An artificial class modelling approach to identify the most largely diffused cultivars of sweet cherry (Prunus avium L.) in Italy

The nutritional and commercial value of the sweet cherry provides it a great economic importance in Italy. The aim of this study was to characterize 35 sweet cherry cultivars and one of sour cherry, by analyzing values of different pomological and nutraceutical traits, identifying cultivars with antioxidant activity and total anthocyanins content closest to those present in literature for Ferrovia (largely diffused in Italy). To this goal, a multivariate metric index through the Soft Independent Modeling of Class Analogy analyzing an artificial dataset and testing a real one, two hierarchical clustering and a principal component analysis, were performed. The multivariate analyses result simultaneously investigated all the variables highlighting cvs. Sylvia, Graffione nero Col di Mosso, Ferrovia, Mora della Punta, Bianchetta Nuchis and Sandra to be more similar to literature data of Ferrovia. This matrix index was a useful tool, to select the most commercial promising varieties.

Estimating Some Physical Properties of Sour and Sweet Cherries Based on Combined Image Processing and AI Techniques

Physical properties of agricultural products are considered as important factors in optimization of storage conditions, packaging, transportation, water adsorption/desorption, heat, pesticides, and foodstuff moving out and also their breathing. This paper presents a time and cost economizing method to determine these important attributes of sour and sweet cherries by combining image processing and two common artificial intelligence techniques, artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS). The measuring technique consisted of a charge-coupled device camera for image acquisition, fluorescent illuminants, capture card, and MATLAB for image analysis. Several networks were designed, trained, and generalized with a back-propagation algorithm using “trainlm” as training function. Several ANFIS models were designed with different number and type of membership functions (MFs) for each input. Generally, “gaussian” and “pi-shaped” MFs showed better results for estimating output variables among others. Considering statistical analysis, ANFIS showed better results than ANN.