• Asia pacific journal of information systems
• /
• v.21 no.2
• /
• pp.43-58
• /
• 2011

Support vector machines (SVMs), a machine learning technique, has been applied to not only binary classification problems such as bankruptcy prediction but also multi-class problems such as corporate credit ratings. However, in general, the performance of SVMs can be easily worse than the best alternative model to SVMs according to the selection of predictors, even though SVMs has the distinguishing feature of successfully classifying and predicting in a lot of dichotomous or multi-class problems. For overcoming the weakness of SVMs, this study has proposed an approach for selecting features for multi-class SVMs that utilize the impurity measures of classification trees. For the selection of the input features, we employed the C4.5 and CART algorithms, including the stepwise method of discriminant analysis, which is a well-known method for selecting features. We have built a multi-class SVMs model for credit rating using the above method and presented experimental results with data regarding S&P 500 companies.

• Korean Journal of Computational Design and Engineering
• /
• v.3 no.4
• /
• pp.236-242
• /
• 1998

This paper presents a development of computer aided cutting tool selection techniques for rough and finish turning operations. The developed system,. which is one of important activities for computer aided operation planning, firstly implements operation sequencing. Then, from relations of the size of machined area, recommended finishing allowance and maximum depth of cut, a main machining method is selected, a number of cut is calculated, cutting tools including toolholders and inserts are selected, and values for cutting parameters are determined. A cutting tool selection procedure is proposed for toolholders and inserts of ISO code in rough cutting, and some important parameters such as holder style, tool approach angle, tool function and its direction are described in detail. In order to demonstrate the validity of the system a case study is performed.

• Fibers and Polymers
• /
• v.5 no.4
• /
• pp.297-302
• /
• 2004

In many engineering applications, the final decision is based on the evaluation of a number of alternatives in terms of a number of criteria. This problem may become very intricate when the selection criteria are expressed in terms of different units or the pertinent data are difficult to be quantified. The Analytic Hierarchy Process (AHP) is an effective way in dealing with such kind of complicated problems. Cotton fiber is selected or graded, in the spinning industries, based on several quality criteria. However, the existing selection or grading method based on Fiber quality Index (FqI) is rather crude and ambiguous. This paper presents a novel approach of cotton fiber selection using the AHP methodology of Multi Criteria Decision Making.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.9
• /
• pp.101-110
• /
• 1998

In process planning for 3D pocket machining, the critical issues for the optimal process planning are the generation of cutting layers and the tool selection for each cutting layers as well as the other factors such as the determination of machining types, tool path, etc. This paper describes the optimal tool selection on a single cutting layer for 2D pocket machining, the generation of cutting layers for 3D pocket machining, the determination of the thickness of each cutting layers, the determination of the tool combinations for each cutting layers and also the development of an algorithm for determining the machining sequence which reduces the number of tool exchanges, which are based on the backward approach. The branch and bound method is applied to select the optimal tools for each cutting layer, and an algorithmic procedure is developed to determine the machining sequence consisting of the pairs of the cutting layers and cutting tools to be used in the same operation.

• International journal of advanced smart convergence
• /
• v.7 no.4
• /
• pp.57-65
• /
• 2018

Artificial neural network is inspired by the biological neural network. For simplicity, in computer science, it is represented as a set of layers. Many research has been made in evaluating the number of neurons in the hidden layer but still, none was accurate. Several methods are used until now which do not provide the exact formula for calculating the number of thehidden layer as well as the number of neurons in each hidden layer. In this paper model selection approach was presented. Proposed model is based on geographical analysis of decision boundary. Proposed model selection method is useful when we know the distribution of the training data set. To evaluate the performance of the proposed method we compare it to the traditional architecture on IRIS classification problem. According to the experimental result on Iris data proposed method is turned out to be a powerful one.

• Communications for Statistical Applications and Methods
• /
• v.26 no.1
• /
• pp.69-78
• /
• 2019

A structured model with both single-index and varying coefficients is a powerful tool in modeling high dimensional data. It has been widely used because the single-index can overcome the curse of dimensionality and varying coefficients can allow nonlinear interaction effects in the model. For high dimensional index vectors, variable selection becomes an important question in the model building process. In this paper, we propose an efficient estimation and a variable selection method based on a smoothing spline approach in a partially linear single-index-coefficient regression model. We also propose an efficient algorithm for simultaneously estimating the coefficient functions in a data-adaptive lower-dimensional approximation space and selecting significant variables in the index with the adaptive LASSO penalty. The empirical performance of the proposed method is illustrated with simulated and real data examples.

• PNF and Movement
• /
• v.10 no.4
• /
• pp.41-48
• /
• 2012

Purpose : The purpose of his study was to analyze the environmental and the medical selection factor on rehabilition hospital admission. Methods : The subjects were 107 patient and inpatients. The date were collected analyzed using the SPSS window 17.0 program. Results : General hospital select the recommendation 35.5%, medical team professionalism 18%, accessibility 16%, any others 14% appear in the rehabilitation hospital admission selection factor. Conclusion : Rehabilitation hospital admission selection factor is recommend and medical team service approach.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1581-1586
• /
• 2004

In this paper, we study the tracking performance of a torsion disk system where the plant is required to track a triangular-type command signal with a small steady state error and delay. We investigate the tracking performance of the traditional inner/outer loop approach and underline its limitations in high performance applications. We then design a more advanced controller using the mixed sensitivity robust control approach and show that the tracking performance of the system can be improved substantially. The success of the design, even for the case of lightly damped plants such as the one considered in this paper, is largely the result of the proper weights selection used in the mixed sensitivity design. The main contribution of this paper is, therefore, the development of design guidelines for the weights selection when accurate tracking of periodic reference signals are desired.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.9
• /
• pp.1-8
• /
• 1993

In this paper, a new approach to the minimization of two-level Reed-Muller circuits is presented. In contrast to the previous method of using Xlinking operations to join two cubes for minimization. Cube selection method tries to select cubes one at a time until they cover the ON-set of the given function. A simple heuristic for selecting appropriate cubes is presented. In this heuristic, simply all cubes from the largest to the smallest are tried and whenever they decrease the number of remaining terms they are accepted. Since cubes once selected are not considered for a new selection, our method takes less time than other methods that need repetitive optimization process. The experimental results turned out to be improved in many cases compared to the best results in the literature.

• Journal of the Korean Society of Systems Engineering
• /
• v.10 no.1
• /
• pp.17-32
• /
• 2014

The trade-off studies in the concept development stage to assess the relative goodness of alternative systems concepts for AE (architect engineering) design for the Barge Mounted SMR (BMSMR) is introduced. With respect to design margin, system performance, schedule and risk, the design selection is cond ucted using the following characteristics; barge mobility, system safety under the natural disaster (seismic), power output, interfacing with the other system, and the additional supporting functions as desalination. There are three findings that should be remedied; deficiencies in the assumed characteristics of the system being modeled, deficiencies in the test model, and excessively stringent system requirements. This study is performed using systems engineering approach with trade off matrix method. In order to execute this work, concept development stage is divided into three (3) phases as NA (needs analysis), CE (concept exploration), and CD (concept definition).