Authors : Asha S.; Annappa S. S.; Lohith C.

Volume/Issue : Volume 11 - 2026, Issue 7 - July

Google Scholar : https://tinyurl.com/56hsbm5a

Scribd : https://tinyurl.com/4xx3zpjc

DOI : https://doi.org/10.38124/ijisrt/26jul1282

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : This paper presents an IoT and edge-AI enabled autonomous agricultural robot that performs early plant disease diagnosis and precision irrigation on a single mobile platform. Unlike earlier automated farming systems that rely on visible-spectrum (RGB) imagery and simple threshold-based watering, the proposed system fuses RGB and nearinfrared (NIR) imagery to compute the Normalised Difference Vegetation Index (NDVI), enabling detection of physiological plant stress several days before visible lesions appear. Leaf images are classified using a lightweight attention-guided convolutional neural network that combines a MobileNetV3 backbone with a Convolutional Block Attention Module (CBAM), allowing the network to focus on lesion-relevant channels and spatial regions while remaining compact enough for real-time inference on an ESP32-S3 edge controller. Irrigation and pesticide-spray decisions are no longer governed by a rigid binary threshold; instead, a Mamdani-type fuzzy inference engine fuses soil moisture, ambient temperature, and the NDVI-derived stress index to compute a proportional, continuously variable actuation signal, reducing both water wastage and false triggering. The robot streams sensor readings, classification results, and actuation logs to a cloud dashboard over Wi-Fi/MQTT so that farmers can monitor crop health and irrigation status remotely and receive real-time alerts. Experimental evaluation on a prototype platform shows that the proposed attention-guided model improves disease-classification accuracy over a baseline CNN, the NDVI-assisted pipeline detects stress earlier than colour-only analysis, and the fuzzy irrigation controller reduces water consumption relative to the binary threshold scheme while maintaining optimal soil-moisture levels. The results indicate that combining multispectral sensing, attention-based lightweight deep learning, and fuzzy control on a single autonomous platform is a practical and scalable route towards sustainable, resource-efficient precision agriculture.

Keywords : Precision Agriculture, Internet of Things, Edge AI, Attention-Guided CNN, CBAM, Multispectral Imaging, NDVI, Fuzzy Logic Irrigation, Autonomous Agricultural Robot, Plant Disease Diagnosis.

References :

1. R. Nair and S. Deshpande, “Challenges and Opportunities in Data-Driven Precision Agriculture for Food Security,” International Journal of Advanced Research in Computer Science, vol. 12, no. 4, pp. 45–52, 2021.
2. A. Verma and P. Chatterjee, “Internet of Things Architectures for Real-Time Agricultural Monitoring: A Survey,” IEEE Access, vol. 8, pp. 152344–152360, 2020.
3. M. Rao and D. Iyer, “Wireless Sensor Network Based Smart Farming System for Remote Crop Monitoring,” International Journal of Innovative Technology and Exploring Engineering, vol. 9, no. 6, pp. 233–239, 2020.
4. S. Kulkarni and T. Bhosale, “Colour, Texture and Shape Feature Based Plant Leaf Disease Identification: A Review,” Journal of Embedded Systems and Applications, vol. 13, no. 2, pp. 88–96, 2021.
5. H. Fujimoto and L. Chen, “Edge Computing Constraints for Deep Learning Based Crop Disease Classification,” IEEE Transactions on Emerging Topics in Computing, vol. 9, no. 3, pp. 112–121, 2021.
6. K. Ramesh and V. Suresh, “Lightweight Convolutional Neural Networks for On-Device Plant Disease Recognition,” International Journal of Computer Applications, vol. 183, no. 15, pp. 19–27, 2021.
7. N. Joshi and R. Pillai, “Cloud-Integrated IoT Framework for Sustainable Agricultural Data Management,” International Journal of Information Systems and Engineering, vol. 14, no. 2, pp. 101–109, 2022.
8. P. Nanda and S. Rout, “Machine Learning Classifiers for Automated Detection of Crop Leaf Disease,” International Journal of Advanced Computer Science and Applications, vol. 12, no. 5, pp. 210–217, 2021.
9. B. Menon and A. Krishnan, “Convolutional Neural Network Architectures for Large-Scale Plant Disease Classification,” International Conference on Artificial Intelligence and Data Science, pp. 98–105, 2021.
10. F. Alonso and M. Castillo, “NDVI and Multispectral Vegetation Indices for Early Detection of Crop Stress: A Review,” Remote Sensing Applications in Agriculture, vol. 6, no. 1, pp. 33–44, 2020.
11. D. Kaul and R. Bansal, “Sensor-Feedback Based Automated Irrigation Using Solenoid Valve Control,” Journal of Sustainable Agricultural Technologies, vol. 9, no. 2, pp. 61–69, 2021.
12. S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “CBAM: Convolutional Block Attention Module,” Proceedings of the European Conference on Computer Vision (ECCV), pp. 3–19, 2018.
13. A. Howard, M. Sandler, G. Chu, et al., “Searching for MobileNetV3,” Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1314–1324, 2019.
14. T. Ghosh and V. Nair, “Fuzzy Logic Based Adaptive Irrigation Control for Water-Efficient Precision Farming,” International Journal of Recent Trends in Engineering and Research, vol. 8, no. 3, pp. 77–85, 2022.
15. World Bank, “Agricultural Innovation for Climate-Smart Development,” The World Bank Publications, Washington, D.C., 2021.