Skip to main content
Log in

Ensemble Learning for Chemical Sensor Arrays

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Electrochemical sensors, like ion-selective field transistors (ISFET), are electronic devices that merge solid-state electronic technology with chemical sensors so as to be sensitive to the concentration of a particular ion in a solution. However, as it has been previously reported, their response does not only depend on a single ion but also is affected by several interfering ions found in the solution to be measured. These interfering ions can be considered as noise and consequently, a post-processing stage that increases the SNR is obligatory. Our work shows how ensemble learning methods could be used in an array of chemical sensors in order to deal with this problem. In particular, we introduce a novel neural learning architecture for ISFET arrays, which employ ISFET models as prior knowledge. The proposed ensemble learning systems are RBF-like solutions based on bagging and optimal linear combination. Several experimental results are included, which demonstrate the interest and viability of the proposed solution.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. Chen, T.,et al.:Highlights of Statistical Signal and Array Processing,IEEE Signal Processing Mag. (Sep.1998),21–64.

  2. Gardner, J.W.:Microsensors:Principles and Applications,John Wiley & Sons, Chichester, 1994.

    Google Scholar 

  3. Nagle,H.T., Schiffman, S.S. and Gutierrez-Osuna, R.:The how and why of electronic noses,IEEE Spectrum.(1998),22–31.

  4. Gutierrez-Osuna, R.and Nagle, H.T.:A method for evaluating data-processing techni-ques for odor classi cation with an array of gas sensors,IEEE Trans.Sys.Man,Cybern. B.SMVB-29,No.5,(1999),626–632.

    Google Scholar 

  5. Wiemho¨fer, H.D. and Cammann, K.:Ion-sensitive Electrodes,In:W. Go¨pel J. Hesse and J.N. Zemel (eds.),Sensors:A Comprehensive Survey,Vol.2,Chemical and Biochemical Sensors Part I.Edited by W.Go ¨pel,T.A.Jones,M.Kleitz,J.Lundstro ¨m,T.Seiyama, VCH,Weinheim,pp.177–183,1991.

  6. Cattrall, R.W.:Chemical Sensors,Oxford University Press, Oxford,1997.

  7. Wilson, D.M., Hoyt, S., Janata, J., Booksh K. and Obando, L.:Chemical Sensors for Portable,Handheld Field Instruments,IEEE Sensors J.,1 (4),(December 2001).

  8. van den Berg, A.:Ion-sensitive Field Effect Transistors,In:W. Go¨pel J. Hesse and J.N. Zemel (eds.),Sensors:A Comprehensive Survey,Vol.2,Chemical and Biochemical Sensors Part I.Edited by W.Go ¨pel,T.A.Jones,M.Kleitz,J.Lundstro ¨m,T.Seiyama,VCH, Weinheim,pp.474–501,1991.

  9. Dybko, A.:Chemical Sensors:Technology and Metrology,Ph.D.Thesis,Department of Analytical Chemistry, Warsaw University of Technology,2001.

    Google Scholar 

  10. Baucke, F.G.K., Naumann, R. and Alexander-Weber, Ch.:Multiple-point calibration with linear regression as a proposed standardization procedure for high-precision pH measurements,Anal.Chem.65 (1993),3244–3251.

    Google Scholar 

  11. Sharkey, A. (ed.).:Combining Artificial Neural Nets,Springer-Verlag, Berlin,1999.

    Google Scholar 

  12. Breiman, L.:The Heuristics of Instability in Model Selection,Ann.Stat.,24 (1997), 2350–2381.

    Google Scholar 

  13. Breiman, L.:Bias-Variance,Regularization,Instability and Stabilization,In:C.M. Bishop (ed.),Neural Networks and Machine Learning,NATO ASI Series,Series F: Computer and Systems Sciences,Vol.168,Springer-Verlag, Berlin,1998.

    Google Scholar 

  14. Geman,S., Bienenstock, E. and Doursat, R.:Neural Networks and the bias/variance dilemma,Neural Comp.4 (1992).

  15. Breiman, L.:Bagging Predictors,Machine Learning.26 No.2,(1996),734–751.

    Google Scholar 

  16. Natftaly, U., Intrator, N., Horn, D.:Optimal Ensemble Averaging of Neural Networks, Technical Report,Israel Institute of Technology,(1997).

  17. Hashem, S.:Optimal linear combinations of neural networks,Neural Networks,10 (4), (1997),599–614.

    Google Scholar 

  18. Bergveld, P.:Development of an Ion-sensitive solid-state device for neurophysiological measurements,IEEE Trans.Biomed.Eng.BME-17 (1970),70–71.

    Google Scholar 

  19. Warner, R.M. Jr. and Grung, B.L.:MOSFET:Theory and Design,Oxford University Press, New York,1999.

    Google Scholar 

  20. Bousse, L., de Rooij, N.F. and Bergveld, P.:Operation of chemically sensitive eld-effect sensors as a function of the insulator-electrolyte interface,IEEE Trans.Electron.Devices. ED-30 (1983),1263–1273.

    Google Scholar 

  21. Smith, R.L. and Scott, D.C.:An integrated sensor for electrochemical measurements, IEEE Trans.Biomed.Eng.BME-33 (1986),83–90.

    Google Scholar 

  22. Sibbald, A.:Chemical-sensitive eld-effect transistors,IEE Proceedings.130 (5),Part I (1983),233–244.

    Google Scholar 

  23. Martinoia, S. and Massobrio, G.:A behavioral macromodel of the ISFET in SPICE, Sens.Act.B.62 (2000),182–189.

    Google Scholar 

  24. Brzo´zka, Z., Holterman, A.J., Honing, W.N., Verkerk, U.H., can den Vlekkert, H.H., Engbersen, J.F.J. and Reinholut, D.N.:Enhanced performance of potassium CHEM-FET by optimization of a polysiloxane membrane,Sens.Act.B.18–19 (1994),38–41.

    Google Scholar 

  25. Opalski,L.J.:Personal communication.

  26. Pala´n, B., Santos, F.V., Karam, J.M., Courtois, B. and Husa´k, M.:New ISFET sensor interface circuit for biomedical applications,Sens.Act.B.57 (1999),36–42.

    Google Scholar 

  27. Chin, Y.-L., Chou, J.-C., Sun, T.-P., Liao, H.-K., Chung, W.-Y. and Hsiung, S.-K.: A novel SnO2/Al discrete gate ISFET pH sensor with CMOS standard process,Sens.Act. B 75 (2001),36–42.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to S. Bermejo.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Bermejo, S., Cabestany, J. Ensemble Learning for Chemical Sensor Arrays. Neural Processing Letters 19, 25–35 (2004). https://doi.org/10.1023/B:NEPL.0000016844.22502.a8

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/B:NEPL.0000016844.22502.a8

Navigation