FPGA implementation of a neural network classifier for gas sensor array applications

Faycal Benrekia*, Mokhtar Attari, Amine Bermak, Khaled Belhout

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

11 Citations (Scopus)

Abstract

A primitive gas recognition system which can discriminate limited species of industrial gas was designed and simulated. The 'electronic nose' consists of an array of 8 microhotplate based SnO2thin film gas sensors with different selectivity patterns, signal collecting unit and a signal pattern recognition and decision part in programmable logic device chip. BP (Back Propagation) neural networks with Multilayer Perceptron structure was designed and implemented on FPGA (Field Programmable Gate Array), of twenty thousand gate level chip by VHDL language for processing the input signals from 8 kinds of gas sensors. The network contained eight input units, one hidden layer with 4 neurons and output with 5 regular neurons. The 'electronic nose' system successfully discriminated 5 kinds of industrial gases in computer simulation. A small application has been tested on the APS X208 FPGA test board.

Original languageEnglish
Title of host publication2009 6th International Multi-Conference on Systems, Signals and Devices, SSD 2009
PublisherIEEE Computer Society
ISBN (Print)9781424443468
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event2009 6th International Multi-Conference on Systems, Signals and Devices, SSD 2009 - Djerba, Taiwan, Province of China
Duration: 23 Mar 200926 Mar 2009

Publication series

Name2009 6th International Multi-Conference on Systems, Signals and Devices, SSD 2009

Conference

Conference2009 6th International Multi-Conference on Systems, Signals and Devices, SSD 2009
Country/TerritoryTaiwan, Province of China
CityDjerba
Period23/03/0926/03/09

Keywords

  • E-nose
  • FPGA-implementation
  • Gas sensor
  • Neural network classifier
  • VHDL

Fingerprint

Dive into the research topics of 'FPGA implementation of a neural network classifier for gas sensor array applications'. Together they form a unique fingerprint.

Cite this