Non-invasive prediction of sweet cherry soluble solids content using dielectric spectroscopy and down-sampling techniques

Sacilik, K., Cetin, N., Ozbey, B. and Cheein, F.A.A. (2025) Non-invasive prediction of sweet cherry soluble solids content using dielectric spectroscopy and down-sampling techniques. Smart Agricultural Technology, 10. ISSN 2772-3755

[img] Text
F Auat Cheein Non-invasive prediction of sweet cherry soluble solids OCR Upload.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.
Download (2MB)

Abstract

The soluble solid content (SSC) in fruits significantly influences consumers’ taste, aroma, and flavor preferences. It also plays a crucial role for farmers and wholesalers in determining the optimal harvest period for marketing. Dielectric spectroscopy, an innovative and non-invasive technique, has shown promise for various applications in the food and agriculture sectors. This study introduces an open-ended coaxial line probe measurement system to non-invasively determine the SSC of sweet cherries at different radio and microwave frequencies. Key parameters such as the dielectric constant (ε′), loss factor (ε′′), loss tangent (tan δ), and SSC of sweet cherries were measured across different harvest periods. The dielectric property frequency ranges were down-sampled from 300 MHz to 15 MHz. Using dielectric spectroscopy, we implemented predictive models: support vector regression (SVR) and multilayer perceptron (MLP), that demonstrated extremely low MAE and RMSE, with correlation coefficients (R) exceeding 0.97 for SVR and 0.96 for MLP. The down-sampled frequency ranges for dielectric properties yielded consistently high performance across all subsets, demonstrating comparable results. These findings suggest that a dielectric measurement system designed for SSC estimation using fewer frequencies could effectively reduce costs while maintaining accuracy.

Item Type: Article
Keywords: Sweet cherries, Down-sampling, Dielectric spectroscopy, Soluble solid content, Machine learning
Divisions: Engineering
Depositing User: Mrs Susan Howe
Date Deposited: 10 Mar 2025 17:53
Last Modified: 10 Mar 2025 17:53
URI: https://hau.repository.guildhe.ac.uk/id/eprint/18191

Actions (login required)

Edit Item Edit Item