Inverse modeling with SVMs-based dynamically reconfigurable systems

Author

Boni, A. ; Pianegiani, E. ; Petri, D.

Author_Institution

Dipt. di Informatica e Telecomunicazioni, Universita degli Studi di Trento, Italy

Volume

3

fYear

2004

fDate

18-20 May 2004

Firstpage

2036

Abstract

In this paper we discuss the performances of an FPGA-based architecture which solves an inverse modeling problem. The case study is a typical telecommunication task where the hardware implementation, on the receiver side, is of paramount importance. A reconfigurable device is used in order to build a complete system on chip implementing an efficient learning by examples technique.

Keywords

adaptive equalisers; field programmable gate arrays; inverse problems; learning by example; reconfigurable architectures; support vector machines; system-on-chip; FPGA-based architecture; SVM-based system; dynamically reconfigurable systems; efficient learning by example; equalization problem; hardware implementation; hardware-platform design; inverse modeling; nonlinear channel; support vector machines; system on chip; Adaptive arrays; Adaptive systems; Art; Delay estimation; Field programmable gate arrays; Hardware; Inverse problems; Semiconductor device measurement; Signal processing algorithms; Telecommunications;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference, 2004. IMTC 04. Proceedings of the 21st IEEE

ISSN

1091-5281

Print_ISBN

0-7803-8248-X

Type

conf

DOI

10.1109/IMTC.2004.1351489

Filename

1351489