2011 | OriginalPaper | Buchkapitel
Function Approximation Using SVM with FCM and Slope Based Partition
verfasst von : Amera Almas, Nisar Hundewale
Erschienen in: Trends in Computer Science, Engineering and Information Technology
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
For a large training data set, the memory space required to store the kernel matrix is a difficult task for the solution of QP problems for SVR. Support Vector Regression (SVR) is used to approximate the function. So we are proposing the slope based partition algorithm, which automatically evolves the partitions based on change in slope. In this paper we are improving the performance of function approximation with SVM by preprocessing the dataset with Fuzzy c-Mean clustering (FCM) and slope based partition methods. Using FCM and slope, we are portioning the data, and for every partitioned dataset we are finding the function approximation, and aggregating the result. The results indicate that Root Mean Square Error (RMSE) has been reduced with the partitioned data, compare to the processing entire dataset, with the increase in performance approximately 40%