N. El Bari

E-Nose and e-Tongue combination for improved recognition of fruit juice samples

There are many important challenges related to food security analysis by application of chemical and electrochemical sensors. One critical parameter is the development of reliable tools, capable of performing an overall sensory analysis. In these systems, as much information as possible is required in relation to smell, taste and colour. Here, we investigated the possibility of using a multisensor data fusion approach, which combines an e-Nose and an e-Tongue, adept in generating combined aroma and taste profiles. In order to shed light on this concept, classification of various Tunisian fruit juices using a low-level of abstraction data fusion technique was attempted. Five tin oxide-based Taguchi Gas Sensors were applied in the e-Nose instrument and the e-Tongue was designed using six potentiometric sensors. Four different commercial brands along with eleven fruit juice varieties were characterised using the e-Nose and the e-Tongue as individual techniques, followed by a combination of the two together. Applying Principal Component Analysis (PCA) separately on the respective e-Nose and e-Tongue data, only few distinct groups were discriminated. However, by employing the low-level of abstraction data fusion technique, very impressive findings were achieved. The Fuzzy ARTMAP neural network reached a 100% success rate in the recognition of the eleven-fruit juices. Therefore, data fusion approach can successfully merge individual data from multiple origins to draw the right conclusions that are more fruitful when compared to the original single data. Hence, this work has demonstrated that data fusion strategy used to combine e-Nose and e-Tongue signals led to a system of complementary and comprehensive information of the fruit juices which outperformed the performance of each instrument when applied separately.

Instrumental assessment of red meat origins and their storage time using electronic sensing systems

Objective and rapid electronic sensing systems for distinguishing among meat species and identifying the degree of spoilage have been developed. A metal oxide sensor-based electronic nose system consisting of six sensors is designed and used to analyze the headspace emanating from beef, goat and sheep meats stored at 4 °C. A rapid, non-destructive technique based on the electronic tongue system formed by seven working electrodes is also applied and used to analyse the fingerprint of the electrochemical compounds of the three meat samples. Data analysis is performed by two pattern recognition methods: Principal Component Analysis (PCA) and Support Vector Machines (SVMs). Discrimination and classification function analyses are performed on the response of the electronic nose and electronic tongue systems to each of the three red meats. The obtained results show that the three red meats can be distinguished and the number of days spent in cold storage can be identified.

Application of a portable electronic nose device to discriminate and identify cheeses with known percentages of cow's and goat's milk

A portable electronic nose comprising an array of 6 metal oxide semiconductor sensors was developed and used, jointly with pattern recognition methods, to discriminate and identify several cheeses made from goats, cows milk and their mixtures. Principal Component Analysis (PCA) was used to visualize the different categories of aroma profiles and Multivariate Analysis of Variance (MANOVA) was performed to test the significance of the differences between cheeses groups. Database was then elaborated using supervised classifiers such as Discriminant Factor Analysis (DFA) with leave one out approach. The results indicate that the portable electronic nose device can clearly and rapidly distinguish between cows milk cheese, goats milk cheese and cheeses containing variable amounts of cows and goats milk. So, this system can be used in order to avoid fraud and to fulfill customer expectations.

Detection of seasonal allergic rhinitis from exhaled breath VOCs using an electronic nose based on an array of chemical sensors

In this study, we investigate for the first time the ability of an electronic nose (E-nose) based on an array of chemical sensors to discriminate between breath Volatile Organic Compounds (VOCs) that characterize patients with Seasonal Allergic Rhinitis (SAR) and healthy states. To reach this aim, multivariate analysis including Principal Component Analysis (PCA), Hierarchical Cluster Analysis (HCA) and Support Vector Machines (SVMs) were applied for database as an alternative tools for the resolution of complex classification situations. The preliminary results reveal that VOC-patterns of exhaled breath were accurately discriminated patients with SAR from healthy controls. These findings indicate that the E-nose may succeed as a non-invasive diagnostic tool, low cost and rapid technique for breath analysis.

Geographical classification of Virgin Olive Oils by combining the electronic nose and tongue

Although the great interest of development of performed gas and liquid sensors, lack of cross-sensitivity still remains the major drawback of electronic sensing systems such as electronic nose and tongue. We propose here an approach aimed at overcoming this shortcoming. So a performed data fusion method of electronic nose and tongue was used in order to classify five Virgin Olive Oils (VOOs) picked up from five Moroccan geographical areas. The electronic nose instrument consists of five commercial available MOS TGS gas sensors and the electronic tongue was designed using four voltammetric electrodes. Two techniques, i.e., Principal Component Analysis (PCA) and Support Vector Machines (SVMs) were used to develop classification models using as inputs specific features extracted from the collected sensor signals. Great enhancement in successful discrimination between all VOOs was achieved when compared to the individual systems due to a performed low-level of abstraction data fusion.

Determination of safranal concentration in saffron samples by means of VE-Tongue, SPME-GC-MS, UV-Vis Spectrophotometry and multivariate analysis

An experimental investigation has been carried out to characterize and discriminate seven saffron samples and to verify their declared geographical origin using a voltammetric electronic tongue (VE-tongue). The ability of multivariable analysis methods such as Principal Component Analysis (PCA), Hierarchical Cluster Analysis (HCA) to classify the saffron samples according to their geographical origin have been investigated. A good discrimination has reached using PCA and HCA in the VE-tongue characterization case. Furthermore, cross validation and Partial Least Square (PLS) techniques were applied in order to build suitable management and prediction models for the determination of safranal concentration in saffron samples based on SPME-GC-MS and UV-Vis Spectrophotometry. The obtained results reveals that some relationships were established between the VE-tongue signal, SPME-GC-MS and UV-Vis spectrophotometry methods to predict safranal concentration levels in saffron samples by using the PLS model. In the light of these results, we can say that the proposed electronic system offer a fast, simple and efficient tool to recognize the declared geographical origin of the saffron samples.