Neural Network Algorithm Development for Ion Sensitive Field Effect Transistor (ISFET) Sensor

  • Authors

    • Maizatul Zolkapli
    • Norsuzila Ya’acob
    • Anees Abdul Aziz
    • Ahmad Sabirin Zoolfakar
    • Azrif Manut
    • Wan Fazlida Hanim Abdullah
    • Muhammad Nasrul Hakim B. Adenan
    2018-07-21
    https://doi.org/10.14419/ijet.v7i3.11.15918
  • Artificial Neural Network (ANN), Backpropagation, CHEMFET, ISFET, MATLAB.
  • Ion Sensitive Field-Effect Transistor (ISFET) is a kind of sensor that able to differentiate the ion by replacing the gate of the FET with electrode and the membrane. Membrane acts as selector for the ions whereas the sensor detects the ions and converts it into electrical signal. However, the sensor has weakness to detect main ion from the interfering ion in the mixed solution when the ions have same characteristic.  In this work, potassium ion (K+) and ammonium ion (NH4+) was used as the sample for both ions that have similar size.  To overcome the problem, the sensor needs to be trained for pre-calibrate and pre-process by developing a model of Artificial Neural Networks (ANN) in MATLAB software. The ANN makes the model learn the pattern by the sample of inputs and outputs to estimate results or to get more accurate data. Backpropagation is used as the learning method of ANN model. The objective of this work is to develop ANN model for ISFET sensor that able to estimate the main ion in mixed solution by learning the pattern of the input and output of the sensor. The ANN model performance can be optimized by altering certain parameters in the learning algorithm. The results show that the model is able to predict with 97% accuracy and has strong and precise estimation ability with R-factor of 91.55%.

     

     

  • References

    1. [1] P. Ir, P. B. Em, and F. Ee, “ISFET , Theory and Practice,†in IEEE Sensor Conference Toronto, 2003, no. October, pp. 1–26.

      [2] W. F. H. Abdullah, M. Othman, M. A. Mohd Ali, and M. S. Islam, “Knowledge Representation of Ion-Sensitive Field-Effect Transistor Voltage Response for Potassium Ion Concentration Detection in Mixed Potassium/Ammonium Ion Solutions 1,†Am. J. Appl. Sci., vol. 7, no. 1, pp. 81–88, 2010.

      [3] R. A. Rani, M. I. Syono, and A. S. Ramli, “Multi-finger gate ISFET (Mf-ISFET) for pH sensor application,†in IEEE International Conference on Semiconductor Electronics, Proceedings, ICSE, 2008, pp. 350–353.

      [4] R. A. Rani and O. Sidek, “ISFET pH sensor characterization: towards biosensor microchip application,†in 2004 IEEE Region 10 Conference TENCON 2004., 2004, vol. D, pp. 660–663.

      [5] W. F. H. Abdullah, M. Othman, M. A. Mohd Ali, and M. S. Islam, “Ion-sensitive field-effect transistor selectivity with back-propagation neural network,†in International Conference on Electronic Devices, Systems, and Applications, 2011, pp. 314–317.

      [6] P. Jeatrakul and K. W. Wong, “Comparing the performance of different neural networks for binary classification problems,†in 2009 Eighth International Symposium on Natural Language Processing, 2009, pp. 111–115.

      [7] A. Mahmoudabadi, “Comparison of Weighted and Simple Linear Regression and Artificial Neural Network Models in Freeway Accidents Prediction,†in 2010 Second International Conference on Computer and Network Technology, 2010, pp. 392–396.

  • Downloads

  • How to Cite

    Zolkapli, M., Ya’acob, N., Abdul Aziz, A., Sabirin Zoolfakar, A., Manut, A., Fazlida Hanim Abdullah, W., & Nasrul Hakim B. Adenan, M. (2018). Neural Network Algorithm Development for Ion Sensitive Field Effect Transistor (ISFET) Sensor. International Journal of Engineering & Technology, 7(3.11), 1-5. https://doi.org/10.14419/ijet.v7i3.11.15918