Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM64631
Volume:
10 |
6 |
Jun 2026
Pages:
1-10
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Electronics and telecommunication
Ajeenkya DY Patil school of engineering
Electronics and telecommunication
Ajeenkya DY Patil school of engineering
Electronics and telecommunication
Ajeenkya DY Patil school of engineering
Electronics and telecommunication
Ajeenkya DY Patil school of engineering
Electronics and telecommunication
Ajeenkya DY Patil school of engineering
Electronics and telecommunication
Ajeenkya DY Patil school of engineering
Electronics and telecommunication
Ajeenkya DY Patil school of engineering
Accurate and early detection of crop diseases is essential for improving agricultural productivity and ensuring sustainable farming practices. Conventional manual wheat crop inspection takes a lot of time, is prone to mistakes, and necessitates specialized knowledge. This research describes a sophisticated Edge AI-based smart farming system that uses deep learning and an Internet of Things (IoT) framework to identify wheat illness in real time. The suggested system makes use of a Raspberry Pi-based acquisition unit with sensors to track environmental factors including temperature, humidity, and soil moisture as well as a camera to take pictures of wheat leaves. The suggested model, in contrast to traditional methods, is tailored for on-device inference using TensorFlow Lite, allowing deployment on an Android-based mobile application for offline and real-time disease prediction. Using a dataset of five thousand annotated photos, a deep convolutional neural network (CNN) model based on transfer learning is trained to categorize wheat diseases into five groups: Crown & Root Rot, Healthy, Leaf Rust, Stem Rust, and Wheat Loose Smut. With a 97% validation accuracy, a 98.8% training accuracy, and a minimal validation loss, the system performs well.Low latency, less reliance on cloud infrastructure, and effective field-level deployment are guaranteed by the combination of Edge AI, IoT, and mobile computing. The suggested solution increases crop productivity and supports precision agriculture by enabling farmers to diagnose diseases instantly and take prompt preventative action.
KEYWORDS
This work introduces a real-time IoT-enabled wheat disease diagnosis system that uses a VGG19 deep learning model in conjunction with Raspberry Pi edge computing. With 98.8% training accuracy and 97% validation accuracy, the system attains great dependability by combining sensor data with image-based categorization. It offers automated, immediate disease detection for ailments including Leaf Rust, Stem Rust, Crown & Root Rot, and Loose Smut, in contrast to manual inspection. It is appropriate for rural, low-resource situations due to its low-cost, low-power Raspberry Pi implementation. By lowering losses and enhancing decision-making, the scalable and offline-capable architecture promotes sustainable precision agriculture. All things considered, the system improves AIoT-based smart farming through adaptive disease monitoring and real-time sensing.
Sharma, R., et al. (2025). Reliable and Cost-Efficient IoT Connectivity for Smart Agriculture. arXiv Nguyen, L., et al. (2025). Past, Present and Future of Deep Plant Leaf Disease Recognition. Computers and Electronics in Agriculture, pp. 1–15. Ahmed, T., et al. (2025). Multi-output Deep-Supervised Classifier Chains for Plant Pathology. IEEE Access, 13, pp. 101–115. Roumeliotis, K. I., et al. (2025). Plant Disease Detection through Multimodal LLMs and CNNs. arXiv. Patel, S., et al. (2025). Advances in Deep Learning Applications for Plant Disease and Pest Detection. Remote Sensing, 17, pp. 45–63. Johnson, E., et al. (2025). Automated Plant Disease Detection – Recent Advancements. Journal of Agricultural Informatics, 12, pp. 33–50. Gupta, B., et al. (2025). Machine Learning and Deep Learning for Crop Disease Diagnosis: Performance Analysis and Review. Agronomy, 15, pp. 120–138. Smith, C., et al. (2024). A Survey on Deep Learning in UAV Imagery for Precision Agriculture. IEEE Geoscience and Remote Sensing Magazine, 12(4), pp. 22–36. Martinez, J. R., et al. (2024). Smart Sensors and Smart Data for Precision Agriculture: A Review. Sensors, 24(2), pp. 11–25. Al-Khaled, M., et al. (2024). Drones in Precision Agriculture: A Comprehensive Review. Drones, 8(3), pp. 14–28. Chaturvedi, V., et al. (2023). Coverage Analysis of LoRa and NB-IoT for LPWAN in Agriculture. Sensors, 23(7), pp. 100–112. Takahashi, H., et al. (2023). Analysis of Crop Diseases Using IoT and Machine Learning Approaches. Proceedings of the Conference on Smart Agriculture, pp. 45–52.
Publication Date
6/16/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...