Early Detection of Jujube Shrinkage Disease by Multi-Source Data on Multi-Task Deep Network
Sensors · 2025
DOI: 10.3390/s25216763 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Junzhang Pan und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Engineering, Tarim University, Alaer 843300, China. Hauptthemen laut MEDLINE: Ziziphus, Plant Diseases. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Xinjiang Production and Construction Corps Science and Technology Project, Southern Xin-jiang Key Industry Innovation and Development Support Plan, the President's Fund Project of Tarim University, Xinjiang Production and Construction Corps Science and Technology Project.
Abstract (Originalsprache)
In the arid cultivation region of Xinjiang, China, shrinkage disease severely compromises the quality, yield, and market value of jujube. Published research has achieved high accuracy in detecting larger lesions using RGB imaging and hyperspectral imaging (HSI). However, these methods lack sensitivity in detecting early and subtle symptoms of disease. In this study, a multi-source data fusion strategy combining RGB imaging and HSI was proposed for non-destructive and high-precision detection of early-stage jujube shrinkage disease. Firstly, a total of 317 fruits of the ‘Junzao’ cultivar were collected during multiple stages of natural infection, covering early-stage shrinkage disease detection across different growth stages, including both green and mature red fruits. Secondly, morphological features were extracted from RGB images in multiple dimensions, while a three-stage feature selection strategy combining Principal Component Analysis (PCA), the Successive Projections Algorithm (SPA), and the Genetic Algorithm (GA) was implemented to identify four key wavelengths from HSI. Thirdly, a hybrid convolutional neural network-multilayer perceptron (CNN-MLP) architecture was constructed, with dynamic feature weighting employed to achieve effective multimodal fusion and optimize detection performance. Experimental results demonstrated that compared to the MLP and CNN models, the proposed method achieved approximately 8.0% and 5.4% improvements in accuracy and 38.6% and 32.4% improvements in F1 scores, respectively. It offers a robust and scalable solution for early disease detection and postharvest quality assessment in jujube production.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Information Engineering, Tarim University, Alaer 843300, China.
- College of Horticulture and Forestry, Tarim University, Alaer 843300, China.
- Key Laboratory of Tarim Oasis Agriculture, Ministry of Education, Tarim University, Alaer 843300, China.
ORCID-Profile: Mingdeng Shi
Förderung
- the Xinjiang Production and Construction Corps Science and Technology Project, Southern Xin-jiang Key Industry Innovation and Development Support Plan
- the President's Fund Project of Tarim University
- Xinjiang Production and Construction Corps Science and Technology Project
- Southern Xinjiang Key Industry Innovation and Development Support Plan
- President’s Fund Project of Tarim University
Zitieren
APA
Pan, J., Zhou, L., Geng, H., Zhang, P., Yan, F., Shi, M., Si, C., & Chen, J. (2025). Early Detection of Jujube Shrinkage Disease by Multi-Source Data on Multi-Task Deep Network. Sensors. https://doi.org/10.3390/s25216763
Vancouver
Pan J, Zhou L, Geng H, Zhang P, Yan F, Shi M, et al. Early Detection of Jujube Shrinkage Disease by Multi-Source Data on Multi-Task Deep Network. Sensors. 2025. doi:10.3390/s25216763
BibTeX
@article{Pan2025,
author = {Pan, Junzhang and Zhou, Lei and Geng, Hui and Zhang, Pengyu and Yan, Fenfen and Shi, Mingdeng and Si, Chunjing and Chen, Junjie},
title = {Early Detection of Jujube Shrinkage Disease by Multi-Source Data on Multi-Task Deep Network},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25216763}
}
EUVIMED