• Communications for Statistical Applications and Methods
• /
• v.13 no.3
• /
• pp.719-732
• /
• 2006

A set of clustering algorithms with proper weight on the formulation of distance which extend to mixed numeric and multiple binary values is presented. A simple matching and Jaccard coefficients are used to measure similarity between objects for multiple binary attributes. Similarities are converted to dissimilarities between i th and j th objects. The performance of clustering algorithms with balancing weight on different similarity measures is demonstrated. Our experiments show that clustering algorithms with application of proper weight give competitive recovery level when a set of data with mixed numeric and multiple binary attributes is clustered.

• IE interfaces
• /
• v.24 no.2
• /
• pp.151-155
• /
• 2011

In this study, we propose a signomial classification method with ₀-regularization (₀-)which seeks a sparse signomial function by solving a mixed-integer program to minimize the weighted sum of the ₀-norm of the coefficient vector of the resulting function and the $L_1$-norm of loss caused by the function. $SC_0$ gives an explicit description of the resulting function with a small number of terms in the original input space, which can be used for prediction purposes as well as interpretation purposes. We present a practical implementation of $SC_0$ based on the mixed-integer programming and the column generation procedure previously proposed for the signomial classification method with $SL_1$-regularization. Computational study shows that $SC_0$ gives competitive performance compared to other widely used learning methods for classification.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.15 no.2
• /
• pp.71-83
• /
• 1990

This paper concerns the analyses of dynamic adjustments in noncooperative games where the market informations are given at discrete time intervals. During the game period, the market informations are given at discrete time intervals. During the game period, the inventories initially stored by players are to be released one day based to the completely competitive market so as to maximize each player's revenue, where players' parameters are unknown one another. Game results have shown that the continuous dynamic adjustment does not necessarily assure the better revenue, and if a player thinks that his parameter is underestimated by hig opponent, then he is better overestimate his opponent's parameter.

• Proceeding of EDISON Challenge
• /
• 2016.03a
• /
• pp.469-472
• /
• 2016

Jansen Mechanism has been a constant popularity by researchers studying legged robots because of many benefits. This paper proposed the design process of optimized legged robots using Jansen Mechanism and m.Sketch(Jansen Mechanism simulation software). First, driving part of legged robots is designed in compliance with the design regulations of a competitive exhibition. Second, setting the length of link and position of joint is conducted in keeping with the constraints. Third, Ground Length (GL) and Ground Angle Coefficient(GAC) values are extracted by m.Sketch simulation. Finally, by repeating the previous procedures, comparing the GL and GAC values, find the optimum input values. This.

• Communications for Statistical Applications and Methods
• /
• v.26 no.1
• /
• pp.57-67
• /
• 2019

Income distribution is a major concern in economic theory. In regional economics, it is often of interest to compare income distributions in different regions. Traditional methods often compare the income inequality of different regions by assuming parametric forms of the income distributions, or using summary statistics like the Gini coefficient. In this paper, we propose a nonparametric procedure to test for heterogeneity in income distributions among different regions, and a K-means clustering procedure for clustering income distributions based on energy distance. In simulation studies, it is shown that the energy distance based method has competitive results with other common methods in hypothesis testing, and the energy distance based clustering method performs well in the clustering problem. The proposed approaches are applied in analyzing data from China Health and Nutrition Survey 2011. The results indicate that there are significant differences among income distributions of the 12 provinces in the dataset. After applying a 4-means clustering algorithm, we obtained the clustering results of the income distributions in the 12 provinces.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.27 no.6
• /
• pp.1152-1159
• /
• 1998

In order to develop more rapid and reproducible analysis of biotin known as vitamin H, attempts were made to establish the condition for enzyme linked immunosorbent assay(ELISA) compared with traditional microbiological assay(MBA). Antibiotin and antiserum were obtained from the immunized rabbits injected with emulsion of biotin KLH conjugate and Freund's adjuvant. The antiserum showed cross reactivity on biocytin, a derivative of biotin, which is converted to biotin in intestine, at the rate of 177%(median inhibitory concentration(IC50)=12.58ppb), but not on other derivatives such as desthiobiotin, diaminobiotin and 2 imino biotin. Specific antibody for biotin was purified from the antiserum through protein A column and desalting column. The conditions of competitive direct ELISA (cdELISA) were established. Detection range of biotin concentration by cdELISA was 0.01∼300ng/ ml(ppb). In the spike test with milk, fruit flake and pine carrot juice, the correlation coefficient between two methods of MBA and ELISA was reliably consistent at the value of r=0.992. But detection of biotin by microbiological assay(MBA) was rather restricted in range and nonspecific. Detection range of biotin by MBA was 0.1∼0.5ng/ml(ppb). It showed cross reactivities on biocytin and desthiobiotin at the rate of 80.1% and 66.7%, respectively. In conclusion, ELISA revealed a significant improvement compared with MBA for the biotin detection in terms of sensitivity, detection range and cross reactivity. In addition, a variety of samples could be analyzed rapidly and conveniently at one time by using ELISA. These results strongly suggest that the ELISA is very promising for the practical application to detect biotin contents in a wide range of food stuffs.

• Journal of Korean Society of Water and Wastewater
• /
• v.22 no.2
• /
• pp.187-193
• /
• 2008

Biological removal capacities for volatile organic compounds (VOCs) were determined using a yeast strain, Candida tropicalis. In this study, VOCs including toluene, benzene, p-xylene, and styrene as single substrates or mixtures were tested in the batch culture of the yeast strain. In addition, a kinetic model was applied to evaluate substrate interactions between the VOCs. The yeast strain was able to biodegrade each VOC effectively as a growth substrate, implying it could applied to wide range of VOCs. When the yeast strain was subjected to VOCs in mixtures, the biodegradation rate of one substrate were either increased (stimulated) or decreased (inhibited) by the presence of the others. Both benzene and toluene were inhibited by the other VOCs, and substrate interaction parameters estimated in the model indicated that styrene was the strongest inhibitor for the benzene and toluene biodegradation. Meanwhile, the biodegradation of p-xylene and styrene was stimulated by the presence of either benzene or toluene. The biodegradation rate of p-xylene was significantly increased especially by the presence of toluene, and the styrene biodegradation was enhanced greatly by the benzene addition. The results of the substrate interaction by the yeast strain suggest that the biodegradation rates for the VOCs in mixtures should be carefully evaluated. Furthermore, the competitive inhibition coefficient could be applied as a useful index to determine the substrate interaction

• Biomedical Science Letters
• /
• v.5 no.1
• /
• pp.11-15
• /
• 1999

Thyroxine (3,5,3',5'-L-tetraiodothyronine; T$_4$) is the most commonly measured thyroid hermono for the diagnosis of various thyroid disorders. Although radioimmunoassay (RIA) is still considered as the reference technique for the measurement of T$_4$, it is generally regarded that RIA has its primary disadventages in handling the wastes and controling the human and material resources. Therefore, establishment of enzyme-linked immunosorbent assay (ELISA) has of great significance. To verify the usefulness of our enzyme immunoassay, we have obtained the standard dose response curve of T$_4$ in patient's sera which is inversely proportional to the amount of herseradish peroxidase (HRP) conjugated monoclonal antibody of T$_4$ bound to the wells. The correlation coefficient (r) between the ELISA and chemiluminescent assay was 0.444 (n=38). Thus we have investigated the establishment of rapid and sensitive competitive ELISA assay method for detection of T$_4$ in patient's sera.

• Journal of Korea Port Economic Association
• /
• v.31 no.3
• /
• pp.93-105
• /
• 2015

The purpose of this study is to outline the strategic implications of a structure analysis and trends of transferred air cargoes for the main airports of the North Asian region for 13 years from 2000 to 2012. To do so, it analyses the concentration levels using a Gini coefficient and Hirschmann Herfindahl index and represents the competitive positioning with regard to the main East Asian airports using the BCG framework and shift-share analysis. Currently, the concentration level is getting weaker in response to the emergence of Chinese airports in the north-east region. It is likely that the steady growth of air cargo of Shanghai airport (PVG) has caused the increase in concentration levels in the region. Seoul airport (ICN) may be directly in competition with PVG for air cargo in the region, giving consideration to reducing or maintaining an average increase ratio of air cargoes of ICN, NRT (Tokyo), and KIX (Osaka) for same period. In the same sense, the average increase in ratio for ICN for same period yields 1.3%, which is far behind the 6.2% and 5.2% of the north-east region and PVG respectively. Additionally, shift-share effect analysis indicates that ICN lost 422,180 tons in the north-east region during the same period, suggesting that transferred cargoes might have been forwarded to PVG.

• Journal of Korean Society of Environmental Engineers
• /
• v.22 no.12
• /
• pp.2175-2185
• /
• 2000

Respiration rate should be a reasonable state variable for the activated sludge and could be used to simulate the performance of the activated sludge process. Toxic materials are classified into three groups, competitive, noncompetitive and uncompetitive. They increase/decrease the half saturation coefficient or specific growth rate. that means decreasing of the substrate removal capacity. In this research, a pilot-scale activated sludge process was operated under extended aeration method, and a representative noncompetitive inhibitor, acidic wastewater was applied to establish a respirometry-based toxicity model. Using this model. the correlation coefficient between measured and calculated respiration rate was 0.96 when acidic wastewater(pH 3.9~5.5) was introduced continuously to the aeration tank. Even though respiration rate was decreased by toxic effect of acidic wastewater, effluent substrate concentration represented to COD was deteriorated just a little bit. It might be caused by the low ratio of readily biodegradable substrate in the input substrate. Reduction of respiration rate by decreasing of input substrate concentration was much lower than that by acidic wastewater, and hence it was estimated that the possibility of false toxic alarm caused by decreasing of substrate concentration should be low.