• Communications for Statistical Applications and Methods
• /
• v.24 no.4
• /
• pp.383-396
• /
• 2017

The model in our approach assumes that computer responses are a realization of a Gaussian processes superimposed on a regression model called a Gaussian process regression model (GPRM). Selecting a subset of variables or building a good reduced model in classical regression is an important process to identify variables influential to responses and for further analysis such as prediction or classification. One reason to select some variables in the prediction aspect is to prevent the over-fitting or under-fitting to data. The same reasoning and approach can be applicable to GPRM. However, only a few works on the variable selection in GPRM were done. In this paper, we propose a new algorithm to build a good prediction model among some GPRMs. It is a post-work of the algorithm that includes the Welch method suggested by previous researchers. The proposed algorithms select some non-zero regression coefficients (${\beta}^{\prime}s$) using forward and backward methods along with the Lasso guided approach. During this process, the fixed were covariance parameters (${\theta}^{\prime}s$) that were pre-selected by the Welch algorithm. We illustrated the superiority of our proposed models over the Welch method and non-selection models using four test functions and one real data example. Future extensions are also discussed.

• Korean Journal of Childcare and Education
• /
• v.16 no.2
• /
• pp.25-45
• /
• 2020

Objective: The purpose of this study is to explore daycare-center director's perceptons of recruitment and to understand how hire beginning teachers. Methods: One hundred twenty-five directors of daycare-centers in Seoul, Incheon, and Gyeonggi-do Province answered a questionnaire that was developed by researchers. The results were analyzed by frequency analysis, descriptive statistics and multiple response analysis through SPSS 18.0. Furthermore, 17 of the directors that participated in the study were given individual interviews by qualitative methods for research. Results: First, 56.8% of the directors felt difficulty to employ beginning teachers because of 'lack of information about them' and 'uncertainty of practice capability.' On the other hand, other directors of daycare-centers said that they hire them for 'high acceptance' and 'operational efficiency of the daycare-center.' Second, the main way to recruit teachers for daycare-centers is open recruitment, and through recommendations of acquaintances or through colleges in relevant fields. Professional talent and personal characteristics were important selection criteria for recruitment, and daycare-center directors used interviews, résumés, cover-letters, and demo classes for the hiring process. Primarily, most directors select candidates through résumés and cover-letters, and the final selection is completed by conducting interviews. Conclusion/Implications: In conclusion, this study can be useful to prepare beginning teachers for employment and for educating applicants.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.9
• /
• pp.733-739
• /
• 2017

This paper is a study on PRF selection method to accurately detect the target in the target tracking mode of airborne radar. The proposed methods are an 'optimization' method to select the closest to the center of the allowable zone considering the uncertainty of the target distance and velocity prediction and a 'quasi-optimization' method to improve the real time performance. In addition, the characteristics of the proposed methods are compared and analyzed through cost function and calculation time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.9
• /
• pp.4658-4679
• /
• 2017

Android is now the most popular smartphone platform and remains rapid growth. There are huge number of sensitive privacy information stored in Android devices. Kinds of methods have been proposed to detect Android malicious applications and protect the privacy information. In this work, we focus on extracting the fine-grained features to maximize the information of Android malware detection, and selecting the least joint features to minimize the number of features. Firstly, permissions and APIs, not only from Android permissions and SDK APIs but also from the developer-defined permissions and third-party library APIs, are extracted as features from the decompiled source codes. Secondly, feature selection methods, including information gain (IG), regularization and particle swarm optimization (PSO) algorithms, are used to analyze and utilize the correlation between the features to eliminate the redundant data, reduce the feature dimension and mine the useful joint features. Furthermore, regularization and PSO are integrated to create a new joint feature mining method. Experiment results show that the joint feature mining method can utilize the advantages of regularization and PSO, and ensure good performance and efficiency for Android malware detection.

• Journal of The Korean Astronomical Society
• /
• v.27 no.2
• /
• pp.103-117
• /
• 1994

To extend the work of Gott, Park, and Lee (1989), statistical properties of gravitational lensing in a wide variety of cosmological models involving non-zero cosmological constant is investigated, using the redshifts of both lens and source and observed angular separation of images for gravitational lens systems. We assume singular isothermal sphere as lensing galaxy in homogenous and isotropic Friedmann­Lemaitre-Robertson- Walker universe, Schechter luminosity function, standard angular diameter distance formula and other galaxy parameters used in Fukugita and Turner (1991). To find the most adequate flat cosmological model and put a limit on the value of dimensionless cosmological constant $\lambda_0$, the mean value of the angular separation of images, probability distribution of angular separation and cumulative probability are calculated for given source and lens redshifts and compared with the observed values through several statistical methods. When there is no angular selection effect, models with highest value of $\lambda_0$ is preferred generally. When the angular selection effects are considered, the preferred model depends on the shape of the selection functions and statistical methods; yet, models with large $\lambda_0$ are preferred in general. However, the present data can not rule out any of the flat universe models with enough confidence. This approach can potentially select out best model. But at the moment, we need more data.

• The Journal of Information Systems
• /
• v.12 no.1
• /
• pp.145-158
• /
• 2003

Workflow is the automation of a business process, in whole or part, during which documents, information or tasks are passed from one participant to another for action, according to a set of procedural rules. The software selection problem is made difficult by the multiplicity of competing products and the lack of expertise and experience of users in the methods of software evaluation. Although the selection process for workflow is similar to that proposed for the acquisition of any software packages, differences arise in their evaluation criteria and choice methods. In this paper, we suggest the Analytic Hierarchy Process(AHP) method for selecting workflow software. The AHP is an intuitively easy method for formulating and analyzing decisions. It was developed to solve a specific class of problems that involves prioritization of potential alternate solutions. We showed how to evaluate 9 commercial workflow products by deciding the relative importance of the main criteria in the AHP model. We utilized the evaluation data for criteria ready suggested by specialist groups. Our methodology will be helpful to those who are going to adopt a best workflow product in their organizations. Although the criteria and their evaluation scores regarding workflow products are suggested, it is not easy to apply them to a real case and get solutions without a model.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.32 no.4
• /
• pp.153-160
• /
• 2009

In the research-oriented university there are various laboratories in the departments according to a major field of study. Under these circumstances the budget to purchase experimental facilities has only to be distributed among research teams and then is spent within the confines of it without rein. However, in case of college the budget for experimental facilities needs to be considered other allocation methods because of no laboratory being managed by professor. In this paper the methodology for the rational selection of experimental facilities for college is proposed. It is composed of the following ; (1) the rational allocation method of the budget for experimental facilities in consideration of the characteristics of individual departments, and (2) the evaluation and selection of the alternative experimental facilities submitting in each department. To decide rationally importance of estimation index for the determination of budget and equipment is applied the Analytic Hierarchy Process(AHP) technique. First the proposed methods are presented and then discussed with simulation results.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.3
• /
• pp.1177-1186
• /
• 2017

This paper presents a torque ripple reduction method of direct torque control (DTC) using fuzzy controller with optimal selection strategy of voltage vectors in a five-phase induction motor. The conventional DTC method has some drawbacks. First, switching frequency changes according to the hysteresis bands and motor's speed. Second, the torque ripple is rapidly increased in long control period. In order to solve these problems, some/most papers have proposed torque ripple reduction methods by using the optimal duty ratio of the non-zero voltage vector. However, these methods are complicated in accordance with the parameter. If this drawback is eliminated, the torque ripple can be reduced compared with conventional method. In addition, the DTC can be simply controlled without the use of the parameter. Therefore, the proposed algorithm is changing the voltage vector insertion time by using the designed fuzzy controller. Also, the optimized voltage vector selection method is used in accordance with the torque error. Simulation and experimental results show effectiveness of the proposed control algorithm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.08a
• /
• pp.160-164
• /
• 2008

Most questions made for remote examinations on E-learning databank based selection system use methods of making questions automatically using degree of difficulty. This methods is the kernel of a question selection that degree of difficulty as make test questions, and then needs continuous management for degree of difficulty. This paper present improved algorithms for dynamically adjustment of degree of difficulty based on examination result that is more efficient set of question. We identified this algorithms is more effective as compared with previously algorithms on web-based education system.

• Nuclear Engineering and Technology
• /
• v.53 no.12
• /
• pp.3944-3951
• /
• 2021

Several reasons such as no free lunch theorem indicate that there is not a universal Feature selection (FS) technique that outperforms other ones. Moreover, some approaches such as using synthetic dataset, in presence of large number of FS techniques, are very tedious and time consuming task. In this study to tackle the issue of dependency of estimation accuracy on the selected FS technique, a methodology based on the heterogeneous ensemble is proposed. The performance of the major learning algorithms of neural network (i.e. the FFNN-BR, the FFNN-LM) in combination with the diverse FS techniques (i.e. the NCA, the F-test, the Kendall's tau, the Pearson, the Spearman, and the Relief) and different combination techniques of the heterogeneous ensemble (i.e. the Min, the Median, the Arithmetic mean, and the Geometric mean) are considered. The target parameters/transients of Bushehr nuclear power plant (BNPP) are examined as the case study. The results show that the Min combination technique gives the more accurate estimation. Therefore, if the number of FS techniques is m and the number of learning algorithms is n, by the heterogeneous ensemble, the search space for acceptable estimation of the target parameters may be reduced from n × m to n × 1. The proposed methodology gives a simple and practical approach for more reliable and more accurate estimation of the target parameters compared to the methods such as the use of synthetic dataset or trial and error methods.