Optimized machine learning and artificial neural networks for NIRS-based prediction of mango internal quality
Kusumiyati Kusumiyati, Wawan Sutari, Unang Supratman, Agus Arip Munawar, Ine Elisa Putri, Yuda Hadiwijaya · 2026
Read Optimized machine learning and artificial neural networks for NIRS-based prediction of mango internal quality by Kusumiyati Kusumiyati, Wawan Sutari, Unang Supratman, Agus Arip Munawar, Ine Elisa Putri, Yuda Hadiwijaya (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13522578.txt.
Description
Kusumiyati Kusumiyati and colleagues combine light scanning with machine learning to judge mango quality without cutting the fruit in a 2026 study. Near-infrared spectra were collected from one hundred thirty-six intact mangoes and corrected before modeling. Five regression methods, from a traditional linear approach to boosted trees and a neural network, were tuned to predict total acidity and vitamin C content.
Nonlinear models clearly beat the traditional method, with the neural network reaching the highest accuracy on both measures. Performance scores indicated the predictions were strong enough for practical sorting use. The authors present the combined method as a fast, non-destructive option for quality control, supply chain decisions, and breeding programs that need reliable measures of fruit chemistry.
Catalog record
| CREATOR | Kusumiyati Kusumiyati, Wawan Sutari, Unang Supratman, Agus Arip Munawar, Ine Elisa Putri, Yuda Hadiwijaya |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 58919 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |