Locally weighted neural networks for an analysis of the biosensor response
Kybernetika, Tome 43 (2007) no. 1, pp. 21-30 Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

This paper presents a semi-global mathematical model for an analysis of a signal of amperometric biosensors. Artificial neural networks were applied to an analysis of the biosensor response to multi-component mixtures. A large amount of the learning and test data was synthesized using computer simulation of the biosensor response. The biosensor signal was analyzed with respect to the concentration of each component of the mixture. The paradigm of locally weighted linear regression was used for retraining the neural networks. The application of locally weighted regression significantly improved the quality of the prediction of the concentrations.
This paper presents a semi-global mathematical model for an analysis of a signal of amperometric biosensors. Artificial neural networks were applied to an analysis of the biosensor response to multi-component mixtures. A large amount of the learning and test data was synthesized using computer simulation of the biosensor response. The biosensor signal was analyzed with respect to the concentration of each component of the mixture. The paradigm of locally weighted linear regression was used for retraining the neural networks. The application of locally weighted regression significantly improved the quality of the prediction of the concentrations.
Classification : 62J12, 62M45, 62P10, 68T05, 92C45, 92C55
Keywords: locally weighted regression; artificial neural network; modelling; biosensor
@article{KYB_2007_43_1_a1,
     author = {Baronas, Romas and Ivanauskas, Feliksas and Maslovskis, Romualdas and Radavi\v{c}ius, Marijus and Vaitkus, Pranas},
     title = {Locally weighted neural networks for an analysis of the biosensor response},
     journal = {Kybernetika},
     pages = {21--30},
     year = {2007},
     volume = {43},
     number = {1},
     mrnumber = {2343328},
     zbl = {1136.62374},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/KYB_2007_43_1_a1/}
}
TY  - JOUR
AU  - Baronas, Romas
AU  - Ivanauskas, Feliksas
AU  - Maslovskis, Romualdas
AU  - Radavičius, Marijus
AU  - Vaitkus, Pranas
TI  - Locally weighted neural networks for an analysis of the biosensor response
JO  - Kybernetika
PY  - 2007
SP  - 21
EP  - 30
VL  - 43
IS  - 1
UR  - http://geodesic.mathdoc.fr/item/KYB_2007_43_1_a1/
LA  - en
ID  - KYB_2007_43_1_a1
ER  - 
%0 Journal Article
%A Baronas, Romas
%A Ivanauskas, Feliksas
%A Maslovskis, Romualdas
%A Radavičius, Marijus
%A Vaitkus, Pranas
%T Locally weighted neural networks for an analysis of the biosensor response
%J Kybernetika
%D 2007
%P 21-30
%V 43
%N 1
%U http://geodesic.mathdoc.fr/item/KYB_2007_43_1_a1/
%G en
%F KYB_2007_43_1_a1
Baronas, Romas; Ivanauskas, Feliksas; Maslovskis, Romualdas; Radavičius, Marijus; Vaitkus, Pranas. Locally weighted neural networks for an analysis of the biosensor response. Kybernetika, Tome 43 (2007) no. 1, pp. 21-30. http://geodesic.mathdoc.fr/item/KYB_2007_43_1_a1/

[1] Artursson T., Eklöv T., Lundström I., Mårtensson P., Sjöström, M., Holmberg M.: Drift correction for gas sensors using multivariate methods. J. Chemometrics 14 (2000), 711–723 | DOI

[2] Atkeson C. G., Moore A. W., Schaal S.: Locally weighted learning. Artificial Intelligence Rev. 11 (1997), 11–73 | DOI

[3] Baronas R., Christensen J., Ivanauskas, F., Kulys J.: Computer simulation of amperometric biosensor response to mixtures of compounds. Nonlinear Anal. Model. Control 7 (2002), 3–14 | Zbl

[4] Baronas R., Ivanauskas, F., Kulys J.: The influence of the enzyme membrane thickness on the response of amperometric biosensors. Sensors 3 (2003), 248–262 | DOI

[5] Baronas R., Ivanauskas F., Maslovskis, R., Vaitkus P.: An analysis of mixtures using amperometric biosensors and artificial neural networks. J. Math. Chem. 36 (2004), 281–297 | DOI | MR | Zbl

[6] Chan L. W., Szeto C. C.: Training recurrent network with block-diagonal approximated Levenberg–Marquardt algorithm. In: Proc. IEEE Internat. Joint Conference on Neural Networks, IJCNN ’99, pp. 1521–1526, 1999

[7] Devroye L., Gyorfi, L., Lugosi G.: A Probabilistic Theory of Pattern Recognition. Springer–Verlag, New York 1996 | MR

[8] Haykin S.: Neural Networks: A Comprehensive Foundation. Second edition. Prentice Hall, New York 1999 | Zbl

[9] INTELLISENS: Intelligent Signal Processing of Biosensor Arrays Using Pattern Recognition for Characterisation of Wastewater: Aiming Towards Alarm Systems. EC RTD project. 2000 – 2003

[10] Malkavaara P., Alén, R., Kolehmainen E.: Chemometrics: an important tool for the modern chemist, an example from wood-processing chemistry. J. Chem. Inf. Comput. Sci. 40 (2000), 438–441 | DOI

[11] Martens H., Næs T.: Multivariate Calibration. Wiley, Chichester 1989 | MR | Zbl

[12] Moore A. W., Schneider J. G., Deng K.: Efficient Locally Weighted Polynomial Regression Predictions. In: Proc. Fourteenth International Conference on Machine Learning, pp. 236–244, 1997

[13] Nakamoto T., Hiramatsu H.: Study of odor recorder for dynamical change of odor using QCM sensors and neural network. Sens. Actuators B 85 (2002), 98–105 | DOI

[14] Patterson D.: Artificial Neural Networks, Theory and Applications. Prentice Hall, Upper Saddle River 1996 | Zbl

[15] Rao C. R.: Linear Statistical Inference and its Application. Wiley, New York 1973 | MR

[16] Rogers K. R.: Biosensors for environmental applications. Biosens. Biolectron. 10 (1995), 533–541 | DOI

[17] Ruppert D., Wand M. P.: Multivariate locally weighted least squares regression. Ann. Statist. 22 (1994), 1346–1370 | DOI | MR | Zbl

[18] Ruzicka J., Hansen E. H.: Flow Injection Analysis. Wiley, New York 1988

[19] Samarskii A. A.: The Theory of Difference Schemes. Marcel Dekker, New York – Basel 2001 | MR | Zbl

[20] Schaal S., Atkeson C. G.: Assessing the quality of learned local models, In: Advances in Neural Information Processing Systems 6 (J. Cowan, G. Tesauro, J. Alspector, eds.), Morgan Kaufmann 1994, pp. 160–167

[21] Schaal S., Atkeson C. G.: Constructive incremental learning from only local information. Neural Comput. 10 (1998), 2047–2084 | DOI

[22] Scheller F., Schubert F.: Biosensors, Vol. 7. Elsevier, Amsterdam 1992

[23] Schulmeister T.: Mathematical modelling of the dynamics of amperometric enzyme electrodes. Selective Electrode Rev. 12 (1990), 260–303

[24] Turner A. P. F., Karube, I., Wilson G. S.: Biosensors: Fundamentals and Applications. Oxford University Press, Oxford 1987

[25] Wang Z., Isaksson, T., Kowalski B. R.: New approach for distance measurement in locally weighted regression. Anal. Chem. 66 (1994), 249–260 | DOI

[26] Wollenberger U., Lisdat, F., Scheller F. W.: Frontiers in Biosensorics 2: Practical Applications. Birkhauser Verlag, Basel 1997

[27] Ziegler C., Göpel W., Hämmerle H., Hatt H., Jung G., Laxhuber L., Schmidt H.-L., Schütz S., Vögtle, F., Zell A.: Bioelectronic noses: A status report. Part II. Biosens. Bioelectron. 13 (1998), 539–571