Fruit ripeness monitoring using an Electronic Nose

In this work, the use of an Electronic Nose for non-destructively monitoring the fruit ripening process is presented. Based on a tin oxide chemical sensor array and neural network-based pattern recognition techniques, the olfactory system designed is able to classify fruit samples into three different states of ripeness (green, ripe and overripe) with very good accuracy. Measures done with peaches and pears show a success rate above 92%, while a slightly worse accuracy is reached with apples. An additional feature of the system is its ability to accurately predict the number of days the fruit has been in storage since harvest. Measures done with peaches show a maximum error of 1 day.