EUVIMEDEUVIMED entdecken
Crossref

Explainable AI‐Guided Hyperspectral Feature Selection in Fruit Quality Assessment and Spatial Visualization

Most Mira Khatun iD, Md Zohurul Islam, Md Niaz Imtiaz, Md Wadud Ahmed iD, Md Toukir Ahmed iD

Journal of Food Science · 2026-03 · 91 (3)

DOI: 10.1111/1750-3841.70976 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Food Science, online erschienen am 19.03.2026. Verfasst von Most Mira Khatun und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics, Pabna University of Science and Technology, Pabna, Bangladesh. Hauptthemen laut MEDLINE: Fruit, Hyperspectral Imaging, Malus, Artificial Intelligence. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: Pabna University of Science and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The integration of hyperspectral imaging (HSI) with machine learning enables non‐destructive prediction and visualization of food quality. However, multicollinearity and redundant features in spectral data can reduce model accuracy and increase computational time, emphasizing the need for key wavelength selection. In response, this study presents an inventive method combining a genetic algorithm (GA) with explainable artificial intelligence (XAI) to select key wavelengths for predicting apple dry matter content (DMC). A partial least squares regression (PLSR) model using the selected features outperformed recursive feature elimination (RFE) and competitive adaptive reweighted sampling (CARS), achieving a coefficient of determination ( R 2 ) of 0.46 and a root mean squared error (RMSE) of 0.70%. The approach was further applied to hyperspectral images to visualize pixelwise DMC distribution, providing spatial insights into fruit composition. Results demonstrate that integrating XAI with evolutionary feature selection offers a noninvasive, transparent, and efficient strategy for assessing and visualizing fruit quality.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

FruitHyperspectral ImagingMalusArtificial IntelligenceFood QualityLeast-Squares AnalysisGenetic AlgorithmsAlgorithmsMachine Learning

Stichwörter der Autor:innen

explainable artificial intelligencefeature selectiongenetic algorithmhyperspectral imagingmachine learningspatial visualization

Autor:innen und Institutionen

  • Department of Statistics, Pabna University of Science and Technology, Pabna, Bangladesh.
  • Department of Computer Science and Engineering, Pabna University of Science and Technology, Pabna, Bangladesh.
  • Department of Agricultural Engineering, Sher-e-Bangla Agricultural University, Dhaka, Bangladesh.

ORCID-Profile: Most Mira Khatun, Md Wadud Ahmed, Md Toukir Ahmed

Förderung

  • Pabna University of Science and Technology

Zitieren

APA

Khatun, M. M., Islam, M. Z., Imtiaz, M. N., Ahmed, M. W., & Ahmed, M. T. (2026). Explainable AI‐Guided Hyperspectral Feature Selection in Fruit Quality Assessment and Spatial Visualization. Journal of Food Science, 91(3). https://doi.org/10.1111/1750-3841.70976

Vancouver

Khatun MM, Islam MZ, Imtiaz MN, Ahmed MW, Ahmed MT. Explainable AI‐Guided Hyperspectral Feature Selection in Fruit Quality Assessment and Spatial Visualization. Journal of Food Science. 2026;91(3). doi:10.1111/1750-3841.70976

BibTeX
@article{Khatun2026,
  author = {Khatun, Most Mira and Islam, Md Zohurul and Imtiaz, Md Niaz and Ahmed, Md Wadud and Ahmed, Md Toukir},
  title = {Explainable AI‐Guided Hyperspectral Feature Selection in Fruit Quality Assessment and Spatial Visualization},
  journal = {Journal of Food Science},
  year = {2026},
  volume = {91},
  number = {3},
  doi = {10.1111/1750-3841.70976}
}
Kostenlos starten →