Implementation of a SigmaBoost-based ensemble of SVM in a multiple processor system on chip

Author

Lopes, Danniel C. ; Lima, Naiyan H C ; De Melo, Jorge D. ; Neto, Adrião D D

Author_Institution

Departmento de Cienc. Exatas e Naturais, UFERSA Mossoro, Mossoro, Brazil

fYear

2010

fDate

24-26 March 2010

Firstpage

179

Lastpage

182

Abstract

This paper shows the effectiveness of a classifier ensemble composed of weak classifiers trained with a boosting algorithm implemented in a multiprocessor system on chip. The network is applied on the classification on thyroid disease diagnosis. The objective is to show that, even an FPGA with hardware restrictions, can be used to implement a complex problem, when parallel processing is used. To improve the system performance four soft processors were used with a shared memory.

Keywords

learning (artificial intelligence); medical computing; parallel processing; patient diagnosis; pattern classification; shared memory systems; support vector machines; system-on-chip; FPGA; MPSoC; SigmaBoost-based ensemble; boosting algorithm; classifier ensemble; multiple processor system on chip; parallel processing; shared memory; support vector machines; thyroid disease diagnosis; Boosting; Diseases; Field programmable gate arrays; Hardware; Multiprocessing systems; Parallel processing; Support vector machine classification; Support vector machines; System performance; System-on-a-chip;

fLanguage

English

Publisher

ieee

Conference_Titel

Programmable Logic Conference (SPL), 2010 VI Southern

Conference_Location

Ipojuca

Print_ISBN

978-1-4244-6309-1

Type

conf

DOI

10.1109/SPL.2010.5483014

Filename

5483014