New methods for SVM feature selection

Support Vector Machines have been a popular topic for quite some time now, and as they develop, a need for new methods of feature selection arises. This work presents various approaches SVM feature selection developped during the author's summer internship at STMicroelectronics. The work focuses on the use of one-class SVM's for wafer testing. A key problem in OC-SVM algorithms is dimensionality reduction, otherwise known as feature selection. Prior to the execution of the proper SVM part of the algorithm, the program first needs to asses what will be the most significant data to take into account.