Simple and rapid instrumental characterization of sensory attributes of virgin olive oil based on the direct coupling headspace-mass spectrometry

Analyzing the Organoleptic Quality of Commercial Extra Virgin Olive Oils: IOC Recognized Panel Tests vs. Electronic Nose

Virgin olive oil (VOO) classification into quality categories determines its labeling and market price. This procedure involves performing a series of chemical-physical analyses and, ultimately, a sensory analysis through the panel test. This work explores the analysis of VOOs quality with an electronic olfactory system (EOS) and examines its abilities using the panel test as a reference. To do this, six commercial olive oils labelled as extra virgin were analyzed with an EOS and classified by three panels recognized by the International Olive Council. The organoleptic analysis of the oils by the panels indicated that most of the oils in the study were in fact not extra virgin. Besides this, the classifications showed inconsistencies between panels, needing statistical treatment to be used as a reference for the EOS training. The analysis of the same oils by the EOS and their subsequent statistical analysis by PCA revealed a good correlation between the first principal component and the olive oil quality from the panels using average scores. It also showed a more consistent classification than the panels. Overall, the EOS proved to be a cheaper, faster, and highly reliable method as a complement to the panel test for the olive oil classification.

Quality Control of Olive Oils Using Machine Learning and Electronic Nose

The adulteration of olive oils can be detected with chemical test. This is very expensive and takes very long time. Thus, this study is focused on reducing both time and cost. For this purpose, the raw data has been collected from olive oils by using an e-nose from different regions in Balikesir in Turkey. This study presents two methods to analyze quality control of olive oils. In the first method, 32 inputs are applied to the classifiers directly. In the second, 32-input collected data are reduced to 8 inputs by Principal Component Analysis. These reduced data as 8 inputs are applied to the classifiers. Different machine learning classifiers such as Naïve Bayesian, K-Nearest Neighbors (k-NN), Linear Discriminate Analysis (LDA), Decision Tree, Artificial Neural Networks (ANN), and Support Vector Machine (SVM) were used. Then performances of these classifiers were compared according to their accuracies.

Food analysis using artificial senses

Nowadays, consumers are paying great attention to the characteristics of food such as smell, taste, and appearance. This motivates scientists to imitate human senses using devices known as electronic senses. These include electronic noses, electronic tongues, and computer vision. Thanks to the utilization of various sensors and methods of signal analysis, artificial senses are widely applied in food analysis for process monitoring and determining the quality and authenticity of foods. This paper summarizes achievements in the field of artificial senses. It includes a brief history of these systems, descriptions of most commonly used sensors (conductometric, potentiometric, amperometic/voltammetric, impedimetric, colorimetric, piezoelectric), data analysis methods (for example, artificial neural network (ANN), principal component analysis (PCA), model CIE L*a*b*), and application of artificial senses to food analysis, in particular quality control, authenticity and falsification assessment, and monitoring of production processes.

Invited review article: an odor-sensing system--powerful technique for foodstuff studies

This work examines gas sensor array technology combined with multivariate data processing methods and demonstrates a promising potential for rapid, non-destructive analysis of food. Main attention is focused on detailed description of sensor used in e-nose instruments, construction, and principle of operation of these systems. Moreover, this paper briefly reviews the progress in the field of artificial olfaction and future trends in electronic nose technology, namely, e-nose based on mass spectrometry. Further discussion concerns a comparison of artificial nose with gas chromatography-olfactometry and the application of e-nose instruments in different areas of food industry.