CHEMFET response for supervised learning of neural network

Wan Fazlida Hanim Abdullah, Masuri Othman, Mohd Alaudin Mohd Ali

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

    1 Citation (Scopus)

    Abstract

    Electrical response from Chemical Field-Effect Transistor (CHEMFET) sensors intended to be selective to a specific ion is influenced by interfering chemical ions present in the solution. To be able to detect the main chemical ion of interest, we include a neural network post-processing stage after a readout interface circuit. This work focuses on the training data collection of potassium sensors in the presence of ammonium ions intended for the supervised learning of the neural network module. Using function fitting approach, the network aims to find the potassium ion concentration. Training data is obtained from sample solutions prepared by keeping the main ion concentration constant while the activity of the interfering ions based on the fixed interference method. The training algorithm is back-propagation with generalized delta rule on a multilayer feed-forward network. Activation function based on the MOSFET drain current equation in the linear region is attempted in the hidden layer. We find that referencing voltage readings to sensor response in deionized water prior to measurement improves repeatability of measured training data.

    Original languageEnglish
    Title of host publication2009 International Conference on Computer and Electrical Engineering, ICCEE 2009
    Pages452-455
    Number of pages4
    Volume1
    DOIs
    Publication statusPublished - 2009
    Event2009 International Conference on Computer and Electrical Engineering, ICCEE 2009 - Dubai
    Duration: 28 Dec 200930 Dec 2009

    Other

    Other2009 International Conference on Computer and Electrical Engineering, ICCEE 2009
    CityDubai
    Period28/12/0930/12/09

    Fingerprint

    Supervised learning
    Field effect transistors
    Neural networks
    Ions
    Potassium
    Sensors
    Deionized water
    Drain current
    Backpropagation
    Multilayers
    Chemical activation
    Networks (circuits)
    Electric potential
    Processing

    Keywords

    • Back-propagation
    • CHEMFET
    • Chemical sensor
    • Readout circuit
    • Semiconductor device

    ASJC Scopus subject areas

    • Computer Science(all)
    • Electrical and Electronic Engineering

    Cite this

    Abdullah, W. F. H., Othman, M., & Ali, M. A. M. (2009). CHEMFET response for supervised learning of neural network. In 2009 International Conference on Computer and Electrical Engineering, ICCEE 2009 (Vol. 1, pp. 452-455). [5380450] https://doi.org/10.1109/ICCEE.2009.184

    CHEMFET response for supervised learning of neural network. / Abdullah, Wan Fazlida Hanim; Othman, Masuri; Ali, Mohd Alaudin Mohd.

    2009 International Conference on Computer and Electrical Engineering, ICCEE 2009. Vol. 1 2009. p. 452-455 5380450.

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

    Abdullah, WFH, Othman, M & Ali, MAM 2009, CHEMFET response for supervised learning of neural network. in 2009 International Conference on Computer and Electrical Engineering, ICCEE 2009. vol. 1, 5380450, pp. 452-455, 2009 International Conference on Computer and Electrical Engineering, ICCEE 2009, Dubai, 28/12/09. https://doi.org/10.1109/ICCEE.2009.184
    Abdullah WFH, Othman M, Ali MAM. CHEMFET response for supervised learning of neural network. In 2009 International Conference on Computer and Electrical Engineering, ICCEE 2009. Vol. 1. 2009. p. 452-455. 5380450 https://doi.org/10.1109/ICCEE.2009.184
    Abdullah, Wan Fazlida Hanim ; Othman, Masuri ; Ali, Mohd Alaudin Mohd. / CHEMFET response for supervised learning of neural network. 2009 International Conference on Computer and Electrical Engineering, ICCEE 2009. Vol. 1 2009. pp. 452-455
    @inproceedings{e9e7f74885c243b3a759abbc30967a8b,
    title = "CHEMFET response for supervised learning of neural network",
    abstract = "Electrical response from Chemical Field-Effect Transistor (CHEMFET) sensors intended to be selective to a specific ion is influenced by interfering chemical ions present in the solution. To be able to detect the main chemical ion of interest, we include a neural network post-processing stage after a readout interface circuit. This work focuses on the training data collection of potassium sensors in the presence of ammonium ions intended for the supervised learning of the neural network module. Using function fitting approach, the network aims to find the potassium ion concentration. Training data is obtained from sample solutions prepared by keeping the main ion concentration constant while the activity of the interfering ions based on the fixed interference method. The training algorithm is back-propagation with generalized delta rule on a multilayer feed-forward network. Activation function based on the MOSFET drain current equation in the linear region is attempted in the hidden layer. We find that referencing voltage readings to sensor response in deionized water prior to measurement improves repeatability of measured training data.",
    keywords = "Back-propagation, CHEMFET, Chemical sensor, Readout circuit, Semiconductor device",
    author = "Abdullah, {Wan Fazlida Hanim} and Masuri Othman and Ali, {Mohd Alaudin Mohd}",
    year = "2009",
    doi = "10.1109/ICCEE.2009.184",
    language = "English",
    isbn = "9780769539256",
    volume = "1",
    pages = "452--455",
    booktitle = "2009 International Conference on Computer and Electrical Engineering, ICCEE 2009",

    }

    TY - GEN

    T1 - CHEMFET response for supervised learning of neural network

    AU - Abdullah, Wan Fazlida Hanim

    AU - Othman, Masuri

    AU - Ali, Mohd Alaudin Mohd

    PY - 2009

    Y1 - 2009

    N2 - Electrical response from Chemical Field-Effect Transistor (CHEMFET) sensors intended to be selective to a specific ion is influenced by interfering chemical ions present in the solution. To be able to detect the main chemical ion of interest, we include a neural network post-processing stage after a readout interface circuit. This work focuses on the training data collection of potassium sensors in the presence of ammonium ions intended for the supervised learning of the neural network module. Using function fitting approach, the network aims to find the potassium ion concentration. Training data is obtained from sample solutions prepared by keeping the main ion concentration constant while the activity of the interfering ions based on the fixed interference method. The training algorithm is back-propagation with generalized delta rule on a multilayer feed-forward network. Activation function based on the MOSFET drain current equation in the linear region is attempted in the hidden layer. We find that referencing voltage readings to sensor response in deionized water prior to measurement improves repeatability of measured training data.

    AB - Electrical response from Chemical Field-Effect Transistor (CHEMFET) sensors intended to be selective to a specific ion is influenced by interfering chemical ions present in the solution. To be able to detect the main chemical ion of interest, we include a neural network post-processing stage after a readout interface circuit. This work focuses on the training data collection of potassium sensors in the presence of ammonium ions intended for the supervised learning of the neural network module. Using function fitting approach, the network aims to find the potassium ion concentration. Training data is obtained from sample solutions prepared by keeping the main ion concentration constant while the activity of the interfering ions based on the fixed interference method. The training algorithm is back-propagation with generalized delta rule on a multilayer feed-forward network. Activation function based on the MOSFET drain current equation in the linear region is attempted in the hidden layer. We find that referencing voltage readings to sensor response in deionized water prior to measurement improves repeatability of measured training data.

    KW - Back-propagation

    KW - CHEMFET

    KW - Chemical sensor

    KW - Readout circuit

    KW - Semiconductor device

    UR - http://www.scopus.com/inward/record.url?scp=77950503724&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77950503724&partnerID=8YFLogxK

    U2 - 10.1109/ICCEE.2009.184

    DO - 10.1109/ICCEE.2009.184

    M3 - Conference contribution

    SN - 9780769539256

    VL - 1

    SP - 452

    EP - 455

    BT - 2009 International Conference on Computer and Electrical Engineering, ICCEE 2009

    ER -