Wine quality rapid detection using a compact electronic nose system: Application focused on spoilage thresholds by acetic acid

Abstract

It is crucial for the wine industry to have methods like electronic nose systems (E-Noses) for real-time monitoring thresholds of acetic acid in wines, preventing its spoilage or determining its quality. In this paper, we prove that the portable and compact self-developed E-Nose, based on thin film semiconductor (SnO2) sensors and trained with an approach that uses deep Multilayer Perceptron (MLP) neural network, can perform early detection of wine spoilage thresholds in routine tasks of wine quality control. To obtain rapid and online detection, we propose a method of rising-window focused on raw data processing to find an early portion of the sensor signals with the best recognition performance. Our approach was compared with the conventional approach employed in E-Noses for gas recognition that involves feature extraction and selection techniques for preprocessing data, succeeded by a Support Vector Machine (SVM) classifier.The results evidence that is possible to classify three wine spoilage levels in 2.7 seconds after the gas injection point, implying in a methodology 63 times faster than the results obtained with the conventional approach in our experimental setup.

Electronic nose dataset for detection of wine spoilage thresholds

“…O-NOSE performs the measurement process in three stages: concentration, data acquisition (the recorded data corresponds to 180 seconds with 18.5 Hz sample rate) and purge [1] . Each measurement corresponds to the time-dependent output voltages of each gas sensor converted to resistance values according to the voltage-divider scheme [5] and the corresponding load resistor ( ).…”

“…To obtain spoiled samples, 13 of the 22 bottles were randomly selected and left opened for six months before starting the measurements (low-quality LQ wines). Besides, four bottles were opened two weeks before beginning the data collection (average-quality AQ wines), and the remaining five bottles were opened at the starting time of each measurement (high-quality HQ wines) [1] .…”

“…To ensure the repeatability of the experiments using O-NOSE, we collected between 10 and 11 samples of 1mL of each wine bottles; and between 10 and 12 of the ethanol samples at their different concentrations. In this way, the database contains 235 measurements of wines divided into three groups: high quality (HQ), average quality (AQ) and low quality (LQ), with 51, 43, and 141 measurements, respectively, and 65 ethanol measurements [1] .…”

Bio-Inspired Strategies for Improving the Selectivity and Sensitivity of Artificial Noses: A Review

“…This solution is interesting, since it does not require feature extraction from the data. Rodriguez et al [176] achieved a similar result with a deep multilayer perceptron neural network to identify wine spoilage in less than three seconds. Munoz-Mata et al [177] held the same reasoning with QCM sensors.…”

Collaborative Analysis on the Marked Ages of Rice Wines by Electronic Tongue and Nose based on Different Feature Data Sets

“…Electronic tongue (e-tongue) and electronic nose (e-nose) offer a fast, low cost, and non-destructive alternative to detecting samples without sample preparation, [13][14][15]. E-tongue (e-nose) can simulate human gustatory (olfactory) evaluation process to evaluate food qualities via 'taste' (smell) information [16][17][18][19], and both the instrument has been used successfully for evaluating the wine quality [20][21][22][23][24]. Although the e-tongue and e-nose were not used for detecting the quality of Chinese rice wine, the successful usage of the instruments indicated that e-tongue and e-nose have technique potential for identifying the wine age of rice wines.…”