Investigating the Effect of Packaging Conditions on the Properties of Peeled Garlic by Using Artificial Neural Network (ANN)

Abstract

This study investigated the effect of packaging conditions on the properties of peeled garlic during storage, and the results have been evaluated using statistical analysis and artificial neural network (ANN). Peeled garlic was packed with polyethylene (PE) film and polyethylene film equipped with nanoparticles (2% nanoclay) and filled into the packages using ambient and modified atmospheres (1% O2, 5% CO2 and 94% N2). A group of packages was also packed under vacuum conditions. The packaged samples were stored at 25°C, 4°C and −18°C for 35 days. Colour indices (a*, b* and L*), chemical properties (pH and TSS) and mechanical properties (Fmax and Emod) of the peeled garlic were measured during the storage time. The final results showed that the use of nanofilm and modified atmosphere had a positive effect on maintaining the quality of peeled garlic during the storage. On the other hand, the temperature changes showed that the freezing temperature had a negative effect on the garlic quality (properties) during the storage period. The statistical analysis results of the data showed the significant effect of treatments and their interactions on properties at levels of 1% and 5%. The results of ANN showed that the peeled garlic properties (physical, chemical and mechanical) could be predicted with the highest performance scores. The most successful ANN models were identified for each property, with the Trainbr learning algorithm and Tansig transfer function yielding the highest prediction scores for physical (R2 > 0.90) and chemical properties; on the other hand, Logsig was most successful for mechanical properties (R2 > 0.84).