Abstract
Crop disease detection is essential for controlling dis-ease spread and minimizing agricultural losses. In this demo, we present an implementation of iCrop+, an end-to-end autonomous crop disease detection system that integrates on-device AI, low-power long-range communication (LoRa), and server-based deep learning to create a hybrid architecture suitable for real-world deployment. The prototype efficiently balances local processing and remote inference through category-based optimization, adaptive classification, and intelligent data transmission, ensuring that only the most informative segments are transmitted to the server. Built on low-cost devices such as Raspberry Pi, LoRa transceiver modules, and a laptop, the demo showcases its potential for enhancing precision agriculture applications, providing a scalable, cost-effective solution for large-scale crop monitoring. The validation results show that iCrop+ provides 90% classification accuracy while reducing data transmission by up to 60% over server-only inference solutions.
Recommended Citation
X. Tao et al., "ICrop+: An Edge-boosted Crop Disease Detection System Via TinyML and LoRa Communication," IEEE International Conference on Pervasive Computing and Communications Workshops Percom Workshops, no. 2025, pp. 558 - 560, Institute of Electrical and Electronics Engineers, Jan 2025.
The definitive version is available at https://doi.org/10.1109/PerComWorkshops65533.2025.00127
Department(s)
Computer Science
Keywords and Phrases
Crop Disease Detection; LoRa; On-device AI; Precision Agriculture
International Standard Serial Number (ISSN)
2766-8576; 2836-5348
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2025 Institute of Electrical and Electronics Engineers, All rights reserved.
Publication Date
01 Jan 2025
Comments
National Science Foundation, Grant 1952045