Analysis of the Response Signals of an Electronic Nose Sensor for Differentiation between Fusarium Species

Abstract

Fusarium is a genus of fungi found throughout the world. It includes many pathogenic species that produce toxins of agricultural importance. These fungi are also found in buildings and the toxins they spread can be harmful to humans. Distinguishing Fusarium species can be important for selecting effective preventive measures against their spread. A low-cost electronic nose applying six commercially available TGS-series gas sensors from Figaro Inc. was used in our research. Different modes of operation of the electronic nose were applied and compared, namely, gas adsorption and desorption, as well as modulation of the sensor’s heating voltage. Classification models using the random forest technique were applied to differentiate between measured sample categories of four species: F. avenaceum, F. culmorum, F. greaminarum, and F. oxysporum. In our research, it was found that the mode of operation with modulation of the heating voltage had the advantage of collecting data from which features can be extracted, leading to the training of machine learning classification models with better performance compared to cases where the sensor’s response to the change in composition of the measured gas was exploited. The optimization of the data collection time was investigated and led to the conclusion that the response of the sensor at the beginning of the heating voltage modulation provides the most useful information. For sensor operation in the mode of gas desorption/absorption (i.e., modulation of the gas composition), the optimal time of data collection was found to be longer.

Analysis of Wheat Grain Infection by Fusarium Mycotoxin-Producing Fungi Using an Electronic Nose, GC-MS, and qPCR

“…We can observe in this figure that the overall performance of the models using such features as predictors exhibits better performance than those based on the data collected during the adsorption phase. We observed similar results in one of our previous experiments [31].…”

“…This is the case with the Figaro Inc. sensors [ 32 ] used in our device. However, there are many research studies [ 24 , 25 , 31 , 38 , 39 ] that report on electronic noses based on the Figaro TGS series sensors using the possibility of gas detection in the sensor temperature modulation framework. An important aspect of operating the electronic nose in this mode is the protocol choice for the sensor heating modulation profile.…”

“…In our previous research [ 24 , 25 , 31 ], we used a rectangular form of sensor heating voltage modulation that uses a single repetition of the voltage change step [ 24 ]. We have verified that voltage modulation with a relatively small voltage drop from the nominal sensor heater is the correct choice and allows us to perform better in classifying samples using electronic nose data.…”

“…Some studies have shown that the electronic nose sensor captures the most meaningful information that can be used to differentiate between sample categories right at the beginning of the transition phase [ 31 , 62 ]. This is a very different approach from many other research studies and applications of electronic noses, where the steady state after the completion of the transient phase of the response is used for classification.…”

“…In Figure 2 , one can see a photo of the electronic nose device used, together with two samples of measured grain in Petri dishes. Details of the electrical circuit [ 24 ] of the electronic nose and the construction of the sensor chamber and operation principle [ 25 , 31 ] were described in previous papers.…”