• Journal of Korean Society of Rural Planning
• /
• v.12 no.3 s.32
• /
• pp.81-95
• /
• 2006

The objective of the this study is to find a way to increase fm household income through investigating their computer applications. We utilized the 2000 Korea Agricultural Survey data and applied a Heckman Selection Model to correct a selection bias. The present study found the following results. First, determinant of income among fm households by the level of computer applications has significant statistical differences based on their choices of computer applications. Accordingly, the application of general linear regression about fm income without adjusting these choices may cause statistical fallacy. Second, it has been reported that increasing the member of household is not directly related to increasing the fm income. In case of computer-own farm household, the effect of decrease in income according to increasing in age was predicted. However, in the fm household not possessing computer, it shows negative relationship. It shows that an agricultural career of farm owner and educational attainment of all farm household members have positive relationship regardless of computer possession. The income of the farm household those main field is not agriculture is also found to be lower than that of farm household whose major earnings come from agriculture.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.8
• /
• pp.738-745
• /
• 2014

Recently, mobile users continuously increase, and mobile applications also increase As mobile applications increase, the mobile users used to store sensitive and private information such as Bank information, location information, ID, password on their mobile devices. Therefore, recent malicious application targeted to mobile device instead of PC environment is increasing. In particular, since the Android is an open platform and includes security vulnerabilities, attackers prefer this environment. This paper analyzes the performance of malware detection system applying linear SVM machine learning classifier to detect Android malware application. This paper also performs feature selection in order to improve detection performance.

• Korean Journal of Mathematics
• /
• v.23 no.4
• /
• pp.643-654
• /
• 2015

This study analyses the cross-application system, one of the diversified college admission processes, based on the entrance examination system by the reorganization of the education curriculum. In addition, this study suggests an improvement direction of mathematics education for students who cross-apply by comparing and analysing academic results in Calculus for those students entering universities through the cross-application system.

• The Journal of Information Systems
• /
• v.26 no.3
• /
• pp.63-90
• /
• 2017

Purpose This study proposes a novel system trading model using case-based reasoning (CBR) based on absolute similarity threshold. The proposed model is designed to optimize the absolute similarity threshold, feature selection, and instance selection of CBR by using genetic algorithm (GA). With these mechanisms, it enables us to yield higher returns from stock market trading. Design/Methodology/Approach The proposed CBR model uses the absolute similarity threshold varying from 0 to 1, which serves as a criterion for selecting appropriate neighbors in the nearest neighbor (NN) algorithm. Since it determines the nearest neighbors on an absolute basis, it fails to select the appropriate neighbors from time to time. In system trading, it is interpreted as the signal of 'hold'. That is, the system trading model proposed in this study makes trading decisions such as 'buy' or 'sell' only if the model produces a clear signal for stock market prediction. Also, in order to improve the prediction accuracy and the rate of return, the proposed model adopts optimal feature selection and instance selection, which are known to be very effective in enhancing the performance of CBR. To validate the usefulness of the proposed model, we applied it to the index trading of KOSPI200 from 2009 to 2016. Findings Experimental results showed that the proposed model with optimal feature or instance selection could yield higher returns compared to the benchmark as well as the various comparison models (including logistic regression, multiple discriminant analysis, artificial neural network, support vector machine, and traditional CBR). In particular, the proposed model with optimal instance selection showed the best rate of return among all the models. This implies that the application of CBR with the absolute similarity threshold as well as the optimal instance selection may be effective in system trading from the perspective of returns.

• The Korean Journal of Applied Statistics
• /
• v.22 no.1
• /
• pp.197-204
• /
• 2009

In the model selection problem, the main objective is to choose the true model from a manageable set of candidate models. An information criterion gauges the validity of a statistical model and judges the balance between goodness-of-fit and parsimony; "how well observed values ran approximate to the true values" and "how much information can be explained by the lower dimensional model" In this study, we introduce some information criteria modified from the Akaike Information Criterion (AIC) and the Bayesian Information Criterion(BIC). The information criteria considered in this study are compared via simulation studies and real application.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.19 no.38
• /
• pp.43-50
• /
• 1996

Evolution Programs, a form of Genetic Algorithms transformed from chromosome representation, are applied to the Timetabling of University which is one of the NP-hard problems. At the step of algorithms application, each class is established to be a specific category in feasible solution space. At. the same time, the exiting gene used in chromosome expression of Evolution Programs is modified to satisfy constraints effectively by transformation of gene which has multi-information. The new crossover method for fester operation in the Recombination attempted.. Roulette wheel selection and tournament selection are prepared.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.6 no.2
• /
• pp.85-100
• /
• 2004

In this paper the historical and technological developments of rock TBM and the technical classification of the machines proposed by ITA (International Tunnelling Association) are initially presented. Then the general criteria for the TBMs selection are discussed and at the end the limiting geological conditions for the application of TBMs are analysed.

• Journal of the Korean Home Economics Association
• /
• v.33 no.2
• /
• pp.19-27
• /
• 1995

This paper discusses the bias that results from using nonrandomly selectd samples of consumer research. A two stage system (maximum likelihood probit analysis and ordinary least square analysis) is a solution to sample selection bias. Empirical results show that correcting for sample selection bias improves the validity of consumer research results.

• Proceedings of the KIEE Conference
• /
• 1993.07b
• /
• pp.660-662
• /
• 1993

We have numerically analyzed by using the Beam Propagation Method the Dual-channel directional couplers, which peforms a number of useful fuctions in thin-films devices, including power division, modulation, switching, frequency selection, and polarization selection. We also use the effective index method to reduce one dimension.

• Proceedings of the Materials Research Society of Korea Conference
• /
• 2009.11a
• /
• pp.3.2-3.2
• /
• 2009

Microfluidics and BioMEMStechnology has increasingly been used as a tool for studying small volumes oftissue and even individual cells. One of the most important benefits ofmicrofluidic technology is the potential to build devices that analyze and sortmammalian cells. The "sorting problem" typically requires that a fewcells be selected and isolated from a larger population of hundreds, thousandsor even millions of other cells. For example, cancer tumor cells may resideamong a large population of healthy cells, but it would be of great interest toidentify, isolate and study only the cancer cells. In another application, onemay want to determine the number of white blood cells within a sample of blood.We have developed microfluidic devices that enable researchers to select cellsfrom a population by a variety of methods, including antibody staining,dielectrophoretic selection, and physical size selection. These devices haveapplications in cancer research where cancer cells must be identified fromnormal tissue, but where only small samples of tissue are available. In thistalk, we will present some of our microfluidic cell sorting devices, discusstheir physical principles, and their use in biological applications.