Abstract
For continuous processes, the global LSSVM always gives good prediction for testing data located in the neighborhood of dense training data but incompetent for these in the sparse part. To solve the problem, the paper proposed a local weighted LSSVM method in the online modeling of continuous processes. At each period, only the samples similar to the current input are added into the training set and the obtained model is just for predicting the current output. To distinguish the importance of the training data, weight is defined to each data according to the Euclidean distances between the training data and testing data. The presented algorithm is applied in pH neutralization process and the result shows the excellent performance of the presented algorithm in precision and predicting time.
This work was supported by the Jiansu Province Natural Science Fund(BK2009356), Jiansu Provincial university Natural Science Fund(09KJB51000) and Youth Found of Nanjing University of Technology.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Vapnik, V.: The nature of statistical learning theory. Springer, Heidelberg (1995)
Vapnik, V.: Statistical learning theory. John Wiley, New York (1998)
Suykens, J.A.K., Vandewalle, J.: Least squares support vector machine classifiers. Neural Processing Letters 9, 293–300 (1999)
Suykens, J.A.K., Lukas, L., Vandewalle, J.: Sparse approximation using least squares support vector machines. In: Proceeding of IEEE International Symposium on Circuits and Systems, pp. 757–760. IEEE Press, Lausanne (2000)
de Kruif, B.J., de Vries, T.J.A.: Pruning error minimization in least squares support vector machines. IEEE Transaction on neural networks 14, 696–702 (2003)
Zeng, X., wenChen, X.: Smo-based pruning methods for sparse least squares support vector machines. IEEE Transaction on neural networks 16, 1541–1546 (2005)
Li, L., Su, H., Chu, J.: Sparse representation based on projection in least squares support vector machines. Control Theory and Application 7, 163–168 (2009)
Liu, Y., Wang, H., Li, P.: Local least squares support vector regression with application to online modeling for batch processes. Journal of Chemical Industry and Engineering (China) 58, 2846–2851 (2007)
Smola, A.J., Schökopf, B.: A tutorial on support vector regression, http://www.neurocolt.com/tech_reps/1998/98030.ps.gz
Nie, J.H., Loh, A.P., Hang, C.C.: Modeling ph neutralization process using fuzzy-neutral approaches. Fuzzy set and systems 78, 5–22 (1996)
Chen, M., Cheng, J., Liu, X.: Determination of Alkaloids of Coptis chinensis by Spectral Analysis Based on Local Fitting Principal Component Regression. Acta Chimica Sinica 61, 1623–1627 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, L., Yu, H., Liu, J., Zhang, S. (2010). Local Weighted LS-SVM Online Modeling and the Application in Continuous Processes. In: Wang, F.L., Deng, H., Gao, Y., Lei, J. (eds) Artificial Intelligence and Computational Intelligence. AICI 2010. Lecture Notes in Computer Science(), vol 6320. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16527-6_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-16527-6_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-16526-9
Online ISBN: 978-3-642-16527-6
eBook Packages: Computer ScienceComputer Science (R0)