Evaluation of sensory crispness of dry crispy foods by convolutional neural networks

• Grant number: 21/05317-9
• Support Opportunities: Scholarships in Brazil - Master
• Start date: October 01, 2021
• End date: April 30, 2023
• Field of knowledge: Agronomical Sciences - Food Science and Technology - Food Engineering
• Principal Investigator: Gustavo Cesar Dacanal
• Grantee: Rafael Zinni Lopes
• Host Institution: Faculdade de Zootecnia e Engenharia de Alimentos (FZEA). Universidade de São Paulo (USP). Pirassununga , SP, Brazil

Abstract

Convective drying is traditionally applied to dehydrate fresh and processed food. The process reduces volume and water activity, thus, it's easier to transport and store. The volume decreases due to water loss resulting in shrinking the material. The molecular matrix pileup changes its elasticity coefficient depending on the operational conditions (temperature, humidity, and airspeed). The crispness of dried food such as cookies, snacks, dried fruit, and dried vegetables will be analyzed in this study by sound and mathematical approaches. The dried samples will be stored in a salt desiccator to contain relative humidity, which will be used to define their water activity. Pycnometry will measure the volume variation, while Image Analysis by Scanning Electron Microscopy will measure the pore volume. The sound is what links the porosity to the crispness. In uniaxial compression tests, the sound is captured and transformed by discrete Fourier Transform in a Power Spectrogram using Python. The compression and sound noise profiles will be determined by a manual lever device containing a data acquisition system via Arduino. The experimental results will be used to explain the relationship between shrinkage, moisture content, and noise properties.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

LOPES, RAFAEL Z.; DACANAL, GUSTAVO C.. Classification of crispness of food materials by deep neural networks. JOURNAL OF TEXTURE STUDIES, v. N/A, p. 15-pg., 2023-08-01. (21/05317-9)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

LOPES, Rafael Zinni. Evaluation of sensory crispness of dry crispy foods by convolutional neural networks. 2023. Master's Dissertation - Universidade de São Paulo (USP). Faculdade de Zootecnica e Engenharia de Alimentos (FZE/BT) Pirassununga.