Chocolate Classification by an Electronic Nose with Pressure Controlled Generated Stimulation

Abstract

In this work, we will analyze the response of a Metal Oxide Gas Sensor (MOGS) array to a flow controlled stimulus generated in a pressure controlled canister produced by a homemade olfactometer to build an E-nose. The built E-nose is capable of chocolate identification between the 26 analyzed chocolate bar samples and four features recognition (chocolate type, extra ingredient, sweetener and expiration date status). The data analysis tools used were Principal Components Analysis (PCA) and Artificial Neural Networks (ANNs). The chocolate identification E-nose average classification rate was of 81.3% with 0.99 accuracy (Acc), 0.86 precision (Prc), 0.84 sensitivity (Sen) and 0.99 specificity (Spe) for test. The chocolate feature recognition E-nose gives a classification rate of 85.36% with 0.96 Acc, 0.86 Prc, 0.85 Sen and 0.96 Spe. In addition, a preliminary sample aging analysis was made. The results prove the pressure controlled generated stimulus is reliable for this type of studies.

Roadmap of cocoa quality and authenticity control in the industry: A review of conventional and alternative methods

“…An electronic nose/GC–MS system combined with artificial neural network has been used for determining roasting degree in cocoa beans (Tan & Kerr, ). Electronic nose combined with pressure control–generated stimulation has been used in chocolate classification (Valdez & Gutiérrez, ). The hyperspectral image analysis has been used for cocoa bean quality assessments (Soto et al., ) and to predict the fermentation index, polyphenol content, and antioxidant activity in single cocoa beans (Caporaso, Whitworth, Fowler, & Fisk, ).…”

Bacterial Infection Potato Tuber Soft Rot Disease Detection Based on Electronic Nose

“…10-fold cross validation was used for training and testing. Artificial neural network (RBF NN) and support vector machine (SVM) were utilized for performance analysis, and the difference of the estimation and the system availability were validated [21,22]. An artificial neural network is widely used in pattern recognition due to its strong nonlinear mapping ability and superior fault tolerance.…”

Application of an olfactory system to detect and distinguish bitter chocolates with different percentages of cocoa

“…Sensory evaluation is performed at standard conditions by trained and experienced people, on the appearance, smoothness, and glossiness of the surface, uniformity, dimensions, taste, texture, and size of coffee beans, and their reactions on the evaluator's tongue. Chemical evaluation involves PH measuring, ash analysis, and moisture determination, which should not exceed 1.5% (a greater amount would have undesirable effects on the appearance, physical properties, color, and taste) as well as the amount and type of fat, fatty acids, fat corruption, sugar spectrum, melting point, soap number, and iodine number for cocoa (Valdez & Gutiérrez, ). Some studies showed that the alcohols are the main compounds in chocolate mixtures (Bastos et al, ; Megías‐Pérez, Grimbs, D'Souza, Bernaert, & Kuhnert, ; Saputro, Van de Walle, Hinneh, Van Durme, & Dewettinck, ).…”

“…In a study similar to ours, the researchers studied the ability of the olfaction machine to classify various types of chocolate (bitter, semibitter, and milk chocolate) under controlled pressure. The results of that study demonstrated that the olfaction machine can be applied as a reliable, fast and low-cost method in conducting similar studies (Valdez & Gutiérrez, 2016). Since one of the important evaluations in the chocolate industry is the determination of the amount and percentage of cocoa in bitter chocolate, the present study examines the possibility of using the olfaction machine system to distinguish and classify different cocoa percentages (78, 85, and 96%) in chocolate.…”