Drift Compensation for pH IsFET Sensor Using NARX Neural Networks


  • Mohammad Iqwhanus Syaffa Amir
  • Md Rizal Othman
  • Mohd Ismahadi Syono






Artificial Neural Network, Drift, Bayesian regularization, Ion sensitive field effect transistor, Nonlinear autoregressive.


This paper introduces a Nonlinear Autoregressive Neural Network (NARX) to predict the sensor error of IsFET pH drift with accuracy over the long period. The Bayesian Regularization (BR) backpropagation was used as network training function for this problem and combined with different delay and hidden layer. The results were compared to predict the sensor error in buffer solution pH 4, pH 7 and pH 10 over the time. The NARX performance will be measure based on the value of Mean Squared Error (MSE) and coefficient of determination (R2). The results proved by using Bayesian Regularization with 10 hidden nodes and 50 delays produced the accurate sensor error prediction. This research will provide the significant contributions to the implementation of IsFET pH sensor drift compensation over the time.




[1] Moser, N., Lande, T. S., Toumazou, C., & Georgiou, P. (2016). ISFETs in CMOS and emergent trends in instrumentation: A review. IEEE Sensors Journal, 16(17), 6496-6514.

[2] Jamasb, S., Collins, S. D., & Smith, R. L. (1998). A physical model for threshold voltage instability in Si/sub 3/N/sub 4/-gate H/sup+/-sensitive FET's (pH ISFET's). IEEE Transactions on Electron Devices, 45(6), 1239-1245.

[3] Jamasb, S. (2004). An analytical technique for counteracting drift in ion-selective field effect transistors (ISFETs). IEEE Sensors Journal, 4(6), 795-801.

[4] Chen, D. Y., & Chan, P. K. (2008). An intelligent ISFET sensory system with temperature and drift compensation for long-term monitoring. IEEE Sensors Journal, 8(12), 1948–1959.

[5] Chung, W. Y., Cruz, F. R. G., Yang, C. H., He, F. S., Liu, T. T., Pijanowska, D. G., Torbicz, W., Grabiec, P. B., & Jarosewicz, B. (2010). CMOS readout circuit developments for ion sensitive field effect transistor based sensor applications. In J. W. Swart (Ed.), Solid State Circuits Technologies. London: IntechOpen, pp. 421-444.

[6] Sundaram, S., & Sharma, N. N. (2010). Modeling interface diffusion as a mechanism for threshold voltage drift in pH sensors. Proceedings of the IEEE Sensors, pp. 2547-2550.

[7] Lee, S. K., & Choi, S. Y. (2010). Improvement of drift characteristic to continuously measure Al2O3 pH-ISFET with the protective structure. Proceedings of the Meeting Abstracts, pp. 38-38.

[8] Chang, K. M., Chang, C. T., Chao, K. Y., & Lin, C. H. (2010). A novel pH-dependent drift improvement method for zirconium dioxide gated pH-ion sensitive field effect transistors. Sensors, 10(5), 4643-4654.

[9] Jiao, L. H., & Barakat, N. (2013). Ion-sensitive field effect transistor as a pH sensor. Journal of Nanoscience and Nanotechnology, 13(2), 1194-1198.

[10] Abdullah, W. F. H., Othman, M., Ali, M. A. M., & Islam, M. S. (2010). Multiple feedforward classifiers by bagging for ion-sensitive field effect transistor sensor response. Proceedings of the IEEE International Conference on Computer Applications and Industrial Electronics, pp. 90-93.

[11] Das, M. P., & Bhuyan, M. (2014). New ISFET interface circuits with noise reduction capability. Proceedings of the IEEE International Conference on Recent Advances and Innovations in Engineering, pp. 1-6.

[12] Uzzal, M. M., Zarkesh-Ha, P., Edwards, J. S., Coelho, E., & Rawat, P. (2014). A highly sensitive ISFET using pH-to-current conversion for real-time DNA sequencing. Proceedings of the 27th IEEE International System-on-Chip Conference, pp. 410-414.

[13] Sohbati, M., & Toumazou, C. (2014). A temperature insensitive continuous time ΔpH to digital converter. Proceedings of the IEEE International Symposium on Circuits and Systems, pp. 37-40.

[14] Kalofonou, M., & Toumazou, C. (2014). A low power sub-µW chemical Gilbert cell for ISFET differential reaction monitoring. IEEE Transactions on Biomedical Circuits and Systems, 8(4), 565-574.

[15] Hu, Y., & Georgiou, P. (2014). A robust ISFET pH-measuring front-end for chemical reaction monitoring. IEEE Transactions on Biomedical Circuits and Systems, 8(2), 177-185.

[16] Moser, N., Lande, T. S., & Georgiou, P. (2015). A novel pH-to-time ISFET pixel architecture with offset compensation. Proceedings of the IEEE International Symposium on Circuits and Systems, pp. 481-484.

[17] Jamasb, S. (2016). A time-domain method for correction of instability in sensors based on field effect transistors (FETs). International Journal of Circuits, Systems and Signal Processing, 10, 119–125.

[18] Bhardwaj, R., Majumder, S., Ajmera, P. K., Sinha, S., Sharma, R., Mukhiya, R., & Narang, P. (2017). Temperature compensation of ISFET based pH sensor using artificial neural networks. Proceedings of the IEEE Regional Symposium on Micro and Nanoelectronics, pp. 155-158.

[19] Siegelmann, H. T., Horne, B. G., & Giles, C. L. (1997). Computational capabilities of recurrent NARX neural networks. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 27(2), 208-215.

[20] Lin, T. N., Giles, C. L., Horne, B. G., & Kung, S. Y. (1997). A delay damage model selection algorithm for NARX neural networks. IEEE Transactions on Signal Processing, 45(11), 2719-2730.

[21] Diaconescu, E. (2008). The use of NARX neural networks to predict chaotic time series. WSEAS Transactions on Computer Research, 3(3), 182-191.

[22] Diaconescu, E. (2008). The use of NARX neural networks to predict chaotic time series. WSEAS Transactions on Computer Research, 3(3), 182-191.

[23] Al-Sbou, Y. A., & Alawasa, K. M. (2017). Nonlinear autoregressive recurrent neural network model for solar radiation prediction. International Journal of Applied Engineering Research, 12(14), 4518-4527.

[24] Guzman, S. M., Paz, J. O., & Tagert, M. L. M. (2017). The use of NARX neural networks to forecast daily groundwater levels. Water Resources Management, 31(5), 1591-1603.

[25] Pisoni, E., Farina, M., Carnevale, C., & Piroddi, L. (2009). Forecasting peak air pollution levels using NARX models. Engineering Applications of Artificial Intelligence, 22(4-5), 593-602.

[26] Ruiz, L. G. B., Cuéllar, M. P., Calvo-Flores, M. D., & Jiménez, M. D. C. P. (2016). An application of non-linear autoregressive neural networks to predict energy consumption in public buildings. Energies, 9(9), 1-21.

View Full Article: