Low-Power and Low-Cost Implementation of SVMs for Smart Sensors

Author

Boni, Andrea ; Pianegiani, Fernando ; Petri, Dario

Author_Institution

Dept. of Inf. & Commun. Technol., Trento Univ.

Volume

56

Issue

1

fYear

2007

Firstpage

39

Lastpage

44

Abstract

In this paper, we propose an efficient implementation of support vector machines (SVMs) on a low-power and low-cost 8-bit microcontroller. The proposed solution can be advantageously used to implement smart sensors and sensor networks for intelligent data analysis and pervasive computing. A new model selection algorithm that allows fitting the resource constraints imposed by the hardware architecture is proposed. Moreover, the performance of an optimized implementation which exploits the CORDIC algorithm is detailed and discussed

Keywords

intelligent sensors; microcontrollers; support vector machines; SVM; low cost implementation; low power implementation; microcontroller; smart sensors; support vector machines; Communications technology; Constraint optimization; Data analysis; Hardware; High energy physics instrumentation computing; Intelligent networks; Intelligent sensors; Microcontrollers; Signal processing algorithms; Support vector machines; Microcontrollers; model selection; signal processing; smart sensors; support vector machines (SVMs);

fLanguage

English

Journal_Title

Instrumentation and Measurement, IEEE Transactions on

Publisher

ieee

ISSN

0018-9456

Type

jour

DOI

10.1109/TIM.2006.887319

Filename

4061072