EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Non-Destructive Early Detection of Drosophila Suzukii Infestation in Sweet Cherries (c.v. Sweet Heart) Based on Innovative Management of Spectrophotometric Multilinear Correlation Models

Giuseppe Altieri, Mahdi Rashvand Avaei, Attilio Matera, Francesco Genovese, Vincenzo Verrastro, Naouel Admane, Orkhan Mammadov, Sabina Laveglia, Giovanni Carlo Di Renzo

Applied Sciences · 29.12.2024 · 15 (1) · 197

DOI: 10.3390/app15010197 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 29.12.2024. Verfasst von Giuseppe Altieri und 8 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union Next-GenerationEU.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drosophila suzukii (Matsumura), also known as spotted wing drosophila (SWD), is invasive, with a preference for infesting commercially viable soft berries, particularly cherries. SWD infestations in sweet cherries are difficult to detect and remove in the field, packing houses, and processing lines, causing significant economic losses and reducing yields significantly, necessitating early detection of insect infestation in fruits during primary decaying stages. Few publications have addressed the use of non-destructive techniques for the detection of insect infestation in cherries. Based on the advantages and effectiveness of the spectrophotometric techniques, an attempt was made to use the spectrophotometry to rapidly detect postharvest SWD infestations of intact sweet cherry fruit, to employ it in sweet cherry fruit selection and grading processes. The main purpose of this study was to apply spectrophotometry as a rapid and non-destructive method in detecting and classifying healthy sweet cherry fruit versus that infested with SWD eggs. To model the data fit/prediction, principal components regression and partial least squares regression algorithms were considered. The external cross-validation set was initially set to 20% of the overall available samples and subsequently increased to 50% in the final selected optimal model. The identified procedure of management of regression algorithms allowed the selection of a very performant and robust model using the partial least squares regression algorithm: its false negative rate and false positive rate, after 500 Monte Carlo runs, were 0.004% +/− 0.003 and 0.02% +/− 0.01, respectively, and, in addition, the 50% of samples were used for the external cross-validation set.

Förderung

  • European Union Next-GenerationEU

Zitieren

APA

Altieri, G., Avaei, M. R., Matera, A., Genovese, F., Verrastro, V., Admane, N., Mammadov, O., Laveglia, S., & Renzo, G. C. D. (2024). Non-Destructive Early Detection of Drosophila Suzukii Infestation in Sweet Cherries (c.v. Sweet Heart) Based on Innovative Management of Spectrophotometric Multilinear Correlation Models. Applied Sciences, 15(1), 197. https://doi.org/10.3390/app15010197

Vancouver

Altieri G, Avaei MR, Matera A, Genovese F, Verrastro V, Admane N, et al. Non-Destructive Early Detection of Drosophila Suzukii Infestation in Sweet Cherries (c.v. Sweet Heart) Based on Innovative Management of Spectrophotometric Multilinear Correlation Models. Applied Sciences. 2024;15(1):197. doi:10.3390/app15010197

BibTeX
@article{Altieri2024,
  author = {Altieri, Giuseppe and Avaei, Mahdi Rashvand and Matera, Attilio and Genovese, Francesco and Verrastro, Vincenzo and Admane, Naouel and Mammadov, Orkhan and Laveglia, Sabina and Renzo, Giovanni Carlo Di},
  title = {Non-Destructive Early Detection of Drosophila Suzukii Infestation in Sweet Cherries (c.v. Sweet Heart) Based on Innovative Management of Spectrophotometric Multilinear Correlation Models},
  journal = {Applied Sciences},
  year = {2024},
  volume = {15},
  number = {1},
  pages = {197},
  doi = {10.3390/app15010197}
}
Kostenlos starten →