Methods of Decreasing the Number of Support Vectors via k-Mean Clustering

Xia, Xiao-Lei; Lyu, Michael R.; Lok, Tat-Ming; Huang, Guang-Bin

doi:10.1007/11538059_75

Cited by 17 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also interesting to compare these results to those of Chen et al (2010), in which they compared the linear kernel, the polynomial kernel and the Gaussian kernel and concluded that no single kernel dominated the volatility predictions. The number of support vectors is important in SVM application, as a well-performed SVM is expected approximately to outline an entire dataset from a small fraction of input data (Xia et al, 2005). In general, for both in-sample and out-of-sample data, most NMSE and NMAE values present a decreasing trend, whereas DA increases from Table 1 to Table 3.…”

Section: Monte Carlo Experiments and Results Comparisonmentioning

confidence: 99%

“…Table 4 shows that the number of support vectors in the wavelet kernel-based SVM is lower than that in the Gaussian kernel-based SVM. The number of support vectors is important in SVM application, as a well-performed SVM is expected approximately to outline an entire dataset from a small fraction of input data (Xia et al, 2005). For the training data, fewer support vectors will lead to sparse datasets when solving the quadratic programming GARCH 271 267 231 201 GJR-GARCH 198 181 141 139 TS-GARCH 468 300 468 205 T-GARCH 174 346 146 305 optimization problem.…”

Section: Monte Carlo Experiments and Results Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

Estimating and Forecasting APARCH‐Skew‐t Model by Wavelet Support Vector Machines

2014

Journal of Forecasting

View full text Add to dashboard Cite

This paper concentrates on comparing estimation and forecasting ability of quasi‐maximum likelihood (QML) and support vector machines (SVM) for financial data. The financial series are fitted into a family of asymmetric power ARCH (APARCH) models. As the skewness and kurtosis are common characteristics of the financial series, a skew‐t distributed innovation is assumed to model the fat tail and asymmetry. Prior research indicates that the QML estimator for the APARCH model is inefficient when the data distribution shows departure from normality, so the current paper utilizes the semi‐parametric‐based SVM method and shows that it is more efficient than the QML under the skewed Student's‐t distributed error. As the SVM is a kernel‐based technique, we further investigate its performance by applying separately a Gaussian kernel and a wavelet kernel. The results suggest that the SVM‐based method generally performs better than QML for both in‐sample and out‐of‐sample data. The outcomes also highlight the fact that the wavelet kernel outperforms the Gaussian kernel with lower forecasting error, better generation capability and more computation efficiency. Copyright © 2014 John Wiley & Sons, Ltd.

show abstract

Section: Monte Carlo Experiments and Results Comparisonmentioning

confidence: 99%

Section: Monte Carlo Experiments and Results Comparisonmentioning

confidence: 99%

Estimating and Forecasting APARCH‐Skew‐t Model by Wavelet Support Vector Machines

2014

Journal of Forecasting

View full text Add to dashboard Cite

show abstract

“…Combining kmeans and SVM has been studied before, but not in the context of NALM. Recognizing that in a majority of cases a large portion of the input data is redundant for training, in [28], k-means is used to decrease the number of support vectors and the training set size. Similarly, in [12], [13], k-means is employed to select a subset of original data for the SVM training.…”

Section: B Classificationmentioning

confidence: 99%

A low-complexity energy disaggregation method: Performance and robustness

Altrabalsi

Liao

Stanković

2014

2014 IEEE Symposium on Computational Intelligence Applications in Smart Grid (CIASG)

View full text Add to dashboard Cite

This version is available at https://strathprints.strath.ac.uk/51404/ Strathprints is designed to allow users to access the research output of the University of Strathclyde. Unless otherwise explicitly stated on the manuscript, Copyright © and Moral Rights for the papers on this site are retained by the individual authors and/or other copyright owners. Please check the manuscript for details of any other licences that may have been applied. You may not engage in further distribution of the material for any profitmaking activities or any commercial gain. You may freely distribute both the url (https://strathprints.strath.ac.uk/) and the content of this paper for research or private study, educational, or not-for-profit purposes without prior permission or charge.Any correspondence concerning this service should be sent to the

show abstract

“…From inequality (1), it can be deduced that a small number of support vectors will generate a small testing error and also leads to better generalization capability in SVM [9].Successful use of k-means requires a cautiously selected distance measure that demonstrates the properties of the clustering task. Designing the distance measure by hand is a tough job.…”

Section: E[pr(error )]<= E[ Number Of Support Vectors]/number Of Traimentioning

confidence: 99%