An online tool based on the Internet of Things and intelligent blockchain technology for data privacy and security in rural and agricultural development
Abstract The standard implementation of the Internet of Things (IoT) has renovated numerous sectors, supporting agriculture with modern technological development. Termed Agriculture-Internet of Things (Agri-IoT), this combination has helped in Smart Farming (SF) using wireless sensors that record re...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-13231-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract The standard implementation of the Internet of Things (IoT) has renovated numerous sectors, supporting agriculture with modern technological development. Termed Agriculture-Internet of Things (Agri-IoT), this combination has helped in Smart Farming (SF) using wireless sensors that record real-time data improvement sustainable agriculture practices like irrigation, pest control, and overall field operations. So far, Agri-IoT research faces challenges, mainly focusing on data security and management, which are vulnerabilities in existing centralized solutions. Enter Blockchain Technology (BCT): a decentralized, transparent, and perfect mechanism that improves data security and access control and paves the technique for efficient transactions. This research work introduces a novel multi-tiered BCT personalized for Agri-IoT. The model comprises Edge, Fog, and Cloud levels, employing discrete ‘Data Handlers’ for each tier, confirming an efficient data lifecycle. Central to this model is the proposed Quantum Neural Network + Bayesian Optimization (QNN + BO), a practiced algorithm that, when combined with methods like the Elliptic Curve Cryptography (ECC) and Coyote Optimization Algorithm (COA), guarantees secure data flow, processing, and storage. The proposed QNN + BO model, evaluated using the ToN_IoT dataset, validates significant performance enhancements — reducing encryption and decryption times by up to 46.7% and 54.6%, and improving prediction accuracy with a 19.3% Mean Absolute Percentage Error (MAPE), outperforming baseline models. Additionally, it consumes up to 33% less memory, supporting its suitability for resource-constrained agricultural environments. This integrative model proposes a complete solution to connect Agri-IoT’s potential while addressing its challenges. |
|---|---|
| ISSN: | 2045-2322 |