Design of Support Vector Classifier for identifying the ignition phases of an Electronic Ballast HID-MH Lamp

This paper presents the design and implementation of a multivariable support vector classifier with a Radial Basis Function kernel, which is responsible for identifying the different ignition stages of a 250 watts HID lamp. The classifier is implemented according to the four high-intensity discharge lamps current and voltage data. Support vector regression is used in the data improvement stage (training and testing data) as the classifier model.