Electronic nose and neural network use for the classification of honey

Abstract

-Seventy samples of honey of different geographical and botanical origin were analysed with an electronic nose. The instrument, equipped with 10 Metal Oxide Semiconductor Field Effect Transistors (MOSFET) and 12 Metal Oxide Semiconductor (MOS) sensors, was used to generate a pattern of the volatile compounds present in the honey samples. The sensor responses were evaluated by Principal Component Analysis (PCA) and Artificial Neural Network (ANN). Good results were obtained in the classification of honey samples by using a neural network model based on a multilayer perceptron that learned using a backpropagation algorithm. The methodology is simple, rapid and results suggest that the electronic nose could be a useful tool for the characterisation and control of honey.honey / electronic nose / classification / neural network analysis

Physico-chemical methods for the characterisation of unifloral honeys: a review

“…Many applications have been reported for other foods, most of them using specific sensors. The electronic nose has been successfully used for the classification of Swiss unifloral honeys (Ampuero et al, 2004;Benedetti et al, 2004).…”

Comparison of an Electronic Nose with the Sensory Evaluation of Food Products by “Triangle Test”

“…Recently a great number of application were reported in literature that use the so called "electronic nose" (e-nose) [2] to evaluate the odor pattern of different foodstuff: to dairy products [3], as quality estimation of ground meat [4], evaluation of the shelf life of fresh vegetables [5], estimation of fish freshness [6], classification of honey of different botanic and geographic origin [7], to follow beer production [8].…”

Fuzzy Supervised Neural Training Algorithm for Varied Diabetes Recognition

“…By contrast with Supervised Learning or Reinforcement Learning, there are no explicit target outputs or environmental evaluations associated with each input; rather the unsupervised learner brings to bear prior biases as to what aspects of the structure of the input should be captured in the output. Unsupervised learning is important since it is likely to be much more common in the brain than supervised learning (Benedetti et al, 2005).…”