EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Classification and Recognition of Soybean Quality Based on Hyperspectral Imaging and Random Forest Methods

Man Chen, Zhichang Chang, Chengqian Jin, Gong Cheng, Shiguo Wang, Youliang Ni

Sensors · 01.03.2025 · 25 (5) · 1539

DOI: 10.3390/s25051539 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 01.03.2025. Verfasst von Man Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China. Hauptthemen laut MEDLINE: Glycine max, Hyperspectral Imaging. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China, National key research and development plan project, General Project of Jiangsu Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To achieve the rapid and accurate classification and identification of soybean components, this study selected soybeans harvested by the 4LZ-1.5 soybean combine harvester as the research subject. Hyperspectral images of soybean samples were collected using the Pika L spectrometer, and spectral information was extracted from the regions of interest (ROI) in the images. Eight preprocessing methods, including baseline correction (BC), moving average (MA), Savitzky–Golay derivative (SGD), normalization, standard normal variate transformation (SNV), multiplicative scatter correction (MSC), first derivative (DS), and Savitzky–Golay smoothing (SGS), were applied to the raw spectral data to eliminate irrelevant information. Feature wavelengths were selected using the successive projections algorithm (SPA) and the competitive adaptive reweighted sampling (CARS) algorithm to reduce spectral redundancy and enhance model detection performance, retaining eight and ten feature wavelengths, respectively. Subsequently, a random forest (RF) model was developed for soybean component classification. The model parameters were optimized using particle swarm optimization (PSO) and differential evolution (DE) algorithms to improve performance. Experimental results showed that the RF classification model based on SPA-BC preprocessed spectra and DE-tuned parameters achieved an optimal prediction accuracy of 1.0000 during training. This study demonstrates the feasibility of using hyperspectral imaging technology for the rapid and accurate detection of soybean components, providing technical support for the assessment of breakage and impurity levels during soybean harvesting and storage processes. It also offers a reference for the development of future machine-harvested soybean breakage and impurity detection systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Glycine maxHyperspectral ImagingAlgorithmsRandom Forest

Stichwörter der Autor:innen

classification and identificationfeature extractionhyperspectral imagingrandom forestsoybean

Autor:innen und Institutionen

  • Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China.
  • National Digital Agriculture Equipment (South China Intelligence Agricultural Mchine) Innovation Sub-Center, Nanjing 210014, China.
  • Xinjiang Academy of Agricultural Reclamation Sciences, Institute of Mechanical Equipment, Shihezi 832000, China.

Förderung

  • the National Natural Science Foundation of China
  • National key research and development plan project
  • General Project of Jiangsu Natural Science Foundation
  • National Natural Science Foundation of China
  • General Project of the Jiangsu Natural Science Foundation

Zitieren

APA

Chen, M., Chang, Z., Jin, C., Cheng, G., Wang, S., & Ni, Y. (2025). Classification and Recognition of Soybean Quality Based on Hyperspectral Imaging and Random Forest Methods. Sensors, 25(5), 1539. https://doi.org/10.3390/s25051539

Vancouver

Chen M, Chang Z, Jin C, Cheng G, Wang S, Ni Y. Classification and Recognition of Soybean Quality Based on Hyperspectral Imaging and Random Forest Methods. Sensors. 2025;25(5):1539. doi:10.3390/s25051539

BibTeX
@article{Chen2025,
  author = {Chen, Man and Chang, Zhichang and Jin, Chengqian and Cheng, Gong and Wang, Shiguo and Ni, Youliang},
  title = {Classification and Recognition of Soybean Quality Based on Hyperspectral Imaging and Random Forest Methods},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {5},
  pages = {1539},
  doi = {10.3390/s25051539}
}
Kostenlos starten →