• 한국지능시스템학회논문지
• /
• 제17권5호
• /
• pp.679-683
• /
• 2007

Vapnik의 통계적 학습이론은 분류, 회귀, 그리고 군집화를 위하여 SVM(support vector machine), SVR(support vector regression), 그리고 SVC(support vector clustering)의 3가지 학습 알고리즘을 포함한다. 이들 중에서 SVC는 가우시안 커널함수에 기반한 지지벡터를 이용하여 비교적 우수한 군집화 결과를 제공하고 있다. 하지만 SVM, SVR과 마찬가지로 SVC도 커널모수와 정규화상수에 대한 최적결정이 요구된다 하지만 대부분의 분석작업에서 사용자의 주관적 경험에 의존하거나 격자탐색과 같이 많은 컴퓨팅 시간을 요구하는 전략에 의존하고 있다. 본 논문에서는 SVC에서 사용되는 커널모수와 정규화상수의 효율적인 결정을 위하여 차분진화를 이용한 DESVC(differential evolution based SVC)를 제안한다 UCI Machine Learning repository의 학습데이터와 시뮬레이션 데이터 집합들을 이용한 실험을 통하여 기존의 기계학습 알고리즘과의 성능평가를 수행한다.

• 경영과학
• /
• 제23권2호
• /
• pp.75-91
• /
• 2006

The purpose of this paper is to propose a new software development cost estimation method using SVR(Support Vector Regression) SVR, one of machine learning techniques, has been attracting much attention for its theoretic clearness and food performance over other machine learning techniques. This paper may be the first study in which SVR is applied to the field of software cost estimation. To derive the new method, we analyze historical cost data including both well-known overseas and domestic software projects, and define cost drivers affecting software cost. Then, the SVR model is trained using the historical data and its estimation accuracy is compared with that of the linear regression model. Experimental results show that the SVR model produces more accurate prediction than the linear regression model.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 춘계 학술대회 학술발표 논문집
• /
• pp.81-84
• /
• 2003

$\varepsilon$-SVR(e-Support Vector Regression)학습방법은 SV(Support Vector)들을 이용하여 함수 근사(Regression)하는 방법으로 최근 주목받고 있는 기법이다. SVM(SV machine)의 한 가지 방법으로, 신경망을 기반으로 한 다른 알고리즘들이 학습과정에서 지역적 최적해로 수렴하는 등의 문제를 한계로 갖는데 반해, 이러한 구조들을 대체할 수 있는 학습방법으로 사용될 수 있다. 일반적인 $\varepsilon$-SVR에서는 학습 데이터와 관사 함수 f사이에 허용 가능한 에러범위 $\varepsilon$값이 학습하기 전에 정해진다. 그러나 Nu-SVR(ν-version SVR)학습방법은 학습의 결과로 최적화 된 $\varepsilon$값을 얻을 수 있다. 정해진 기저함수가 포함되는 $\varepsilon$-SVR 학습방법(Sermparametric SVR)은 정해진 독립 기저함수를 사용하여 함수를 근사하는 방법으로, 일반적인 $\varepsilon$-SVR 학습방범에 비해 우수한 결과를 나타내는 것이 성공적으로 입증된 바 있다. 이에 따라, 본 논문에서는 정해진 기저함수가 포함된 ν-SVR 학습 방법을 제안하고, 이에 대한 수식을 유도하였다. 그리고, 모의 실험을 통하여 제안된 Sermparametric ν-SVR 학습 방법의 적용 가능성을 알아보았다.

• Journal of the Korean Data and Information Science Society
• /
• 제25권2호
• /
• pp.447-454
• /
• 2014

In many practical machine learning and data mining applications, unlabeled training examples are readily available but labeled ones are fairly expensive to obtain. Therefore semi-supervised learning algorithms have attracted much attentions. However, previous research mainly focuses on classication problems. In this paper, a semi-supervised regression method based on support vector regression (SVR) formulation that is proposed. The estimator is easily obtained via the dual formulation of the optimization problem. The experimental results with simulated and real data suggest superior performance of the our proposed method compared with standard SVR.

• 한국군사과학기술학회지
• /
• 제16권5호
• /
• pp.675-682
• /
• 2013

Reliability analysis and prediction of next failure time is critical to sustain weapon systems, concerning scheduled maintenance, spare parts replacement and maintenance interventions, etc. Since 1981, many methodology derived from various probabilistic and statistical theories has been suggested to do that activity. Nowadays, many A.I. tools have been used to support these predictions. Support Vector Regression(SVR) is a nonlinear regression technique extended from support vector machine. SVR can fit data flexibly and it has a wide variety of applications. This paper utilizes SVM and SVR with combining time series to predict the next failure time based on historical failure data. A numerical case using failure data from the military equipment is presented to demonstrate the performance of the proposed approach. Finally, the proposed approach is proved meaningful to predict next failure point and to estimate instantaneous failure rate and MTBF.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2005년도 춘계학술대회
• /
• pp.155-163
• /
• 2005

This paper applies Support Vector Regression (SVR) to estimate and forecast nonlinear autoregressive integrated (ARI) model of the daily exchange rates of four currencies (Swiss Francs, Indian Rupees, South Korean Won and Philippines Pesos) against U.S. dollar. The forecasting abilities of SVR are compared with linear ARI model which is estimated by OLS. Sensitivity of SVR results are also examined to kernel type and other free parameters. Empirical findings are in favor of SVR. SVR method forecasts exchange rate level better than linear ARI model and also has superior ability in forecasting the exchange rates direction in short test phase but has similar performance with OLS when forecasting the turning points in long test phase.

• 한국컴퓨터정보학회논문지
• /
• 제14권7호
• /
• pp.17-24
• /
• 2009

정보시스템에 대한 이용이 늘어남에 따라 소프트웨어 개발 요구와 개발 비용이 증가하게 되었다. 기존에는 통계적 알고리즘 기반의 회귀분석을 이용하여 소프트웨어 개발비용을 산정하였으나 오늘날은 기계학습 방법들이 많이 연구되고 있다. 본 논문에서는 기계학습 기술의 하나인 SVR를 사용하여 소프트웨어 비용을 산정하였고, 이 때 SVR에서 사용하는 파라미터들의 최적 조합을 면역계의 동작원리를 적용한 면역 알고리즘을 적용하여 최적 조합을 찾았다. 소프트웨어 비용산정을 위해 세대수, 기억세포수, 대립유전자수를 변경해 가면서 면역 알고리즘 기반의 SVR을 적용하였고, 그 실험 결과를 기존 연구된 다른 기계학습 방법과 비교 분석하였다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.136-136
• /
• 2022

This study investigates the possibility of coupling empirical mode decomposition (EMD) for runoff prediction from machine learning (ML) models. Here, support vector regression (SVR) and convolutional neural network (CNN) were considered for ML algorithms. Precipitation (P), minimum temperature (Tmin), maximum temperature (Tmax) and their intrinsic mode functions (IMF) values were used for input variables at a monthly scale from Jan. 1973 to Dec. 2020 in the Grand river basin, Canada. The support vector machine-recursive feature elimination (SVM-RFE) technique was applied for finding the best combination of predictors among input variables. The results show that the proposed method outperformed the individual performance of SVR and CNN during the training and testing periods in the study area. According to the correlation coefficient (R), the EMD-SVR model outperformed the EMD-CNN model in both training and testing even though the CNN indicated a better performance than the SVR before using IMF values. The EMD-SVR model showed higher improvement in R value (38.7%) than that from the EMD-CNN model (7.1%). It should be noted that the coupled models of EMD-SVR and EMD-CNN represented much higher accuracy in runoff prediction with respect to the considered evaluation indicators, including root mean square error (RMSE) and R values.

• 산업경영시스템학회지
• /
• 제43권4호
• /
• 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.

• Structural Engineering and Mechanics
• /
• 제63권1호
• /
• pp.115-124
• /
• 2017

In this paper, a different technique to predict the effects of soil-structure interaction (SSI) on seismic response of building systems is investigated. The technique use a machine learning algorithm called Support Vector Regression (SVR) with technical and analytical results as input features. Normally, the effects of SSI on seismic response of existing building systems can be identified by different types of large data sets. Therefore, predicting and estimating the seismic response of building is a difficult task. It is possible to approximate a real valued function of the seismic response and make accurate investing choices regarding the design of building system and reduce the risk involved, by giving the right experimental and/or numerical data to a machine learning regression, such as SVR. The seismic response of both single-degree-of-freedom system and six-storey RC frame which can be represent of a broad range of existing structures, is estimated using proposed SVR model, while allowing flexibility of the soil-foundation system and SSI effects. The seismic response of both single-degree-of-freedom system and six-storey RC frame which can be represent of a broad range of existing structures, is estimated using proposed SVR model, while allowing flexibility of the soil-foundation system and SSI effects. The results show that the performance of the technique can be predicted by reducing the number of real data input features. Further, performance enhancement was achieved by optimizing the RBF kernel and SVR parameters through grid search.