• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.93-96
• /
• 2000

본 논문에서는 SVM의 학습성 개선을 위해 모멘트와 kernel-adatron 기법이 조합된 하이브리드 학습알고리즘을 제안하였다. 제안된 학습알고리즘은 SVM의 학습기법인 기울기상승법에서 발생하는 최적해로의 수렴에 따른 발진을 억제하여 그 수렴속도를 좀 더 개선시키는 모멘트의 장점과 비선형 특징공간에서의 동작과 구현의 용이성을 가진 kernel-adatron 알고리즘의 장점을 그대로 살리는 것이다. 제안된 알고리즘을 비선형 함수 회귀에 적용해 본 결과 학습속도에 있어서 QP와 기존의 kernel-adatron 알고리즘보다 더 우수한 성능이 있음을 확인하였다

• Journal of the Korean Data and Information Science Society
• /
• v.13 no.2
• /
• pp.65-75
• /
• 2002

The support vector machine (SVM), first developed by Vapnik and his group at AT &T Bell Laboratories, is being used as a new technique for regression and classification problems. In this paper we present an approach to estimating approximate prediction intervals for SVM regression based on posterior predictive densities. Furthermore, the method is illustrated with a data example.

• 한국데이터정보과학회:학술대회논문집
• /
• 2005.10a
• /
• pp.161-169
• /
• 2005

In this paper we propose a fuzzy c-regression model based on weighted least squares support vector machine(LS-SVM), which can be used to detect outliers in the switching regression model while preserving simultaneous yielding the estimates of outputs together with a fuzzy c-partitions of data. It can be applied to the nonlinear regression which does not have an explicit form of the regression function. We illustrate the new algorithm with examples which indicate how it can be used to detect outliers and fit the mixed data to the nonlinear regression models.

• Structural Monitoring and Maintenance
• /
• v.5 no.2
• /
• pp.243-260
• /
• 2018

Detection of damages in fibre reinforced plastic (FRP) composite structures is important from the safety and serviceability point of view. Usually, damage is realized as a local reduction of stiffness and if dynamic responses of the structure are sensitive enough to such changes in stiffness, then a well posed inverse problem can provide an efficient solution to the damage detection problem. Usually, such inverse problems are solved within the framework of pattern recognition. Support Vector Machine (SVM) Algorithm is one such methodology, which minimizes the weighted differences between the experimentally observed dynamic responses and those computed using the finite element model- by optimizing appropriately chosen parameters, such as stiffness. A damage detection strategy is hereby proposed using SVM which perform stepwise by first locating and then determining the severity of the damage. The SVM algorithm uses simulations of only a limited number of damage scenarios and trains the algorithm in such a way so as to detect damages at unknown locations by recognizing the pattern of changes in dynamic responses. A rectangular fiber reinforced plastic composite plate has been investigated both numerically and experimentally to observe the efficiency of the SVM algorithm for damage detection. Experimentally determined modal responses, such as natural frequencies and mode shapes are used as observable parameters. The results are encouraging since a high percentage of damage cases have been successfully determined using the proposed algorithm.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.5
• /
• pp.831-839
• /
• 2010

Least squares support vector machine (LS-SVM) is a kernel trick gaining a lot of popularities in the regression and classification problems. We use LS-SVM to propose a iterative algorithm for a nonlinear generalized autoregressive conditional heteroscedasticity model in the mean (GARCH-M) model to estimate the mean and the conditional volatility of stock market returns. The proposed method combines a weighted LS-SVM for the mean and unweighted LS-SVM for the conditional volatility. In this paper, we show that nonlinear GARCH-M models have a higher performance than the linear GARCH model and the linear GARCH-M model via real data estimations.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.15 no.5
• /
• pp.437-444
• /
• 2015

In simulation-based circuit optimization, many simulation runs may be wasted while evaluating infeasible designs, i.e. the designs that do not meet the constraints. To avoid such a waste, this paper investigates the use of support vector machine (SVM) classifiers in predicting the design's feasibility prior to simulation and the optimal selection of the SVM parameters, namely, the Gaussian kernel shape parameter ${\gamma}$ and the misclassification penalty parameter C. These parameters affect the complexity as well as the accuracy of the model that SVM represents. For instance, the higher ${\gamma}$ is good for detailed modeling and the higher C is good for rejecting noise in the training set. However, our empirical study shows that a low ${\gamma}$ value is preferable due to the high spatial correlation among the circuit design candidates while C has negligible impacts due to the smooth and clean constraint boundaries of most circuit designs. The experimental results with an LC-tank oscillator example show that an optimal selection of these parameters can improve the prediction accuracy from 80 to 98% and model complexity by $10{\times}$.

• Computers and Concrete
• /
• v.20 no.5
• /
• pp.555-562
• /
• 2017

The accuracy and integrity of stress data acquired by bridge heath monitoring system is of significant importance for bridge safety assessment. However, the missing and abnormal data are inevitably existed in a realistic monitoring system. This paper presents a data reconstruction approach for bridge heath monitoring based on the wavelet multi-resolution analysis and support vector machine (SVM). The proposed method has been applied for data imputation based on the recorded data by the structural health monitoring (SHM) system instrumented on a prestressed concrete cable-stayed bridge. The effectiveness and accuracy of the proposed wavelet-based SVM prediction method is examined by comparing with the traditional autoregression moving average (ARMA) method and SVM prediction method without wavelet multi-resolution analysis in accordance with the prediction errors. The data reconstruction analysis based on 5-day and 1-day continuous stress history data with obvious preternatural signals is performed to examine the effect of sample size on the accuracy of data reconstruction. The results indicate that the proposed data reconstruction approach based on wavelet multi-resolution analysis and SVM is an effective tool for missing data imputation or preternatural signal replacement, which can serve as a solid foundation for the purpose of accurately evaluating the safety of bridge structures.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.3
• /
• pp.209-216
• /
• 2009

The accurate estimation of software development cost is important to a successful development in software engineering. This paper presents a software cost estimation method using a support vector machine. Support vector machine is one of the efficient techniques for classification, and it is the classification method of input data based on Maximum-Margin Hyperplane. But SVM has the problem of the selection of optimal parameters, because it is dependent on user's parameters. This paper selects optimized SVM parameters using advanced method, and estimates software development cost. The proposed approach outperform some recent results reported in the literature.

• The Korean Journal of Applied Statistics
• /
• v.29 no.5
• /
• pp.961-975
• /
• 2016

The hierarchically penalized support vector machine (H-SVM) has been developed to perform simultaneous classification and input variable selection when input variables are naturally grouped or generated by factors. However, the H-SVM may suffer from estimation inefficiency because it applies the same amount of shrinkage to each variable without assessing its relative importance. In addition, when analyzing imbalanced data with uneven class sizes, the classification accuracy of the H-SVM may drop significantly in predicting minority class because its classifiers are undesirably biased toward the majority class. To remedy such problems, we propose the weighted adaptive H-SVM (WAH-SVM) method, which uses a adaptive tuning parameters to improve the performance of variable selection and the weights to differentiate the misclassification of data points between classes. Numerical results are presented to demonstrate the competitive performance of the proposed WAH-SVM over existing SVM methods.

• Journal of Information Technology Services
• /
• v.11 no.4
• /
• pp.233-250
• /
• 2012

In this paper, credit card delinquency means the possibility of occurring bad debt within the certain near future from the normal accounts that have no debt and the problem is to predict, on the monthly basis, the occurrence of delinquency 3 months in advance. This prediction is typical binary classification problem but suffers from the issue of data imbalance that means the instances of target class is very few. For the effective prediction of bad debt occurrence, Support Vector Machine (SVM) with kernel trick is adopted using credit card usage and payment patterns as its inputs. SVM is widely accepted in the data mining society because of its prediction accuracy and no fear of overfitting. However, it is known that SVM has the limitation in its ability to processing the large-scale data. To resolve the difficulties in applying SVM to bad debt occurrence prediction, two stage clustering is suggested as an effective data reduction method and ensembles of SVM models are also adopted to mitigate the difficulty due to data imbalance intrinsic to the target problem of this paper. In the experiments with the real world data from one of the major domestic credit card companies, the suggested approach reveals the superior prediction accuracy to the traditional data mining approaches that use neural networks, decision trees or logistics regressions. SVM ensemble model learned from T2 training set shows the best prediction results among the alternatives considered and it is noteworthy that the performance of neural networks with T2 is better than that of SVM with T1. These results prove that the suggested approach is very effective for both SVM training and the classification problem of data imbalance.