• Journal of Animal Science and Technology
• /
• v.52 no.5
• /
• pp.349-356
• /
• 2010

This study was conducted to estimate heritabilities, repeatabilities and rank correlation coefficients among breeding values for litter size and sex ratio of Yorkshire and Landrace pigs using various single trait animal models. The analyses were carried out the data comprising 26,390 litters of Yorkshire and 26,173 litters of Landrace collected from the year 1998 to 2008 at a private swine breeding farm located in central part of Korea. Five different analytical models were used for genetic parameter estimation. Model 1 was most simple basic model fitted with year-month contemporary group fixed effect, random additive genetic effect and random residual effect. Model 2 was similar to the model 1 but permanent maternal environmental effect added as random effect, and model 3 was similar with the model 2 but linear and quadratic effects of sow age were added as fixed covariate effect. Model 4 was similar as model 2 except that the parity was added as fixed effect and model 5 was similar to model 3 or model 4 but covariate of sow age was nested within parity effect. The results obtained in this study are summarized as follows: The means and standard error of total number of pigs born per litter (TNB) and number of pigs born alive per litter (NBA) were $11.35{\pm}0.02$ and $10.04{\pm}0.02$ for Yorkshire, $10.97{\pm}0.02$ and $9.98{\pm}0.02$ for Landrace, respectively. The sex ratio (percentage of female per litter) was $45.75{\pm}0.11%$ and $45.75{\pm}0.11%$ for Yorkshire and Landrace, respectively. The heritability estimates of TNB (0.243) and NBA (0.192) from model 1 tended to be higher than those from any other models in both breeds. Differences in heritability and repeatability for TNB were not large among models 3, 4 and 5 and same tendency of negligible differences among estimates by models 3, 4 and 5 were observed for NBA, where heritability and repeatability ranged from 0.096 to 0.099 and from 0.188 to 0.193, respectively, in Yorkshire; and ranged from 0.092 to 0.098 and from 0.193 and 0.196, respectively, in Landrace. The heritability estimates for sex ratio were close to zero which was ranged from 0.002 to 0.003 for TNB and from 0.001 to 0.003 for NBA over the models applied. The rank correlation coefficients of breeding values by model 1 with those from other models (model 2, 3, 4 and 5), and breeding values by model 2 with those from other models (model 1, 3, 4 and 5) were highly positive but lower than the coefficients among breeding values by model 3, model 4 and model 5 which were high of 0.99, approximately, for TNB and NBA of both breeds.

• Journal of Animal Science and Technology
• /
• v.46 no.4
• /
• pp.509-516
• /
• 2004

This study is to investigate the amount of biased estimates for heritability and genetic correlation according to data structure on marbling scores in Korean cattle. Breeding population with 5 generations were simulated by way of selection for carcass weight, Longissimus muscle area and latent values of marbling scores and random mating. Latent variables of marbling scores were categorized into five by the thresholds of 0, I, 2, and 3 SD(DSI) or seven by the thresholds of -2, -1, 0,1I, 2, and 3 SD(DS2). Variance components and genetic pararneters(Heritabilities and Genetic correlations) were estimated by restricted maximum likelihood on multivariate linear mixed animal models and by Gibbs sampling algorithms on multivariate threshold mixed animal models in DS1 and DS2. Simulation was performed for 10 replicates and averages and empirical standard deviation were calculated. Using REML, heritabilitis of marbling score were under-estimated as 0.315 and 0.462 on DS1 and DS2, respectively, with comparison of the pararneter(0.500). Otherwise, using Gibbs sampling in the multivariate threshold animal models, these estimates did not significantly differ to the parameter. Residual correlations of marbling score to other traits were reduced with comparing the parameters when using REML algorithm with assuming linear and normal distribution. This would be due to loss of information and therefore, reduced variation on marbling score. As concluding, genetic variation of marbling would be well defined if liability concepts were adopted on marbling score and implemented threshold mixed model on genetic parameter estimation in Korean cattle.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.303-308
• /
• 2020

The ReLU(Rectified Linear Unit) function has been dominantly used as a standard activation function in most deep artificial neural network models since it was proposed. Later, Leaky ReLU, Swish, and Mish activation functions were presented to replace ReLU, which showed improved performance over existing ReLU function in image classification task. Therefore, we recognized the need to experiment with whether performance improvements could be achieved by replacing the RELU with other activation functions in the super resolution task. In this paper, the performance was compared by changing the activation functions in EDSR model, which showed stable performance in the super resolution task. As a result, in experiments conducted with changing the activation function of EDSR, when the resolution was converted to double, the existing activation function, ReLU, showed similar or higher performance than the other activation functions used in the experiment. When the resolution was converted to four times, Leaky ReLU and Swish function showed slightly improved performance over ReLU. PSNR and SSIM, which can quantitatively evaluate the quality of images, were able to identify average performance improvements of 0.06%, 0.05% when using Leaky ReLU, and average performance improvements of 0.06% and 0.03% when using Swish. When the resolution is converted to eight times, the Mish function shows a slight average performance improvement over the ReLU. Using Mish, PSNR and SSIM were able to identify an average of 0.06% and 0.02% performance improvement over the RELU. In conclusion, Leaky ReLU and Swish showed improved performance compared to ReLU for super resolution that converts resolution four times and Mish showed improved performance compared to ReLU for super resolution that converts resolution eight times. In future study, we should conduct comparative experiments to replace activation functions with Leaky ReLU, Swish and Mish to improve performance in other super resolution models.

• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.139-155
• /
• 2009

For the last few decades, many studies have tried to explore and unveil venture companies' success factors and unique features in order to identify the sources of such companies' competitive advantages over their rivals. Such venture companies have shown tendency to give high returns for investors generally making the best use of information technology. For this reason, many venture companies are keen on attracting avid investors' attention. Investors generally make their investment decisions by carefully examining the evaluation criteria of the alternatives. To them, credit rating information provided by international rating agencies, such as Standard and Poor's, Moody's and Fitch is crucial source as to such pivotal concerns as companies stability, growth, and risk status. But these types of information are generated only for the companies issuing corporate bonds, not venture companies. Therefore, this study proposes a method for evaluating venture businesses by presenting our recent empirical results using financial data of Korean venture companies listed on KOSDAQ in Korea exchange. In addition, this paper used multi-class SVM for the prediction of DEA-based efficiency rating for venture businesses, which was derived from our proposed method. Our approach sheds light on ways to locate efficient companies generating high level of profits. Above all, in determining effective ways to evaluate a venture firm's efficiency, it is important to understand the major contributing factors of such efficiency. Therefore, this paper is constructed on the basis of following two ideas to classify which companies are more efficient venture companies: i) making DEA based multi-class rating for sample companies and ii) developing multi-class SVM-based efficiency prediction model for classifying all companies. First, the Data Envelopment Analysis(DEA) is a non-parametric multiple input-output efficiency technique that measures the relative efficiency of decision making units(DMUs) using a linear programming based model. It is non-parametric because it requires no assumption on the shape or parameters of the underlying production function. DEA has been already widely applied for evaluating the relative efficiency of DMUs. Recently, a number of DEA based studies have evaluated the efficiency of various types of companies, such as internet companies and venture companies. It has been also applied to corporate credit ratings. In this study we utilized DEA for sorting venture companies by efficiency based ratings. The Support Vector Machine(SVM), on the other hand, is a popular technique for solving data classification problems. In this paper, we employed SVM to classify the efficiency ratings in IT venture companies according to the results of DEA. The SVM method was first developed by Vapnik (1995). As one of many machine learning techniques, SVM is based on a statistical theory. Thus far, the method has shown good performances especially in generalizing capacity in classification tasks, resulting in numerous applications in many areas of business, SVM is basically the algorithm that finds the maximum margin hyperplane, which is the maximum separation between classes. According to this method, support vectors are the closest to the maximum margin hyperplane. If it is impossible to classify, we can use the kernel function. In the case of nonlinear class boundaries, we can transform the inputs into a high-dimensional feature space, This is the original input space and is mapped into a high-dimensional dot-product space. Many studies applied SVM to the prediction of bankruptcy, the forecast a financial time series, and the problem of estimating credit rating, In this study we employed SVM for developing data mining-based efficiency prediction model. We used the Gaussian radial function as a kernel function of SVM. In multi-class SVM, we adopted one-against-one approach between binary classification method and two all-together methods, proposed by Weston and Watkins(1999) and Crammer and Singer(2000), respectively. In this research, we used corporate information of 154 companies listed on KOSDAQ market in Korea exchange. We obtained companies' financial information of 2005 from the KIS(Korea Information Service, Inc.). Using this data, we made multi-class rating with DEA efficiency and built multi-class prediction model based data mining. Among three manners of multi-classification, the hit ratio of the Weston and Watkins method is the best in the test data set. In multi classification problems as efficiency ratings of venture business, it is very useful for investors to know the class with errors, one class difference, when it is difficult to find out the accurate class in the actual market. So we presented accuracy results within 1-class errors, and the Weston and Watkins method showed 85.7% accuracy in our test samples. We conclude that the DEA based multi-class approach in venture business generates more information than the binary classification problem, notwithstanding its efficiency level. We believe this model can help investors in decision making as it provides a reliably tool to evaluate venture companies in the financial domain. For the future research, we perceive the need to enhance such areas as the variable selection process, the parameter selection of kernel function, the generalization, and the sample size of multi-class.

• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.21 no.4
• /
• pp.325-334
• /
• 2008

The standard prestressed concrete I-girder bridge (PSC I-girder bridge) is one of the most prevalent types for small and medium bridges in Korea. When determining the member forces in a section to assess the safety of girder in this type of bridge, the general practice is to use the simplified practical equations or the live load distribution factors proposed in design standards rather than the precise analysis through the finite element method or so. Meanwhile, the live load distribution factors currently used in Korean design practice are just a reflection of overseas research results or design standards without alterations. Therefore, it is necessary to develop an equation of the live load distribution factors fit for the design conditions of Korea, considering the standardized section of standard PSC I-girder bridges and the design strength of concrete. In this study, to develop an equation of the live load distribution factors, a parametric analysis and sensitivity analysis were carried out on the parameters such as width of bridge, span length, girder spacing, width of traffic lane, etc. As a result, the major variables to determine the size of distribution factors were girder spacing, overhang length and span length in case of external girders. For internal adjacent girders, the determinant factors were girder spacing, overhang length, span length and width of bridge. For internal girders, the factors were girder spacing, width of bridge and span length. Then, an equation of live load distribution factors was developed through the multiple linear regression analysis on the results of parametric analysis. When the actual practice engineers design a bridge with the equation of live load distribution factors developed here, they will determine the design of member forces ensuring the appropriate safety rate more easily. Moreover, in the preliminary design, this model is expected to save much time for the repetitive design to improve the structural efficiency of PSC I-girder bridges.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.185-202
• /
• 2012

.Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

• Bulletin of the Korean Chemical Society
• /
• v.34 no.6
• /
• pp.1684-1688
• /
• 2013

A rapid and sensitive method for determining usnic acid of Lethariella cladonioides in rat was established using high performance liquid chromatography (HPLC) quadrupole time-of-flight (QTOF) tandem mass (MS/MS). Rat plasma was pretreated by mixture of acetonitrile and chloroform to precipitate plasma proteins. Chromatographic separation was achieved on a column ($50{\times}2.1$ mm, $5{\mu}m$) with a mobile phase consisting of water (containing $5{\times}10^{-3}$ M ammonium formate, pH was adjusted to 3.0 with formic acid) and acetonitrile (20:80, v/v) at a flow rate of 0.3 mL/min. A tandem mass spectrometric detection with an electrospray ionization (ESI) interface was conducted via collision induced dissociation (CID) under negative ionization mode. The MS/MS transitions monitored were m/z 343.0448 ${\rightarrow}$ m/z 313.2017 for usnic acid and m/z 153.1024 ${\rightarrow}$ m/z 136.2136 for protocatechuic acid (internal standard). The linear range was calculated to be 2.0-160.0 ng/mL with a detection limit of 3.0 pg/mL. The inter- and intra-day accuracy and precision were within ${\pm}7.0%$. Pharmacokinetic study showed that the apartment of usnic acid in vivo confirmed to be a two compartment open model. The method was fully valid and will probably be an alternative for pharmacokinetic study of usnic acid.

• Journal of Korea Water Resources Association
• /
• v.36 no.3 s.134
• /
• pp.385-398
• /
• 2003

The concept of the effective storage ratio has been suggested to determine the size of detention pond by the previous researchers. The 11 pump - pond facilities in Dongdu-chun city were selected to analyze the critical duration for design rainfall and the storage ratio for each rainfall duration in this study It has been then found that the criteria of the maximum storage ratio is not reasonable for determining the size of detention pond because the difference of storage ratio with respect to each rainfall duration is too small. Moreover, since the size of pond compared with the pump capacity is not always big enough, the pump should be frequently operated, which may result in pump failure. Thus, the pond should be sufficiently sized to prevent the possibility of the pump failure due to frequent operation. According to the analyses for changing pump capacity, it has been found that if the function of the pond compared with the pump is concentrated, determining the size of pond based on the storage ratio is operationally feasible for even small basin. Thus, an improved procedure based on the storage ratio for determining the size of detention pond in small basin has been suggested. The results by the proposed procedure considering pump switching frequency may lead to reasonable pump operation. A simple linear programming model has been also adopted to figure out the relationship between pump capacity and pond size. It has been shown that the determination lot the size of detention pond based on conventional hydrologic flood routing in pond is feasible for only urban districts not rural areas.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.11
• /
• pp.843-850
• /
• 2020

The purpose of this study is to evaluate the structural risk and weakness of a railway tank car through nonlinear collision analysis according to overseas collision safety standards. The goal is to propose a crash safety design guideline for railway tank cars for transporting dangerous goods in Korea. We analyzed the buffer impact test procedure of railway freight cars prescribed in EN 12663-2 and the tank puncture test criteria prescribed in 49CFR179. A nonlinear finite element model according to each standard was modeled using LS-DYNA, a commercial finite element analysis solver. As a result of the buffing impact test simulation, it was predicted that plastic deformation would not occur at a collision speed of 6 km/h or less. However, plastic deformation was detected at the rear of the center sill and at the tank center supporting the structure at a collision speed of 8 km/h or more. As a result of a head-on test simulation of tank puncture, the outer tank shell was destroyed at the corner of the tank head when 4% of the kinetic energy of the impacter was absorbed. The tank shell was destroyed in the area of contact with the impacter in the test mode analysis of tank shell puncture when the kinetic energy of the moving vehicle was reduced by 30%. Therefore, the simulation results of the puncture test show that fracture at the tank shell and leakage of the internal material is expected. Consequently, protection and structural design reinforcement are required on railway tank cars in Korea.