|
Abstract
|
Sorting of agricultural products is one of the core research areas in the field of agricultural postharvest engineering. This paper presents an algorithm based method to sort four varieties of almond (Yalda, France, Shokofeh, and Shahrood 15) using impulse acoustic signals, selected features and rules generated from a decision tree, and fuzzy inference system. Two impact plates (Plywood and Stainless steel) and two fall heights (14 cm and 24 cm) were considered as test conditions. Results showed that the best decision tree will be obtained when impact plate is Stainless steel and fall height is 24 cm. In this condition, the fuzzy inference engine performance was found to be encouraging and its accuracy in the classification of almond varieties was 84.16%.
|