Intelligent Engineering Systems through Artificial Neural Networks, Volume 20
11 Support Vector Machines Applied to Multivariate Processes
Download citation file:
- Ris (Zotero)
- Reference Manager
Support Vector Machines (SVMs) and other kernel methods can be applied to the monitoring of multivariate processes. Notably, kernel methods are designed to be robust to common probabilistic assumptions which is a lacking characteristic of conventional control charts. The aim of this work is to show the applications of SVMs to multivariate processes with unknown distribution and correlated characteristics. Experimental results with data sets from the UCI repository of machine learning databases showed remarkable potential.