Advertisement

BP Neural Network with Regularization and Sensor Array for Prediction of Component Concentration of Mixed Gas

  • Lin Zhao
  • Jing WangEmail author
  • Xiuyu Chen
Conference paper
  • 2.5k Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10878)

Abstract

BP neural network with L 1 regularization is employed in this paper to solve the volatile organic compounds recognition problems. Recognition performance of neural networks is closely related to number of layers and number of nodes in each layer. The L 1 regularization makes some weights of the neural network approach zero, and helps to determine the nodes number of hidden layer in prediction of component concentrations in a gas mixture. Some rules of hidden layer node pruning are established by combining the function of regularization term, the response characteristics of sensors and composition of sensor array. The number of the hidden layer nodes determined by the pruning method gives better solution, and is close to the number of the hidden layer nodes determined by exhaustive experiments.

Keywords

BP neural network Mixed gas recognition Component concentration L1 regularization 

Notes

Acknowledgement

The authors thank The National Natural Science Foundation of China (61574025) for financial support.

References

  1. 1.
    Koc, H., King, J., Teschl, G., Unterkofler, K., Teschl, S., Mochalski, P., Hinterhuber, H., Amann, A.: The role of mathematical modeling in VOC analysis using isoprene as a prototypic example. J. Breath Res. 5(3), 037102 (2011)CrossRefGoogle Scholar
  2. 2.
    Mirzaei, A., Leonardi, S.G., Neri, G.: Detection of hazardous volatile organic compounds (VOCs) by metal oxide nanostructures-based gas sensors: a review. Ceram. Int. 42(14), 15119–15141 (2016)CrossRefGoogle Scholar
  3. 3.
    Saalberg, Y., Wolff, M.: VOC breath biomarkers in lung cancer. Clin. Chim. Acta 459, 5–9 (2016)CrossRefGoogle Scholar
  4. 4.
    Ayhan, B., Kwan, C., Zhou, J., Kish, L.B., Benkstein, K.D., Rogers, P.H., Semancik, S.: Fluctuation enhanced sensing (FES) with a nanostructured, semiconducting metal oxide film for gas detection and classification. Sens. Actuators B Chem. 188(11), 651–660 (2013)CrossRefGoogle Scholar
  5. 5.
    Kwan, C., Schmera, G., Smulko, J., Kish, L.B., Heszler, P., Granqvist, C.G.: Advanced agent identification at fluctuation-enhanced sensing. IEEE Sens. J. 8, 706–713 (2008)CrossRefGoogle Scholar
  6. 6.
    Li, W., Leung, H., Kwan, C., Linnell, B.R.: E-nose vapor identification based on Dempster–Shafer fusion of multiple classifiers. IEEE Trans. Instrum. Meas. 57(10), 2273–2282 (2008)CrossRefGoogle Scholar
  7. 7.
    Kwan, C., Ayhan, B., Chen, G., Wang, J., Ji, B., Chang, C.I.: A novel approach for spectral unmixing, classification, and concentration estimation of chemical and biological agents. IEEE Trans. Geosci. Remote Sens. 44(2), 409–419 (2006)CrossRefGoogle Scholar
  8. 8.
    Ampuero, S., Bosset, J.O.: The electronic nose applied to dairy products: a review. Sens. Actuators B Chem. 94(1), 1–12 (2003)CrossRefGoogle Scholar
  9. 9.
    Krutzler, C., Unger, A., Marhold, H., Fricke, T., Conrad, T., Schütze, A.: Influence of MOS gas-sensor production tolerances on pattern recognition techniques in electronic noses. IEEE Trans. Instrum. Meas. 61, 276–283 (2012)CrossRefGoogle Scholar
  10. 10.
    Russo, D.V., Burek, M.J., Iutzi, R.M., Mracek, J.A., Hesjedal, T.: Development of an electronic nose sensing platform for undergraduate education in nanotechnology. Eur. J. Phys. 32(32), 675 (2011)CrossRefGoogle Scholar
  11. 11.
    Kim, H., Konnanath, B., Sattigeri, P., Wang, J., Mulchandani, A., Myung, N., Deshusses, M.A., Spanias, A., Bakkaloglu, B.: Electronic-nose for detecting environmental pollutants: signal processing and analog front-end design. Analog Integr. Circ. Sig. Process 70(1), 15–32 (2012)CrossRefGoogle Scholar
  12. 12.
    Hou, C., Li, J., Huo, D., Luo, X., Dong, J., Yang, M., Shi, X.J.: A portable embedded toxic gas detection device based on a cross-responsive sensor array. Sens. Actuators B Chem. 161(1), 244–250 (2012)CrossRefGoogle Scholar
  13. 13.
    Youn, C., Kawashima, K., Kagawa, T.: Concentration measurement systems with stable solutions for binary gas mixtures using two flowmeters. Meas. Sci. Technol. 22(6), 065401 (2011)CrossRefGoogle Scholar
  14. 14.
    Loui, A., Sirbuly, D.J., Elhadj, S., Mccall, S.K., Hart, B.R., Ratto, T.V.: Detection and discrimination of pure gases and binary mixtures using a dual-modality microcantilever sensor. Sens. Actuators, A: Phys. 159(1), 58–63 (2010)CrossRefGoogle Scholar
  15. 15.
    Lv, P., Tang, Z., Wei, G., Yu, J., Huang, Z.: Recognizing indoor formaldehyde in binary gas mixtures with a micro gas sensor array and a neural network. Meas. Sci. Technol. 18(9), 2997 (2007)CrossRefGoogle Scholar
  16. 16.
    Lewis, E., Sheridan, C., O’Farrell, M., King, D., Flanagan, C., Lyons, W.B., Fitzpatrick, C.: Principal component analysis and artificial neural network based approach to analysing optical fibre sensors signals. Sens. Actuators, A: Phys. 136(1), 28–38 (2007)CrossRefGoogle Scholar
  17. 17.
    Bahraminejad, B., Basri, S., Isa, M., Hambali, Z.: Application of a sensor array based on capillary-attached conductive gas sensors for odor identification. Meas. Sci. Technol. 21(21), 085204 (2010)CrossRefGoogle Scholar
  18. 18.
    Ehret, B., Safenreiter, K., Lorenz, F., Biermann, J.: A new feature extraction method for odour classification. Sens. Actuators B Chem. 158(1), 75–88 (2011)CrossRefGoogle Scholar
  19. 19.
    Argyri, A.A., Panagou, E.Z., Tarantilis, P.A., Polysiou, M., Nychas, G.J.E.: Rapid qualitative and quantitative detection of beef fillets spoilage based on fourier transform infrared spectroscopy data and artificial neural networks. Sens. Actuators B Chem. 145(1), 146–154 (2009)CrossRefGoogle Scholar
  20. 20.
    Alquraishi, A.A., Shokir, E.M.: Artificial neural networks modeling for hydrocarbon gas viscosity and density estimation. J. King Saud Univ. – Eng. Sci. 23(2), 123–129 (2011)Google Scholar
  21. 21.
    Song, K., Wang, Q., Liu, Q., Zhang, H., Cheng, Y.: A wireless electronic nose system using a Fe2O3 gas sensing array and least squares support vector regression. Sensors 11(1), 485–505 (2011)CrossRefGoogle Scholar
  22. 22.
    Wu, W., Wang, J., Cheng, M., Li, Z.: Convergence analysis of online gradient method for BP neural networks. Neural Netw. 24(1), 91–98 (2011)CrossRefGoogle Scholar
  23. 23.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 399–421 (1988). Readings in Cognitive SciencezbMATHGoogle Scholar
  24. 24.
    Zhong, H., Miao, C., Shen, Z., Feng, Y.: Comparing the learning effectiveness of BP, ELM, I-ELM, and SVM for corporate credit ratings. Neurocomputing 128(5), 285–295 (2014)CrossRefGoogle Scholar
  25. 25.
    Liang, Y.C., Feng, D.P., Lee, H.P., Lim, S.P., Lee, K.H.: Successive approximation training algorithm for feedforward neural networks. Neurocomputing 42(1), 311–322 (2002)CrossRefGoogle Scholar
  26. 26.
    Stathakis, D.: How many hidden layers and nodes? Int. J. Remote Sens. 30(8), 2133–2147 (2009)CrossRefGoogle Scholar
  27. 27.
    Loone, S.M., Irwin, G.: Improving neural network training solutions using regularization. Neurocomputing 37, 71–90 (2001)CrossRefGoogle Scholar
  28. 28.
    Setiono, R.: A penalty-function approach for pruning feedforward neural networks. Neural Comput. 9(1), 185–204 (1997)CrossRefGoogle Scholar
  29. 29.
    Shao, H., Xu, D., Zheng, G., Liu, L.: Convergence of an online gradient method with inner-product penalty and adaptive momentum. Neurocomputing 77(1), 243–252 (2012)CrossRefGoogle Scholar
  30. 30.
    Zhao, L., Li, X., Wang, J., Yao, P., Akbar, S.A.: Detection of formaldehyde in mixed VOCs gases using sensor array with neural networks. IEEE Sens. J. 16(15), 6081–6086 (2016)CrossRefGoogle Scholar
  31. 31.
    Zhao, L., Wang, J., Li, X.: Identification of formaldehyde under different interfering gas conditions with nanostructured semiconductor gas sensors. Nanomater. Nanotechnol. 5, 1 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Computer Science and TechnologyDalian Neusoft University of InformationDalianPeople’s Republic of China
  2. 2.Faculty of Electronic Information and Electrical EngineeringDalian University of TechnologyDalianPeople’s Republic of China

Personalised recommendations