Signal and Data Processing for Machine Olfaction and Chemical Sensing: A Review

Abstract

Signal and data processing are essential elements in electronic noses as well as in most chemical sensing instruments. The multivariate responses obtained by chemical sensor arrays require signal and data processing to carry out the fundamental tasks of odor identification (classification), concentration estimation (regression) and grouping of similar odors (clustering). In the last decade, important advances have shown that proper processing can improve the robustness of the instruments against diverse perturbations, namely, environmental variables, background changes, drift, etc. This article reviews the advances made in recent years in signal and data processing for machine olfaction and chemical sensing. Figure 3. Evolution of the pattern of response of a SB31 sensor from FIS Japan when the heated voltage is scanned due to changes in the gas composition (mixture of CO and CH4).One of the problems that affect sensor array instruments is the lack of reproducibility in the sensor signals when technologically identical devices are exposed to a chemical under the exact same conditions. Figure 4 shows the voltage waveforms of 11 temperature modulated Metal Oxide Sensors. It is obvious that the pattern of response is slightly different for both analytes, but the waveform scatter is also remarkable, which poses problems during sensor replacement and calibration transfer scenarios (see section 3).

Learning pattern recognition and decision making in the insect brain

“…It is remarkable that when one asks engineers what problems need to be solved in pattern recognition of gases, they propose feature extraction methods to interpret the spatio-temporal signal form the sensors and a classifier and regressor to discriminate between gases and to estimate the concentrations [165,166,167]. The bioinspiration is not present in these arguments but yet the insect olfactory system appears to be doing just that.…”

Bioinspired early detection through gas flow modulation in chemo-sensory systems

“…To this purpose we employed partial least squares (PLS) regression method, being one of the standard tools in chemometics [42] and machine olfaction [43,44]. In particular, we chose the canonical power partial least squares (CPPLS) approach for gaining computational efficiency, among others [45,46].…”

Analysis of pattern recognition and dimensionality reduction techniques for odor biometrics

“…Once the samples are collected, the problem of odor identification can be tackled from the point of view of machine learning [36,20]. In particular, the problem of subject identification from their body odor can be identified with a supervised multi-class classification task [4] in which each class corresponds to a subject and the classification algorithm (also known as classifier or learning algorithm) must find the dependences between the input data and the classes.…”