A committee machine gas identification system based on dynamically reconfigurable FPGA

M Shi, A Bermak, S Chandrasekaran, A Amira, S Brahim-Belhouari

    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 tinoxide gas sensors.
    LanguageEnglish
    Pages403-414
    JournalIEEE SENSORS JOURNAL
    Volume8
    Issue number3-4
    Publication statusPublished - Mar 2008

    Fingerprint

    Field programmable gate arrays (FPGA)
    Identification (control systems)
    Classifiers
    Hardware
    Gases
    Multilayer neural networks
    Chemical sensors
    Multiplexing
    Principal component analysis
    Pattern recognition
    Sampling
    Sensors
    Processing
    Experiments

    Keywords

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

    Cite this

    Shi, M., Bermak, A., Chandrasekaran, S., Amira, A., & Brahim-Belhouari, S. (2008). A committee machine gas identification system based on dynamically reconfigurable FPGA. 8(3-4), 403-414.
    Shi, M ; Bermak, A ; Chandrasekaran, S ; Amira, A ; Brahim-Belhouari, S. / A committee machine gas identification system based on dynamically reconfigurable FPGA. 2008 ; Vol. 8, No. 3-4. pp. 403-414.
    @article{ade00621c94e48d4be29e333b46b60ce,
    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 tinoxide gas sensors.",
    keywords = "committee machine (CM), dynamically reconfigurable field programmable gate array (FPGA), gas identification, pattern recognition",
    author = "M Shi and A Bermak and S Chandrasekaran and A Amira and S Brahim-Belhouari",
    year = "2008",
    month = "3",
    language = "English",
    volume = "8",
    pages = "403--414",
    number = "3-4",

    }

    Shi, M, Bermak, A, Chandrasekaran, S, Amira, A & Brahim-Belhouari, S 2008, 'A committee machine gas identification system based on dynamically reconfigurable FPGA', vol. 8, no. 3-4, pp. 403-414.

    A committee machine gas identification system based on dynamically reconfigurable FPGA. / Shi, M; Bermak, A; Chandrasekaran, S; Amira, A; Brahim-Belhouari, S.

    Vol. 8, No. 3-4, 03.2008, p. 403-414.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - A committee machine gas identification system based on dynamically reconfigurable FPGA

    AU - Shi, M

    AU - Bermak, A

    AU - Chandrasekaran, S

    AU - Amira, A

    AU - Brahim-Belhouari, S

    PY - 2008/3

    Y1 - 2008/3

    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 tinoxide 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 tinoxide gas sensors.

    KW - committee machine (CM)

    KW - dynamically reconfigurable field programmable gate array (FPGA)

    KW - gas identification

    KW - pattern recognition

    M3 - Article

    VL - 8

    SP - 403

    EP - 414

    IS - 3-4

    ER -

    Shi M, Bermak A, Chandrasekaran S, Amira A, Brahim-Belhouari S. A committee machine gas identification system based on dynamically reconfigurable FPGA. 2008 Mar;8(3-4):403-414.