• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.6
• /
• pp.345-352
• /
• 2014

Edge detection considers the important technical details of digital image processing. Many edge detection operators already perform edge detection in digital color imaging. In this study, the edge of many real color images that represent the type of digital image was detected using a new operator in the least square approximation method, which is a type of numerical method. The Linear Fitting algorithm is computationally more expensive compared to the Canny, LoG, Sobel, Prewitt, HIS, Fuzzy, Parametric, Synthetic and Vector methods, and Robert' operators. The results showed that the new method can detect an edge in a digital color image with high efficiency compared to standard methods used for edge detection. In addition, the suggested operator is very useful for detecting the edge in a digital color image.

• Communications for Statistical Applications and Methods
• /
• v.6 no.3
• /
• pp.843-848
• /
• 1999

Support vector machine(SVM) is a new and very promising classification and regression technique developed by Bapnik and his group at AT&T Bell laboratories. However it has failed to establish itself as common machine learning tool. This is partly due to the fact that SVM is not easy to implement and its standard implementation requires the optimization package for quadratic programming. In this paper we present simple iterative Kernl Adatron algorithm for nonparametric regression which is easy to implement and guaranteed to converge to the optimal solution and compare it with neural networks and projection pursuit regression.

• Communications for Statistical Applications and Methods
• /
• v.6 no.2
• /
• pp.337-344
• /
• 1999

Support vector machine(SVM) is a new and very promising regression and classification technique developed by Vapnik and his group at AT&T Bell laboratories. This article provides a brief overview of SVM focusing on linear regression. We explain from statistical point of view why SVM might be attractive and how this could be compared with other linear regression techniques. Furthermore. we explain model selection based on VC-theory.

• Communications for Statistical Applications and Methods
• /
• v.6 no.3
• /
• pp.813-820
• /
• 1999

Supprot vector machine(SVM) is a new and very promising regression and classification technique developed by Vapnik and his group at AT&T Bell Laboratories. in this paper we provide a brief overview of SVM for regression. Furthermore we describe Bayesian model selection based on macKay's evidence framework for SVM regression.

• Journal of Sasang Constitutional Medicine
• /
• v.22 no.1
• /
• pp.17-25
• /
• 2010

1. Objectives: Voice diagnosis has been used to classify individuals into the Sasang constitution in SCM(Sasang Constitution Medicine) and to recognize his/her health condition in TKM(Traditional Korean Medicine). In this paper, we purposed a new speech classification algorithm for Sasang constitution. 2. Methods: This algorithm is based on the SVM(Support Vector Machine) technique, which is a classification method to classify two distinct groups by finding voluntary nonlinear boundary in vector space. It showed high performance in classification with a few numbers of trained data set. We designed for this algorithm using 3 SVM classifiers to classify into 4 groups, which are composed of 3 constitutional groups and additional indecision group. 3. Results: For the optimal performance, we found that 32.2% of the voice data were classified into three constitutional groups and 79.8% out of them were grouped correctly. 4. Conclusions: This new classification method including indecision group appears efficient compared to the standard classification algorithm which classifies only into 3 constitutional groups. We find that more thorough investigation on the voice features is required to improve the classification efficiency into Sasang constitution.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.51 no.12
• /
• pp.597-602
• /
• 2002

The restructuring of power industry is still going on all over the world for last several decades. Many kinds of restructuring model have been studied, proposed, and applied. Among those models, power pool is more popular than other. This paper assumes the power pool market structure having competitive generation sector, and a new method is presented to build a bidding strategy in that market. The utilities participating in the market have the perfect information of their cost and price functions, but they don't know which strategy to be chosen by others. To define one's strategy as a vector, we make utility's cost/price functions into discrete step functions. An utility knows only his own strategy, so he estimates the other's cost/price functions into discrete step functions. An utility knows only his own strategy, so he estimates the other's strategy using Nash equilibrium or stochastic methods. And he also has to forecast the system demand. According to this forecasting result, his payoffs can be changed. Considering these all conditions, we formulate a bidding game problem and apply noncooperative game theory to that problem for the optimal strategy or solution. Some restrictive assumption are added for simplification of solving process. A numerical example is given in Case Study to show essential features and concrete results of this approach.

• Journal of Microbiology and Biotechnology
• /
• v.14 no.2
• /
• pp.231-236
• /
• 2004

The inexpensive large-scale production of pure PGA (Penicillin G Acylase) has been a commercial goal. PGA has been used as a model enzyme in the development of simple one-step purification methods. In this study, the purification of poly-His tagged PGA protein secreted into the periplasmic space was carried out by using immobilized metal-ion affinity chromatography (IMAC). The PGA gene was obtained from E. coli ATCC 11105. Codons encoding histidines were fused at the C-terminus of the PGA gene by PCR. E. coli JM109 harboring pPGA-HIS6 vector produced active his-tagged acylases in the presence of lac promoter during cultivation at $26^{\circ}C$. The maximum specific activity of the acylase purified by using one-step chromatography after osmotic shock was 38.5 U/mg and was recovered with the yield of 70％. Both 23 kDa ($\alpha$) and 62 kDa ($\beta$) subunits were recovered by using IMAC with just C-terminus tagging of the $\beta$ subunit. The purification of the periplasmic fraction by osmotic shock and that of purified acylase was increased by 2.6-fold and 19-fold, respectively, compared to the crude extract.

• Proceedings of the KIEE Conference
• /
• 2001.11b
• /
• pp.57-59
• /
• 2001

The restructuring of power industry is still going on all over the world for last several decades. Many kinds of restructuring model has been studied, proposed, and applied. Among those models, power pool is more popular than others. This paper assumes the power pool market structure having competitive generation sector and a new method is presented to build bidding strategy in that market. The utilities participating in the market have the perfect information on their cost and price functions, but they don't know the strategy to be chosen by others. To define one's strategy as a vector, we make utility's cost/price function into discrete step function. An utility knows only his own strategy, so he estimates the other's strategy using stochastic methods. For considering these conditions, we introduce the Bayesian rules and noncooperative game theory concepts. Also additional assumptions are included for simplification of solving process. Each utility builds the strategy to maximize his own expected profit function using noncooperative Bayesian game. A numerical example is given in case study to show essential features of this approach.

• Proceedings of the Korean Society of Sericultural Science Conference
• /
• 2003.10a
• /
• pp.149-150
• /
• 2003

The purpose of this experiment is to optimize the yield of the recombinant Cox2 from the stably transformed Drosophila melanogaster S2 cells, using dimethylsulfoxide and sodium butyrale. Materials and Methods : Materials - Cell line : Drosophila melanogaster Schneider 2 (S2) cells - vector pMT/BiP/V5-His and pCoHygro (Invitrogen) (omitted)

• Proceedings of the Korean Society of Sericultural Science Conference
• /
• 2003.10a
• /
• pp.147-148
• /
• 2003

The purpose of this experiment is to confirm whether the recombinant tumstatin revealed from the stably transformed Drosophila melanogaster S2 cells has in vitro capacity. Materials and Methods : Materials - Cell line : Drosophila melanogaster Schneider 2 (S2) cells - vector pMT/BiP/V5-His and pCoHygro (Invitrogen) (omitted)