MACHINE LEARNING BASED ESTIMATION OF DRYING CHARACTERISTICS OF APPLE SLICES

Creative Commons License

Çetin N.

International Scientific Symposium Current Trends in Natural Sciences, Pitesti, Romania, 19 - 21 May 2022, vol.1, no.1, pp.1, (Summary Text)

  • Publication Type: Conference Paper / Summary Text
  • Volume: 1
  • City: Pitesti
  • Country: Romania
  • Page Numbers: pp.1
  • Open Archive Collection: AVESIS Open Access Collection
  • Erciyes University Affiliated: Yes

Abstract

Machine learning algorithms have been commonly used in food drying processing. These algorithms are also effectively used for nonlinear processes. Estimation of drying characteristics is important for optimizing drying conditions. Estimating the properties such as moisture content, moisture rate and drying rate ensures accurate and high quality drying of the product under air-convective drying conditions. In this study, moisture ratio and drying rates of apple slices were estimated in air-convective drying conditions. Three machine learning algorithms (random forest-RF; artificial neural network-ANN; and k-nearest neighbors-kNN) were performed to estimate moisture ratio and drying rate. In the study, correlation coefficients were found to be above 0.85 in the estimation of humidity and drying rate for all algorithms. The present findings show that machine learning algorithms could be successfully applied for the estimation of drying characteristics.