Edge-optimized multimodal cross-fusion architecture for efficient crop disease detection
International Journal of Science, Technology, Engineering and Mathematics · 30.06.2025 · 5 (2) · 1
DOI: 10.53378/ijstem.353186 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Science, Technology, Engineering and Mathematics, online erschienen am 24.05.2025. Verfasst von Thomas Kinyanjui Njoroge und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Accurate and timely crop disease detection is critical for reducing agricultural losses and ensuring food security in low-resource settings. Traditional diagnostic methods, such as manual inspections, are often inefficient and error-prone. Existing deep learning models (e.g., ResNet50, Inception V3) struggle with computational inefficiency and poor generalizability in real-world farming contexts. This study proposes a lightweight multimodal fusion model integrating EfficientNetV2 and MobileNetV2, optimized for edge deployment. The architecture leverages compound scaling and feature fusion to recognize subtle disease patterns, and it was fine-tuned on a globally diverse dataset (PlantVillage and field-collected leaf images). The proposed model achieved state-leading metrics (99.0% accuracy, 0.993 precision, 0.990 F1-score, AUC = 0.999997), outperforming benchmarks like ShuffleNet and DenseNet50 (ranked 2nd–6th). Statistical validation via the Kruskal-Wallis test confirmed significant performance differences across models (H=614.90, p=1.4237e−129), with Bayesian analysis showing a 100% superiority probability over DenseNet50. Notably, the model exhibited the lowest confidence variance (0.000012) compared to alternatives (0.000014–0.000032), demonstrating unmatched prediction stability. Deployment on low-end mobile devices posed challenges such as computational constraints and offline usability. However, the TensorFlow Lite-powered mobile app addressed these limitations, offering real-time, offline disease classification with 0.094-second inference latency on devices with ≤2GB RAM. Validated on 249 unseen field images (95.98% accuracy), this solution bridges the gap between high-performance deep learning and real-world agricultural needs, empowering smallholder farmers with an accessible and scalable tool.
Zitieren
APA
Njoroge, T. K., Shindu, K. M., & Kibuku, R. (2025). Edge-optimized multimodal cross-fusion architecture for efficient crop disease detection. International Journal of Science, Technology, Engineering and Mathematics, 5(2), 1. https://doi.org/10.53378/ijstem.353186
Vancouver
Njoroge TK, Shindu KM, Kibuku R. Edge-optimized multimodal cross-fusion architecture for efficient crop disease detection. International Journal of Science, Technology, Engineering and Mathematics. 2025;5(2):1. doi:10.53378/ijstem.353186
BibTeX
@article{Njoroge2025,
author = {Njoroge, Thomas Kinyanjui and Shindu, Kelvin Mugoye and Kibuku, Rachael},
title = {Edge-optimized multimodal cross-fusion architecture for efficient crop disease detection},
journal = {International Journal of Science, Technology, Engineering and Mathematics},
year = {2025},
volume = {5},
number = {2},
pages = {1},
doi = {10.53378/ijstem.353186}
}
EUVIMED