCSS). It is an enhancement of the RSES, which is used to analyze the hydraulic properties of contaminated sites. This paper focuses on an explanation on how to apply fuzzy set theory for identification of soil types and hydraulic properties of a contaminated site. To illustrate application of fuzzy set theory to the problem, two sample cases are presented in detail.