Sensor drift is currently the most challenging problem in gas sensing. We propose a novel ensemble method with dynamic weights based on fitting (DWF) to solve the gas discrimination problem, regardless of the gas concentration, with high accuracy over extended periods of time. The DWF method uses a dynamic weighted combination of support vector machine (SVM) classifiers trained by the datasets that are collected at different time periods. In the testing of future datasets, the classifier weights are predicted by fitting functions, which are obtained by the proper fitting of the optimal weights during training. We compare the performance of the DWF method with that of competing methods in an experiment based on a public dataset that was compiled over a period of three years. The experimental results demonstrate that the DWF method outperforms the other methods considered. Furthermore, the DWF method can be further optimized by applying a fitting function that more closely matches the variation of the optimal weight over time.
References
[1]
Gardner, J.W.; Bartlett, P.N. Electronic Noses: Principles and Applications; Oxford University Press: New York, NY, USA, 1999; Volume 233.
[2]
Artursson, T.; Ekl？v, T.; Lundstr？m, I.; Ma？rtensson, P.; Sj？str？m, M.; Holmberg, M. Drift correction for gas sensors using multivariate methods. J. Chemom. 2000, 14, 711–723.
[3]
Romain, A.C.; Nicolas, J. Long term stability of metal oxide-based gas sensors for e-nose environmental applications: An overview. Sens. Actuators B Chem. 2010, 146, 502–506.
[4]
Romain, A.C.; André, P.; Nicolas, J. Three years experiment with the same tin oxide sensor arrays for the identification of malodorous sources in the environment. Sens. Actuators B Chem. 2002, 84, 271–277.
[5]
G？pel, W. New materials and transducers for chemical sensors. Sens. Actuators B Chem. 1994, 18, 1–21.
[6]
Yamazoe, N. New approaches for improving semiconductor gas sensors. Sens. Actuators B 1991, 5, 7–19.
[7]
Roth, M.; Hartinger, R.; Faul, R.; Endres, H.E. Drift reduction of organic coated gas-sensors by temperature modulation. Sens. Actuators B Chem. 1996, 36, 358–362.
[8]
Vergara, A.; Llobet, E.; Brezmes, J.; Ivanov, P.; Cané, C.; Gràcia, I.; Vilanova, X.; Correig, X. Quantitative gas mixture analysis using temperature-modulated micro-hotplate gas sensors: Selection and validation of the optimal modulating frequencies. Sens. Actuators B Chem. 2007, 123, 1002–1016.
[9]
Pardo, M.; Faglia, G.; Sberveglieri, G.; Corte, M.; Masulli, F.; Riani, M. Monitoring reliability of sensors in an array by neural networks. Sens. Actuators B Chem. 2000, 67, 128–133.
[10]
Padilla, M.; Perera, A.; Montoliu, I.; Chaudry, A.; Persaud, K.; Marco, S. Fault Detection, Identification, and Reconstruction of Faulty Chemical Gas Sensors under Drift Conditions, Using Principal Component Analysis and Multiscale-PCA. Proceedings of IEEE The 2010 International Joint Conference on Neural Networks, Barcelona, Spain, 18–23 July 2010; pp. 1–7.
[11]
Fonollosa, J.; Vergara, A.; Huerta, R. Algorithmic mitigation of sensor failure: Is sensor replacement really necessary? Sens. Actuators B Chem 2013, 183, 211–221.
[12]
Lee, D.S.; Jung, H.Y.; Lim, J.W.; Lee, M.; Ban, S.W.; Huh, J.S.; Lee, D.D. Explosive gas recognition system using thick film sensor array and neural network. Sens. Actuators B Chem. 2000, 71, 90–98.
[13]
Polikar, R.; Shinar, R.; Udpa, L.; Porter, M.D. Artificial intelligence methods for selection of an optimized sensor array for identification of volatile organic compounds. Sens. Actuators B Chem. 2001, 80, 243–254.
[14]
Srivastava, A. Detection of volatile organic compounds (VOCs) using SnO2 gas-sensor array and artificial neural network. Sens. Actuators B Chem. 2003, 96, 24–37.
[15]
Ciosek, P.; Brzózka, Z.; Wróblewski, W. Classification of beverages using a reduced sensor array. Sens. Actuators B Chem. 2004, 103, 76–83.
[16]
Shi, X.; Wang, L.; Kariuki, N.; Luo, J.; Zhong, C.J.; Lu, S. A multi-module artificial neural network approach to pattern recognition with optimized nanostructured sensor array. Sens. Actuators B Chem. 2006, 117, 65–73.
[17]
Szecowka, P.; Szczurek, A.; Licznerski, B. On reliability of neural network sensitivity analysis applied for sensor array optimization. Sens. Actuators B Chem. 2011, 157, 298–303.
[18]
Xu, Z.; Shi, X.; Wang, L.; Luo, J.; Zhong, C.J.; Lu, S. Pattern recognition for sensor array signals using fuzzy ARTMAP. Sens. Actuators B Chem. 2009, 141, 458–464.
[19]
Distante, C.; Ancona, N.; Siciliano, P. Support vector machines for olfactory signals recognition. Sens. Actuators B Chem. 2003, 88, 30–39.
[20]
Ge, H.; Liu, J. Identification of gas mixtures by a distributed support vector machine network and wavelet decomposition from temperature modulated semiconductor gas sensor. Sens. Actuators B Chem. 2006, 117, 408–414.
[21]
Gualdrón, O.; Brezmes, J.; Llobet, E.; Amari, A.; Vilanova, X.; Bouchikhi, B.; Correig, X. Variable selection for support vector machine based multisensor systems. Sens. Actuators B Chem. 2007, 122, 259–268.
Gao, D.; Chen, M.; Yan, J. Simultaneous estimation of classes and concentrations of odors by an electronic nose using combinative and modular multilayer perceptrons. Sens. Actuators B Chem. 2005, 107, 773–781.
[24]
Gao, D.; Chen, W. Simultaneous estimation of odor classes and concentrations using an electronic nose with function approximation model ensembles. Sens. Actuators B Chem. 2007, 120, 584–594.
[25]
Shi, M.; Brahim-Belhouari, S.; Bermak, A.; Martinez, D. Committee Machine for Odor Discrimination in Gas Sensor Array. Proceedings of 11th International Symposium on Olfaction and Electronic Nose, Barcelona, Spain, 13–15 April 2005; pp. 74–76.
[26]
Vergara, A.; Vembu, S.; Ayhan, T.; Ryan, M.A.; Homer, M.L.; Huerta, R. Chemical gas sensor drift compensation using classifier ensembles. Sens. Actuators B Chem. 2012, 166-167, 320–329.
[27]
Wang, H.; Fan, W.; Yu, P.S.; Han, J. Mining Concept-Drifting Data Streams Using Ensemble Classifiers. Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, 24–27 Auguest; 2003; pp. 226–235.
[28]
Amini, A.; Bagheri, M.A.; Montazer, G. Improving gas identification accuracy of a temperature-modulated gas sensor using an ensemble of classifiers. Sens. Actuators B Chem. 2012. in press.
[29]
Kadri, C.; Tian, F.; Zhang, L.; Li, G.; Dang, L.; Li, G. Neural network ensembles for online gas concentration estimation using an electronic nose. Int. J. Comput. Sci. Issues 2013, 10, 129–135.
[30]
Muezzinoglu, M.K.; Vergara, A.; Huerta, R.; Rulkov, N.; Rabinovich, M.I.; Selverston, A.; Abarbanel, H.D. Acceleration of chemo-sensory information processing using transient features. Sens. Actuators B Chem. 2009, 137, 507–512.
