The Community for Technology Leaders
Pacific-Asia Workshop on Computational Intelligence and Industrial Application, IEEE (2008)
Dec. 19, 2008 to Dec. 20, 2008
ISBN: 978-0-7695-3490-9
pp: 320-325
SVM which is based on statistical theory has the advantage of no relying on designer's experience of learning and the prior knowledge. So it is widely used in optimization, decision-making, regression estimates, speech recognition, facial image recognition, and so on. Because there are some kinds of wrong and isolated samples in the training samples in the forecasting model, and the learning process of samples always presents three major characteristics: batch, increment and online, we propose a learning algorithm of batch, increment and online which base on Support Vector Regression (BIO-SVR) which can ensure the accuracy of the predicting model and update dynamically when the samples increase. When being used in industry, our algorithm can analyze and predict the flatness of plate and the result shows us that comparing to the traditional incremental SVM our algorithm model not only improves the accuracy but also has the ability of real-time and online.

H. Xu, X. Peng, L. Yue, L. Kai and C. Ming, "The Research and Application of a Learning Algorithm of Batch Increment and Online Which Bases on Support Vector Regression," 2008 Pacific-Asia Workshop on Computational Intelligence and Industrial Application. PACIIA 2008(PACIIA), Wuhan, 2008, pp. 320-325.
93 ms
(Ver 3.3 (11022016))