• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.4
• /
• pp.107-115
• /
• 2020

Support vector regression (SVR) is devised to solve the regression problem by utilizing the excellent predictive power of Support Vector Machine. In particular, the ⲉ-insensitive loss function, which is a loss function often used in SVR, is a function thatdoes not generate penalties if the difference between the actual value and the estimated regression curve is within ⲉ. In most studies, the ⲉ-insensitive loss function is used symmetrically, and it is of interest to determine the value of ⲉ. In SVQR (Support Vector Quantile Regression), the asymmetry of the width of ⲉ and the slope of the penalty was controlled using the parameter p. However, the slope of the penalty is fixed according to the p value that determines the asymmetry of ⲉ. In this study, a new ε-insensitive loss function with p1 and p2 parameters was proposed. A new asymmetric SVR called GSVQR (Generalized Support Vector Quantile Regression) based on the new ε-insensitive loss function can control the asymmetry of the width of ⲉ and the slope of the penalty using the parameters p1 and p2, respectively. Moreover, the figures show that the asymmetry of the width of ⲉ and the slope of the penalty is controlled. Finally, through an experiment on a function, the accuracy of the existing symmetric Soft Margin, asymmetric SVQR, and asymmetric GSVQR was examined, and the characteristics of each were shown through figures.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.5
• /
• pp.999-1005
• /
• 2011

This paper proposes a weighted least squares support vector machine for asymmetric least squares regression. This method achieves nonlinear prediction power, while making no assumption on the underlying probability distributions. The cross validation function is introduced to choose optimal hyperparameters in the procedure. Experimental results are then presented which indicate the performance of the proposed model.

• Communications for Statistical Applications and Methods
• /
• v.18 no.2
• /
• pp.165-170
• /
• 2011

Support vector quantile regression(SVQR) is capable of providing a good description of the linear and nonlinear relationships among random variables. In this paper we propose a sparse SVQR to overcome a limitation of SVQR, nonsparsity. The asymmetric e-insensitive loss function is used to efficiently provide sparsity. The experimental results are presented to illustrate the performance of the proposed method by comparing it with nonsparse SVQR.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.1
• /
• pp.71-82
• /
• 2022

Most of the predictions using machine learning are neutral predictions considering the symmetrical situation where the predicted value is not smaller or larger than the actual value. However, in some situations, asymmetric prediction such as over-prediction or under-prediction may be better than neutral prediction, and it can induce better judgment by providing various predictions to decision makers. A method called Asymmetric Twin Support Vector Regression (ATSVR) using TSVR(Twin Support Vector Regression), which has a fast calculation time, was proposed by controlling the asymmetry of the upper and lower widths of the ε-tube and the asymmetry of the penalty with two parameters. In addition, by applying the existing GSVQR and the proposed ATSVR, prediction using the prediction propensities of over-prediction, under-prediction, and neutral prediction was performed. When two parameters were used for both GSVQR and ATSVR, it was possible to predict according to the prediction propensity, and ATSVR was found to be more than twice as fast in terms of calculation time. On the other hand, in terms of accuracy, there was no significant difference between ATSVR and GSVQR, but it was found that GSVQR reflected the prediction propensity better than ATSVR when checking the figures. The accuracy of under-prediction or over-prediction was lower than that of neutral prediction. It seems that using both parameters rather than using one of the two parameters (p_1,p_2) increases the change in the prediction tendency. However, depending on the situation, it may be better to use only one of the two parameters.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.6
• /
• pp.1537-1545
• /
• 2015

Support vector quantile regression (SVQR) can be obtained by applying support vector machine with a check function instead of an e-insensitive loss function into the quantile regression, which still requires to solve a quadratic program (QP) problem which is time and memory expensive. In this paper we propose an SVQR whose objective function is composed of an asymmetric quadratic loss function. The proposed method overcomes the weak point of the SVQR with the check function. We use the iterative procedure to solve the objective problem. Furthermore, we introduce the generalized cross validation function to select the hyper-parameters which affect the performance of SVQR. Experimental results are then presented, which illustrate the performance of proposed SVQR.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.6
• /
• pp.1093-1101
• /
• 2009

Quantile regression has become a more widely used technique to describe the distribution of a response variable given a set of explanatory variables. This paper proposes a novel modelfor quantile regression using doubly penalized kernel machine with support vector machine iteratively reweighted least squares (SVM-IRWLS). To make inference about the shape of a population distribution, the widely popularregression, would be inadequate, if the distribution is not approximately Gaussian. We present a likelihood-based approach to the estimation of the regression quantiles that uses the asymmetric Laplace density.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.4
• /
• pp.208-216
• /
• 2020

With the spread of smart manufacturing, one of the key topics of the 4th industrial revolution, manufacturing systems are moving beyond automation to smartization using artificial intelligence. In particular, in the existing automatic machining, a number of machining defects and non-processing occur due to tool damage or severe wear, resulting in a decrease in productivity and an increase in quality defect rates. Therefore, it is important to measure and predict tool life. In this paper, ν-ASVR (ν-Asymmetric Support Vector Regression), which considers the asymmetry of ⲉ-tube and the asymmetry of penalties for data out of ⲉ-tube, was proposed and applied to the tool wear prediction problem. In the case of tool wear, if the predicted value of the tool wear amount is smaller than the actual value (under-estimation), product failure may occur due to tool damage or wear. Therefore, it can be said that ν-ASVR is suitable because it is necessary to overestimate. It is shown that even when adjusting the asymmetry of ⲉ-tube and the asymmetry of penalties for data out of ⲉ-tube, the ratio of the number of data belonging to ⲉ-tube can be adjusted with ν. Experiments are performed to compare the accuracy of various kernel functions such as linear, polynomial. RBF (radialbasis function), sigmoid, The best result isthe use of the RBF kernel in all cases

• Journal of the Korean Society of Visualization
• /
• v.19 no.3
• /
• pp.31-38
• /
• 2021

The energy harvesting system using an inverted flag is analyzed by using an immersed boundary method to consider the fluid and solid interaction. The inverted flag flutters at a lower critical velocity than a conventional flag. A fluttering motion is classified into straight, symmetric, asymmetric, biased, and over flapping modes. The optimal energy harvesting efficiency is observed at the biased flapping mode. Using the three different machine learning algorithms, i.e., artificial neural network, random forest, support vector regression, the energy harvesting efficiency is predicted by taking bending rigidity, inclination angle, and flapping frequency as input variables. The R² value of the artificial neural network and random forest algorithms is observed to be more than 0.9.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.157-173
• /
• 2011

As the Internet use explodes recently, the malicious attacks and hacking for a system connected to network occur frequently. This means the fatal damage can be caused by these intrusions in the government agency, public office, and company operating various systems. For such reasons, there are growing interests and demand about the intrusion detection systems (IDS)-the security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. The intrusion detection models that have been applied in conventional IDS are generally designed by modeling the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. These kinds of intrusion detection models perform well under the normal situations. However, they show poor performance when they meet a new or unknown pattern of the network attacks. For this reason, several recent studies try to adopt various artificial intelligence techniques, which can proactively respond to the unknown threats. Especially, artificial neural networks (ANNs) have popularly been applied in the prior studies because of its superior prediction accuracy. However, ANNs have some intrinsic limitations such as the risk of overfitting, the requirement of the large sample size, and the lack of understanding the prediction process (i.e. black box theory). As a result, the most recent studies on IDS have started to adopt support vector machine (SVM), the classification technique that is more stable and powerful compared to ANNs. SVM is known as a relatively high predictive power and generalization capability. Under this background, this study proposes a novel intelligent intrusion detection model that uses SVM as the classification model in order to improve the predictive ability of IDS. Also, our model is designed to consider the asymmetric error cost by optimizing the classification threshold. Generally, there are two common forms of errors in intrusion detection. The first error type is the False-Positive Error (FPE). In the case of FPE, the wrong judgment on it may result in the unnecessary fixation. The second error type is the False-Negative Error (FNE) that mainly misjudges the malware of the program as normal. Compared to FPE, FNE is more fatal. Thus, when considering total cost of misclassification in IDS, it is more reasonable to assign heavier weights on FNE rather than FPE. Therefore, we designed our proposed intrusion detection model to optimize the classification threshold in order to minimize the total misclassification cost. In this case, conventional SVM cannot be applied because it is designed to generate discrete output (i.e. a class). To resolve this problem, we used the revised SVM technique proposed by Platt(2000), which is able to generate the probability estimate. To validate the practical applicability of our model, we applied it to the real-world dataset for network intrusion detection. The experimental dataset was collected from the IDS sensor of an official institution in Korea from January to June 2010. We collected 15,000 log data in total, and selected 1,000 samples from them by using random sampling method. In addition, the SVM model was compared with the logistic regression (LOGIT), decision trees (DT), and ANN to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell 4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on SVM outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that our model reduced the total misclassification cost compared to the ANN-based intrusion detection model. As a result, it is expected that the intrusion detection model proposed in this paper would not only enhance the performance of IDS, but also lead to better management of FNE.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.127-137
• /
• 2019

Recidivism prediction has been a subject of constant research by experts since the early 1970s. But it has become more important as committed crimes by recidivist steadily increase. Especially, in the 1990s, after the US and Canada adopted the 'Recidivism Risk Assessment Report' as a decisive criterion during trial and parole screening, research on recidivism prediction became more active. And in the same period, empirical studies on 'Recidivism Factors' were started even at Korea. Even though most recidivism prediction studies have so far focused on factors of recidivism or the accuracy of recidivism prediction, it is important to minimize the prediction misclassification cost, because recidivism prediction has an asymmetric error cost structure. In general, the cost of misrecognizing people who do not cause recidivism to cause recidivism is lower than the cost of incorrectly classifying people who would cause recidivism. Because the former increases only the additional monitoring costs, while the latter increases the amount of social, and economic costs. Therefore, in this paper, we propose an XGBoost(eXtream Gradient Boosting; XGB) based recidivism prediction model considering asymmetric error cost. In the first step of the model, XGB, being recognized as high performance ensemble method in the field of data mining, was applied. And the results of XGB were compared with various prediction models such as LOGIT(logistic regression analysis), DT(decision trees), ANN(artificial neural networks), and SVM(support vector machines). In the next step, the threshold is optimized to minimize the total misclassification cost, which is the weighted average of FNE(False Negative Error) and FPE(False Positive Error). To verify the usefulness of the model, the model was applied to a real recidivism prediction dataset. As a result, it was confirmed that the XGB model not only showed better prediction accuracy than other prediction models but also reduced the cost of misclassification most effectively.