Power Scaling of Chemiresistive Sensor Array Data for Odor Classification

Abstract

The steady state responses of chemical sensors like the tin-oxide and composite conducting polymer sensors exhibit power law dependency on the vapor concentration. In this research, it is shown that linearization of measured (raw) sensor signals by an inverse power scaling improves class separability in feature space, hence the classification efficiency of electronic noses based on these sensors. The follow up data processing is done by dimensional autoscaling, principal component analysis and backpropagation neural network. The data from three tin-oxide sensor array and one CPC sensor array collected from published sources are utilized. It is found that by preprocessing the data according to the suggested power law improves class separability and classification efficiency. An improvement of 14% to 16% is obtained for tin-oxide sensor array and of 33% for conducting polymer sensor array are obtained. The approximate values of the scaling exponents were first deduced as prompted by the sensor response models, and then one adjust were done empirically.

Improving the Performance of Gas Sensor Systems with Advanced Data Evaluation, Operation, and Calibration Methods

“…Sensor arrays can be comprised of different sensor types and technologies to combine their individual benefits. They have been widely used to detect, for example, fires [46], [47], odors [16], [48], and volatile organic compounds (VOCs) [49], [50].…”

“…If only one hyperparameter is varied, the resulting errors are plotted as in Figure 3. 16. For two hyperparameters, the calibration, validation, and prediction errors can be plotted as three-dimensional surface, and for more than two, the remaining ones must be set to fixed values for visualization.…”

Optimized KPCA method for chemical vapor class recognition by SAW sensor array response analysis

“…Preprocessing filters chemical vapor distinguishing pattern from non-distinguishing background contributions by scaling, normalization and denoising [3]. In this context our earlier studies [4,5] establishes a link between sensor model and data pre-processing methods. Feature extraction and selection is another significant step of pattern recognition unit accountable for the chemical vapor recognition efficiency of E-nose.…”

Low Pass Filter Model for Chemical Sensors in Response to Gases and Odors

“…Many articles on this subject have been published over the last few years, mainly in relation to the food and beverage industry, but also concerning environmental, agricultural, medical topics and automotive industry, among others. However, the number of studies dedicated to nose based odor originality systems is still very limited, probably due to the complexity of their matrices (Wongchoosuk et al, 2009;Myrick et al, 2009;Tang et al, 2010;Jha and Yaava, 2011;Bucak and Karlik, 2009;Huang and Wan, 2009;Zeng et al, 2009;Lange et al, 2009;Vera et al, 2011;Song et al, 2011;Cole et al, 2011;Im et al, 2011;Baldwin et al, 2011;Huan et al, 2011;Phaisangittisagul and Nagle, 2011).…”