Committee machine with over 95% classification accuracy for combustible gas identification

Shi Minghua, Amine Bermak

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Gas identification represents a big challenge for pattern recognition systems due to several particular problems such as non-selectivity and drift. This paper proposes a gas identification committee machine (CM), which combines various gas identification algorithms, to obtain a unified decision with improved accuracy. The CM combines 5 different classifiers: K Nearest Neighbors (KNN), Multi-layer Perceptron (MLP), Radial Basis Function (RFB), Gaussian Mixture Model (GMM) and Probabilistic PCA (PPCA). A data acquisition system using tin-oxide gas sensor array has been designed in order to create a real gas data set. The committee machine is implemented by assembling the outputs of these gas identification algorithms based on weighted combination rule. Experiments on real sensors' data proved the effectiveness of our system with an improved accuracy 95.9% over the individual classifiers.

Original languageEnglish
Title of host publicationICECS 2006 - 13th IEEE International Conference on Electronics, Circuits and Systems
Pages862-865
Number of pages4
DOIs
Publication statusPublished - 2006
Externally publishedYes
EventICECS 2006 - 13th IEEE International Conference on Electronics, Circuits and Systems - Nice, France
Duration: 10 Dec 200613 Dec 2006

Other

OtherICECS 2006 - 13th IEEE International Conference on Electronics, Circuits and Systems
CountryFrance
CityNice
Period10/12/0613/12/06

Fingerprint

Gases
Classifiers
Pattern recognition systems
Sensor arrays
Multilayer neural networks
Tin oxides
Chemical sensors
Data acquisition
Sensors
Experiments

Keywords

  • Committee machine
  • Gas identification
  • Pattern recognition
  • Tin oxide gas sensor

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Minghua, S., & Bermak, A. (2006). Committee machine with over 95% classification accuracy for combustible gas identification. In ICECS 2006 - 13th IEEE International Conference on Electronics, Circuits and Systems (pp. 862-865). [4263503] https://doi.org/10.1109/ICECS.2006.379925

Committee machine with over 95% classification accuracy for combustible gas identification. / Minghua, Shi; Bermak, Amine.

ICECS 2006 - 13th IEEE International Conference on Electronics, Circuits and Systems. 2006. p. 862-865 4263503.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Minghua, S & Bermak, A 2006, Committee machine with over 95% classification accuracy for combustible gas identification. in ICECS 2006 - 13th IEEE International Conference on Electronics, Circuits and Systems., 4263503, pp. 862-865, ICECS 2006 - 13th IEEE International Conference on Electronics, Circuits and Systems, Nice, France, 10/12/06. https://doi.org/10.1109/ICECS.2006.379925
Minghua S, Bermak A. Committee machine with over 95% classification accuracy for combustible gas identification. In ICECS 2006 - 13th IEEE International Conference on Electronics, Circuits and Systems. 2006. p. 862-865. 4263503 https://doi.org/10.1109/ICECS.2006.379925
Minghua, Shi ; Bermak, Amine. / Committee machine with over 95% classification accuracy for combustible gas identification. ICECS 2006 - 13th IEEE International Conference on Electronics, Circuits and Systems. 2006. pp. 862-865
@inproceedings{9088b7dc35e4499baea631090f1b1924,
title = "Committee machine with over 95{\%} classification accuracy for combustible gas identification",
abstract = "Gas identification represents a big challenge for pattern recognition systems due to several particular problems such as non-selectivity and drift. This paper proposes a gas identification committee machine (CM), which combines various gas identification algorithms, to obtain a unified decision with improved accuracy. The CM combines 5 different classifiers: K Nearest Neighbors (KNN), Multi-layer Perceptron (MLP), Radial Basis Function (RFB), Gaussian Mixture Model (GMM) and Probabilistic PCA (PPCA). A data acquisition system using tin-oxide gas sensor array has been designed in order to create a real gas data set. The committee machine is implemented by assembling the outputs of these gas identification algorithms based on weighted combination rule. Experiments on real sensors' data proved the effectiveness of our system with an improved accuracy 95.9{\%} over the individual classifiers.",
keywords = "Committee machine, Gas identification, Pattern recognition, Tin oxide gas sensor",
author = "Shi Minghua and Amine Bermak",
year = "2006",
doi = "10.1109/ICECS.2006.379925",
language = "English",
isbn = "1424403952",
pages = "862--865",
booktitle = "ICECS 2006 - 13th IEEE International Conference on Electronics, Circuits and Systems",

}

TY - GEN

T1 - Committee machine with over 95% classification accuracy for combustible gas identification

AU - Minghua, Shi

AU - Bermak, Amine

PY - 2006

Y1 - 2006

N2 - Gas identification represents a big challenge for pattern recognition systems due to several particular problems such as non-selectivity and drift. This paper proposes a gas identification committee machine (CM), which combines various gas identification algorithms, to obtain a unified decision with improved accuracy. The CM combines 5 different classifiers: K Nearest Neighbors (KNN), Multi-layer Perceptron (MLP), Radial Basis Function (RFB), Gaussian Mixture Model (GMM) and Probabilistic PCA (PPCA). A data acquisition system using tin-oxide gas sensor array has been designed in order to create a real gas data set. The committee machine is implemented by assembling the outputs of these gas identification algorithms based on weighted combination rule. Experiments on real sensors' data proved the effectiveness of our system with an improved accuracy 95.9% over the individual classifiers.

AB - Gas identification represents a big challenge for pattern recognition systems due to several particular problems such as non-selectivity and drift. This paper proposes a gas identification committee machine (CM), which combines various gas identification algorithms, to obtain a unified decision with improved accuracy. The CM combines 5 different classifiers: K Nearest Neighbors (KNN), Multi-layer Perceptron (MLP), Radial Basis Function (RFB), Gaussian Mixture Model (GMM) and Probabilistic PCA (PPCA). A data acquisition system using tin-oxide gas sensor array has been designed in order to create a real gas data set. The committee machine is implemented by assembling the outputs of these gas identification algorithms based on weighted combination rule. Experiments on real sensors' data proved the effectiveness of our system with an improved accuracy 95.9% over the individual classifiers.

KW - Committee machine

KW - Gas identification

KW - Pattern recognition

KW - Tin oxide gas sensor

UR - http://www.scopus.com/inward/record.url?scp=36849058936&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36849058936&partnerID=8YFLogxK

U2 - 10.1109/ICECS.2006.379925

DO - 10.1109/ICECS.2006.379925

M3 - Conference contribution

SN - 1424403952

SN - 9781424403950

SP - 862

EP - 865

BT - ICECS 2006 - 13th IEEE International Conference on Electronics, Circuits and Systems

ER -