Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{191743,
        author = {Bimla Godara},
        title = {IOT-Enabled Deep Learning Framework for Scalable Crop Disease Prediction Using Multimodal Sensor and Image Fusion},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {12},
        number = {no},
        pages = {92-107},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191743},
        abstract = {The agricultural sector worldwide continues to face serious challenges from crop diseases, which cause major financial losses and threaten global food security. This study introduces an intelligent, IOT-enabled deep learning framework designed to predict crop diseases by combining leaf image analysis with real-time environmental sensor data. 
The proposed system uses a hybrid deep learning model: EfficientNetB0 extracts visual features from leaf images, while a separate neural network processes environmental parameters such as soil pH, temperature, humidity, moisture, light intensity, rainfall, and wind speed. By merging visual and environmental data, the system delivers context-aware predictions that remain reliable even when sensor readings include ±5% Gaussian noise.
Our approach achieves an impressive 93.8% classification accuracy on an extended version of the PlantVillage dataset containing over 3,000 disease categories—significantly surpassing traditional image-only detection methods. To ensure interpretability, Grad-CAM visualizations are integrated to highlight the image regions influencing each prediction, enhancing user trust and transparency.
 A Flask-based web application further supports real-time use, allowing farmers to upload leaf images and instantly receive disease diagnoses along with practical treatment suggestions.
Experimental evaluations confirm that the proposed framework is scalable, robust, and well-suited for real-world agricultural environments. Overall, this system represents a promising step toward intelligent, data-driven precision farming and sustainable agricultural management.},
        keywords = {Crop Disease Detection, Internet of Things, Deep Learning, Sensor Fusion, Explainable AI, Precision Agriculture, Web Application, EfficientNet, Grad-CAM},
        month = {},
        }