SAW Sensor’s Frequency Shift Characterization for Odor Recognition and Concentration Estimation

In this paper, we propose an approach to determine the time constants and the amplitudes of the mass loading effect and of the viscoelastic contribution of SAW sensor’s frequency shift. This approach consists in optimizing a function of these parameters, which is independent of the concentration profile. We experimentally establish in laboratory conditions ( $T$ = 22 °C), on a data set composed of seven different gases, that these features are suitable for chemical compounds identification. In particular, we obtain a higher classification rate than the traditional amplitudes of the signals during the steady state, and we show that the classification success rate can be increased by using both of them in conjunction with a feature subset selection heuristic. We also propose a method based on deconvolution and kernel regression to estimate the temporal concentration profile.

[1]  Stephanie Thalberg,et al.  Acoustic Wave Sensors Theory Design And Physico Chemical Applications , 2016 .

[2]  Philippe Bergonzo,et al.  New sensitive coating based on modified diamond nanoparticles for chemical SAW sensors , 2011 .

[3]  E. Capelas de Oliveira.  On generating functions , 1992 .

[4]  Kaare Brandt Petersen,et al.  The Matrix Cookbook , 2006 .

[5]  Ganesh Kumar Mani,et al.  Electronic noses for food quality : a review , 2015 .

[6]  R. Tyrrell Rockafellar,et al.  Lagrange Multipliers and Optimality , 1993, SIAM Rev..

[7]  Thaddeus A. Roppel,et al.  Improved chemical identification from sensor arrays using intelligent algorithms , 2001, SPIE Optics East.

[8]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[9]  H. Keselman,et al.  Backward, forward and stepwise automated subset selection algorithms: Frequency of obtaining authentic and noise variables , 1992 .

[10]  Xin Yao,et al.  Fast Evolution Strategies , 1997, Evolutionary Programming.

[11]  Calogero Pace,et al.  On the Use of the SVM Approach in Analyzing an Electronic Nose , 2007, 7th International Conference on Hybrid Intelligent Systems (HIS 2007).

[12]  Elizabeth A. Baldwin,et al.  Electronic Noses and Tongues: Applications for the Food and Pharmaceutical Industries , 2011, Sensors.

[13]  Ayten Atasoy,et al.  Multiclass classification of n-butanol concentrations with k-nearest neighbor algorithm and support vector machine in an electronic nose , 2012 .

[14]  Kilian Q. Weinberger,et al.  Metric Learning for Kernel Regression , 2007, AISTATS.

[15]  J. Reibel,et al.  New miniaturized SAW-sensor array for organic gas detection driven by multiplexed oscillators , 2000 .

[16]  Yashoda Parmar,et al.  Investigations on the origin of mass and elastic loading in the time varying distinct response of ZnO SAW ammonia sensor , 2012 .

[17]  I ScottKirkpatrick.  Optimization by Simulated Annealing: Quantitative Studies , 1984 .

[18]  Alan V. Oppenheim,et al.  Discrete-time Signal Processing. Vol.2 , 2001 .

[19]  Frans van den Bergh,et al.  An analysis of particle swarm optimizers , 2002 .

[20]  Doron Lancet,et al.  A feature extraction method for chemical sensors in electronic noses , 2003 .

[21]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.