Machine and Deep Learning in the Evaluation of Selected Qualitative Characteristics of Sweet Potatoes Obtained under Different Convective Drying Conditions

This paper discusses the use of various methods to distinguish between slices sweet potato dried in different conditions. The drying conditions varied terms temperature, values were: 60 °C, 70 80 and 90 °C. Examination included instrumental texture analysis using a texturometer digital based on macroscopic images. Classification acquired data involved machine learning techniques types artificial neural networks, such as convolutional networks (CNNs) multi-layer perceptron (MLP). As result, convective drying, changes color darkening were found products with following temperature values: °C (L = 83.41), 81.11), 79.02), 75.53). best-generated model achieved an overall classification efficiency 77%. Sweet at proved be completely distinguishable from other classes, among which 61–83% depending class. means that image deep is valuable tool context assessing quality convective-dried slices.