A Committee Machine Gas Identification System Based on Dynamically Reconfigurable FPGA

Minghua Shi, Amine Bermak, Sofiane Brahim-Belhouari, Shrutisagar Chandrasekaran, Abbes Amira

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

This paper proposes a gas identification system based on the committee machine (CM) classifier, which combines various gas identification algorithms, to obtain a unified decision with improved accuracy. The CM combines five different classifiers: K nearest neighbors (KNNs), multilayer perceptron (MLP), radial basis function (RBF), Gaussian mixture model (GMM), and probabilistic principal component analysis (PPCA). Experiments on real sensors’ data proved the effectiveness of our system with an improved accuracy over individual classifiers. Due to the computationally intensive nature of CM, its implementation requires significant hardware resources. In order to overcome this problem, we propose a novel time multiplexing hardware implementation using a dynamically reconfigurable field programmable gate array (FPGA) platform. The processing is divided into three stages: sampling and preprocessing, pattern recognition, and decision stage. Dynamically reconfigurable FPGA technique is used to implement the system in a sequential manner, thus using limited hardware resources of the FPGA chip. The system is successfully tested for combustible gas identification application using our in-house tin-oxide gas sensors.

Original languageEnglish
Pages (from-to)403-414
Number of pages12
JournalIEEE Sensors Journal
Volume8
Issue number4
DOIs
Publication statusPublished - 2008
Externally publishedYes

Fingerprint

field-programmable gate arrays
system identification
Field programmable gate arrays (FPGA)
Identification (control systems)
Classifiers
classifiers
Hardware
hardware
Gases
gases
resources
Multilayer neural networks
Tin oxides
Chemical sensors
Multiplexing
Principal component analysis
self organizing systems
Pattern recognition
sensors
preprocessing

Keywords

  • Committee machine (CM)
  • dynamically reconfigurable field programmable gate array (FPGA)
  • gas identification
  • pattern recognition

ASJC Scopus subject areas

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

A Committee Machine Gas Identification System Based on Dynamically Reconfigurable FPGA. / Shi, Minghua; Bermak, Amine; Brahim-Belhouari, Sofiane; Chandrasekaran, Shrutisagar; Amira, Abbes.

In: IEEE Sensors Journal, Vol. 8, No. 4, 2008, p. 403-414.

Research output: Contribution to journalArticle

Shi, Minghua ; Bermak, Amine ; Brahim-Belhouari, Sofiane ; Chandrasekaran, Shrutisagar ; Amira, Abbes. / A Committee Machine Gas Identification System Based on Dynamically Reconfigurable FPGA. In: IEEE Sensors Journal. 2008 ; Vol. 8, No. 4. pp. 403-414.
@article{97d2bfb6668146fbaee33e84f9d5fffc,
title = "A Committee Machine Gas Identification System Based on Dynamically Reconfigurable FPGA",
abstract = "This paper proposes a gas identification system based on the committee machine (CM) classifier, which combines various gas identification algorithms, to obtain a unified decision with improved accuracy. The CM combines five different classifiers: K nearest neighbors (KNNs), multilayer perceptron (MLP), radial basis function (RBF), Gaussian mixture model (GMM), and probabilistic principal component analysis (PPCA). Experiments on real sensors’ data proved the effectiveness of our system with an improved accuracy over individual classifiers. Due to the computationally intensive nature of CM, its implementation requires significant hardware resources. In order to overcome this problem, we propose a novel time multiplexing hardware implementation using a dynamically reconfigurable field programmable gate array (FPGA) platform. The processing is divided into three stages: sampling and preprocessing, pattern recognition, and decision stage. Dynamically reconfigurable FPGA technique is used to implement the system in a sequential manner, thus using limited hardware resources of the FPGA chip. The system is successfully tested for combustible gas identification application using our in-house tin-oxide gas sensors.",
keywords = "Committee machine (CM), dynamically reconfigurable field programmable gate array (FPGA), gas identification, pattern recognition",
author = "Minghua Shi and Amine Bermak and Sofiane Brahim-Belhouari and Shrutisagar Chandrasekaran and Abbes Amira",
year = "2008",
doi = "10.1109/JSEN.2008.917124",
language = "English",
volume = "8",
pages = "403--414",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - A Committee Machine Gas Identification System Based on Dynamically Reconfigurable FPGA

AU - Shi, Minghua

AU - Bermak, Amine

AU - Brahim-Belhouari, Sofiane

AU - Chandrasekaran, Shrutisagar

AU - Amira, Abbes

PY - 2008

Y1 - 2008

N2 - This paper proposes a gas identification system based on the committee machine (CM) classifier, which combines various gas identification algorithms, to obtain a unified decision with improved accuracy. The CM combines five different classifiers: K nearest neighbors (KNNs), multilayer perceptron (MLP), radial basis function (RBF), Gaussian mixture model (GMM), and probabilistic principal component analysis (PPCA). Experiments on real sensors’ data proved the effectiveness of our system with an improved accuracy over individual classifiers. Due to the computationally intensive nature of CM, its implementation requires significant hardware resources. In order to overcome this problem, we propose a novel time multiplexing hardware implementation using a dynamically reconfigurable field programmable gate array (FPGA) platform. The processing is divided into three stages: sampling and preprocessing, pattern recognition, and decision stage. Dynamically reconfigurable FPGA technique is used to implement the system in a sequential manner, thus using limited hardware resources of the FPGA chip. The system is successfully tested for combustible gas identification application using our in-house tin-oxide gas sensors.

AB - This paper proposes a gas identification system based on the committee machine (CM) classifier, which combines various gas identification algorithms, to obtain a unified decision with improved accuracy. The CM combines five different classifiers: K nearest neighbors (KNNs), multilayer perceptron (MLP), radial basis function (RBF), Gaussian mixture model (GMM), and probabilistic principal component analysis (PPCA). Experiments on real sensors’ data proved the effectiveness of our system with an improved accuracy over individual classifiers. Due to the computationally intensive nature of CM, its implementation requires significant hardware resources. In order to overcome this problem, we propose a novel time multiplexing hardware implementation using a dynamically reconfigurable field programmable gate array (FPGA) platform. The processing is divided into three stages: sampling and preprocessing, pattern recognition, and decision stage. Dynamically reconfigurable FPGA technique is used to implement the system in a sequential manner, thus using limited hardware resources of the FPGA chip. The system is successfully tested for combustible gas identification application using our in-house tin-oxide gas sensors.

KW - Committee machine (CM)

KW - dynamically reconfigurable field programmable gate array (FPGA)

KW - gas identification

KW - pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=85008008244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85008008244&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2008.917124

DO - 10.1109/JSEN.2008.917124

M3 - Article

VL - 8

SP - 403

EP - 414

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 4

ER -