Ion-sensitive field-effect transistor selectivity with back-propagation neural network

Wan Fazlida Hanim Abdullah, Masuri Othman, Mohd Alaudin Mohd Ali, Md. Shabiul Islam

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

Abstract

The ion-sensitive field-effect transistor (ISFET) produces voltage signals, in a similar manner to the metal-oxide field-effect transistor, sensitive to ionic concentration change. When immersed in ionic solution with mixed ions of similar chemical characteristics, ISFETs respond with deceptive voltage signals due to the interfering ion contribution over the main ion of interest. In this paper, we applied back-propagation neural network to data acquired from titration of potassium ion (K+) and ammonium ion (NH4+). The role of the post-processing is to extract main ionic concentration level in the presence of an interfering ion. Primary data from measured observations with actual device variation and background ion was fed to a feedforward multilayer perceptron trained with several methods of back-propagation. Results show that neural network trained with backpropagation algorithm is able to improve concentration information by gives 15% improvement with 4 sensor array compared to direct estimation without post-processing. Additionally, averaging from multiple classifiers is shown to give a further 5% improvement on the regression factor between output and targeted values.

Original languageEnglish
Title of host publicationInternational Conference on Electronic Devices, Systems, and Applications
Pages314-317
Number of pages4
DOIs
Publication statusPublished - 2011
Event2011 International Conference on Electronic Devices, Systems and Applications, ICEDSA 2011 - Kuala Lumpur
Duration: 25 Apr 201127 Apr 2011

Other

Other2011 International Conference on Electronic Devices, Systems and Applications, ICEDSA 2011
CityKuala Lumpur
Period25/4/1127/4/11

Fingerprint

Ion sensitive field effect transistors
Backpropagation
Neural networks
Ions
Backpropagation algorithms
Sensor arrays
Electric potential
Multilayer neural networks
Processing
Field effect transistors
Titration
Potassium
Classifiers
Oxides
Metals

Keywords

  • electrochemical devices
  • microsensors
  • MOSFET sensor array
  • selectivity
  • supervised learning

ASJC Scopus subject areas

  • Computer Science Applications
  • Hardware and Architecture
  • Software
  • Electrical and Electronic Engineering

Cite this

Hanim Abdullah, W. F., Othman, M., Mohd Ali, M. A., & Islam, M. S. (2011). Ion-sensitive field-effect transistor selectivity with back-propagation neural network. In International Conference on Electronic Devices, Systems, and Applications (pp. 314-317). [5959093] https://doi.org/10.1109/ICEDSA.2011.5959093

Ion-sensitive field-effect transistor selectivity with back-propagation neural network. / Hanim Abdullah, Wan Fazlida; Othman, Masuri; Mohd Ali, Mohd Alaudin; Islam, Md. Shabiul.

International Conference on Electronic Devices, Systems, and Applications. 2011. p. 314-317 5959093.

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

Hanim Abdullah, WF, Othman, M, Mohd Ali, MA & Islam, MS 2011, Ion-sensitive field-effect transistor selectivity with back-propagation neural network. in International Conference on Electronic Devices, Systems, and Applications., 5959093, pp. 314-317, 2011 International Conference on Electronic Devices, Systems and Applications, ICEDSA 2011, Kuala Lumpur, 25/4/11. https://doi.org/10.1109/ICEDSA.2011.5959093
Hanim Abdullah WF, Othman M, Mohd Ali MA, Islam MS. Ion-sensitive field-effect transistor selectivity with back-propagation neural network. In International Conference on Electronic Devices, Systems, and Applications. 2011. p. 314-317. 5959093 https://doi.org/10.1109/ICEDSA.2011.5959093
Hanim Abdullah, Wan Fazlida ; Othman, Masuri ; Mohd Ali, Mohd Alaudin ; Islam, Md. Shabiul. / Ion-sensitive field-effect transistor selectivity with back-propagation neural network. International Conference on Electronic Devices, Systems, and Applications. 2011. pp. 314-317
@inproceedings{54343465bf034936bff7e47252fca339,
title = "Ion-sensitive field-effect transistor selectivity with back-propagation neural network",
abstract = "The ion-sensitive field-effect transistor (ISFET) produces voltage signals, in a similar manner to the metal-oxide field-effect transistor, sensitive to ionic concentration change. When immersed in ionic solution with mixed ions of similar chemical characteristics, ISFETs respond with deceptive voltage signals due to the interfering ion contribution over the main ion of interest. In this paper, we applied back-propagation neural network to data acquired from titration of potassium ion (K+) and ammonium ion (NH4+). The role of the post-processing is to extract main ionic concentration level in the presence of an interfering ion. Primary data from measured observations with actual device variation and background ion was fed to a feedforward multilayer perceptron trained with several methods of back-propagation. Results show that neural network trained with backpropagation algorithm is able to improve concentration information by gives 15{\%} improvement with 4 sensor array compared to direct estimation without post-processing. Additionally, averaging from multiple classifiers is shown to give a further 5{\%} improvement on the regression factor between output and targeted values.",
keywords = "electrochemical devices, microsensors, MOSFET sensor array, selectivity, supervised learning",
author = "{Hanim Abdullah}, {Wan Fazlida} and Masuri Othman and {Mohd Ali}, {Mohd Alaudin} and Islam, {Md. Shabiul}",
year = "2011",
doi = "10.1109/ICEDSA.2011.5959093",
language = "English",
isbn = "9781612843896",
pages = "314--317",
booktitle = "International Conference on Electronic Devices, Systems, and Applications",

}

TY - GEN

T1 - Ion-sensitive field-effect transistor selectivity with back-propagation neural network

AU - Hanim Abdullah, Wan Fazlida

AU - Othman, Masuri

AU - Mohd Ali, Mohd Alaudin

AU - Islam, Md. Shabiul

PY - 2011

Y1 - 2011

N2 - The ion-sensitive field-effect transistor (ISFET) produces voltage signals, in a similar manner to the metal-oxide field-effect transistor, sensitive to ionic concentration change. When immersed in ionic solution with mixed ions of similar chemical characteristics, ISFETs respond with deceptive voltage signals due to the interfering ion contribution over the main ion of interest. In this paper, we applied back-propagation neural network to data acquired from titration of potassium ion (K+) and ammonium ion (NH4+). The role of the post-processing is to extract main ionic concentration level in the presence of an interfering ion. Primary data from measured observations with actual device variation and background ion was fed to a feedforward multilayer perceptron trained with several methods of back-propagation. Results show that neural network trained with backpropagation algorithm is able to improve concentration information by gives 15% improvement with 4 sensor array compared to direct estimation without post-processing. Additionally, averaging from multiple classifiers is shown to give a further 5% improvement on the regression factor between output and targeted values.

AB - The ion-sensitive field-effect transistor (ISFET) produces voltage signals, in a similar manner to the metal-oxide field-effect transistor, sensitive to ionic concentration change. When immersed in ionic solution with mixed ions of similar chemical characteristics, ISFETs respond with deceptive voltage signals due to the interfering ion contribution over the main ion of interest. In this paper, we applied back-propagation neural network to data acquired from titration of potassium ion (K+) and ammonium ion (NH4+). The role of the post-processing is to extract main ionic concentration level in the presence of an interfering ion. Primary data from measured observations with actual device variation and background ion was fed to a feedforward multilayer perceptron trained with several methods of back-propagation. Results show that neural network trained with backpropagation algorithm is able to improve concentration information by gives 15% improvement with 4 sensor array compared to direct estimation without post-processing. Additionally, averaging from multiple classifiers is shown to give a further 5% improvement on the regression factor between output and targeted values.

KW - electrochemical devices

KW - microsensors

KW - MOSFET sensor array

KW - selectivity

KW - supervised learning

UR - http://www.scopus.com/inward/record.url?scp=80055096093&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80055096093&partnerID=8YFLogxK

U2 - 10.1109/ICEDSA.2011.5959093

DO - 10.1109/ICEDSA.2011.5959093

M3 - Conference contribution

SN - 9781612843896

SP - 314

EP - 317

BT - International Conference on Electronic Devices, Systems, and Applications

ER -