AN ATTENTION-BASED FUSION ARCHITECTURE FOR MULTIMODAL CROP DISEASE DETECTION AND ITS DEPLOYMENT ON EDGE DEVICES
Keywords:
multimodal fusion, attention mechanism, deep learning, edge computing, crop diseases, IoT sensors, model compressionAbstract
The thesis presents a conceptual multimodal architecture that fuses image and sensor data through an attention mechanism for the early detection of crop diseases, together with its mathematical formulation, dataset construction procedure, evaluation criteria, and the prospects of deploying the model on resource-constrained edge devices.References
1. Dolatabadian A. [et al.]. Image-based crop disease detection using machine learning // Plant Pathology. – 2025. – DOI: 10.1111/ppa.14006.
2. Hamid [et al.]. Enhancing Agricultural Disease Detection: A Multi-Model Deep Learning Novel Approach // Engineering Reports. – 2025. – DOI: 10.1002/eng2.13113.
3. Deep learning and computer vision in plant disease detection: a comprehensive review of techniques, models, and trends in precision agriculture // Artificial Intelligence Review. – 2024. – DOI: 10.1007/s10462-024-11100-x.
4. Multimodal Deep Learning and Foundation Models for Early Detection and Forecasting of Plant Diseases // Plants. – 2026. – Vol. 15, No. 17. – Art. 2564. – DOI: 10.3390/plants15172564.
5. Sable N.P., Shukla V., Khedkar V., Ujalambkar D.M. Hybrid multimodal learning framework for crop disease detection, adaptive treatment, and price forecasting // Frontiers in Computer Science. – 2026. – DOI: 10.3389/fcomp.2026.1855851.
6. Artificial Intelligence-Driven Plant Disease Detection and Diagnosis: A Comprehensive Review of Deep Learning Approaches, Multimodal Sensing Technologies, and Future Perspectives in Precision Agriculture // The Plant Pathology Journal. – 2026. – DOI: 10.5423/PPJ.RW.01.2026.0004.
7. A Review on the Detection of Plant Disease Using Machine Learning and Deep Learning Approaches // Journal of Imaging. – 2025. – DOI: 10.3390/jimaging11100326.