FPGA Implementation of a Support Vector Machine Based Classification System and Its Potential Application in Smart Grid

Xiaohui Song, Hong Wang, Lingfeng Wang
2014 2014 11th International Conference on Information Technology: New Generations  
Support Vector Machines (SVMs) is a popular classification and regression prediction tool that uses supervised machine learning theory to maximize the predictive accuracy. This paper focuses on the field programmable gate array ( FPGA) implementation of a Support Vector Machine classification system. Owing to the advanced parallel calculation feature provided by FPGA, a fast data classification can be achieved by the FPGA-based two-class SVM classifier. The classification system works both in
more » ... tem works both in linear mode or non-linear mode, depending on the dimensions of the classification. Simulated results demonstrate that the classification system is effective in fast data classification, as well as a promising technique used in Smart Grid to strengthen the communication security. iv For my lovely, brilliant wife, Lu Wang. Your love, patience, support and understanding have encouraged me to finish this study and thesis v Acknowledgements First, I would like to express the deepest appreciation to my advisors Dr. Hong Wang and Dr. Lingfeng Wang, who have the attitude and the substance of a genius: they continually and convincingly conveyed a spirit of adventure in regard to research and scholarship, and an excitement in regard to teaching. Without their guidance and persistent help this thesis would not have been possible.
doi:10.1109/itng.2014.45 dblp:conf/itng/SongWW14 fatcat:eez5pox3nnfrvjxovcfjldh3lu