EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning Analysis of Hyperspectral Images of Damaged Wheat Kernels

Kshitiz Dhakal iD, Upasana Sivaramakrishnan, Xuemei Zhang, Kassaye Belay, Joseph Oakes, Xing Wei iD, Song Li

Sensors · 28.03.2023 · 23 (7) · 3523

DOI: 10.3390/s23073523 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 28.03.2023. Verfasst von Kshitiz Dhakal und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Plant and Environmental Sciences, Virginia Tech, Blacksburg, VA 24061, USA. Hauptthemen laut MEDLINE: Trichothecenes, Mycotoxins, Fusarium. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Virginia Small Grains Board, Center for Advanced Innovation in Agriculture at Virginia Tech.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fusarium head blight (FHB) is a disease of small grains caused by the fungus Fusarium graminearum. In this study, we explored the use of hyperspectral imaging (HSI) to evaluate the damage caused by FHB in wheat kernels. We evaluated the use of HSI for disease classification and correlated the damage with the mycotoxin deoxynivalenol (DON) content. Computational analyses were carried out to determine which machine learning methods had the best accuracy to classify different levels of damage in wheat kernel samples. The classes of samples were based on the DON content obtained from Gas Chromatography–Mass Spectrometry (GC-MS). We found that G-Boost, an ensemble method, showed the best performance with 97% accuracy in classifying wheat kernels into different severity levels. Mask R-CNN, an instance segmentation method, was used to segment the wheat kernels from HSI data. The regions of interest (ROIs) obtained from Mask R-CNN achieved a high mAP of 0.97. The results from Mask R-CNN, when combined with the classification method, were able to correlate HSI data with the DON concentration in small grains with an R2 of 0.75. Our results show the potential of HSI to quantify DON in wheat kernels in commercial settings such as elevators or mills.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TrichothecenesMycotoxinsFusariumTriticumPlant DiseasesEdible Grain

Stichwörter der Autor:innen

deoxynivalenol (DON)fusarium head blighthyperspectral imagingmachine learningobject detection

Substanzen

TrichothecenesMycotoxins

Autor:innen und Institutionen

  • School of Plant and Environmental Sciences, Virginia Tech, Blacksburg, VA 24061, USA.
  • Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA 24061, USA.
  • Graduate Program in Genetics, Bioinformatics and Computational Biology, Virginia Tech, Blacksburg, VA 24061, USA.
  • Virginia Tech Eastern Virginia Agricultural Research and Extension Center (AREC), Warsaw, VA 22572, USA.
  • Department of Agricultural and Biological Engineering, Purdue University, West Lafayette, IN 47907, USA.

ORCID-Profile: Kshitiz Dhakal, Xing Wei

Förderung

  • Virginia Small Grains Board
  • Center for Advanced Innovation in Agriculture at Virginia Tech

Zitieren

APA

Dhakal, K., Sivaramakrishnan, U., Zhang, X., Belay, K., Oakes, J., Wei, X., & Li, S. (2023). Machine Learning Analysis of Hyperspectral Images of Damaged Wheat Kernels. Sensors, 23(7), 3523. https://doi.org/10.3390/s23073523

Vancouver

Dhakal K, Sivaramakrishnan U, Zhang X, Belay K, Oakes J, Wei X, et al. Machine Learning Analysis of Hyperspectral Images of Damaged Wheat Kernels. Sensors. 2023;23(7):3523. doi:10.3390/s23073523

BibTeX
@article{Dhakal2023,
  author = {Dhakal, Kshitiz and Sivaramakrishnan, Upasana and Zhang, Xuemei and Belay, Kassaye and Oakes, Joseph and Wei, Xing and Li, Song},
  title = {Machine Learning Analysis of Hyperspectral Images of Damaged Wheat Kernels},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {7},
  pages = {3523},
  doi = {10.3390/s23073523}
}
Kostenlos starten →