Block Chain and Internet of Nano-Things for Optimizing Chemical Sensing in Smart Farming

TL;DR

This paper introduces a blockchain-enabled IoNT system for chemical sensing in smart farming, enhancing data security, transparency, and decision-making accuracy with a novel machine learning-based smart contract.

Contribution

It proposes the first integrated BC-IoNT system for chemical sensing in agriculture, combining machine learning, blockchain, and IoNT for improved farm management.

Findings

Accuracy >90% for distributed BC-IoNT approach

Distributed approach outperforms centralized in chemical detection

Sensing efficiency depends on sampling frequency and farm variability

Abstract

The use of Internet of Things (IoT) with the Internet of Nano Things (IoNT) can further expand decision making systems (DMS) to improve reliability as it provides a new spectrum of more granular level data to make decisions. However, growing concerns such as data security, transparency and processing capability challenge their use in real-world applications. DMS integrated with Block Chain (BC) technology can contribute immensely to overcome such challenges. The use of IoNT and IoT along with BC for making DMS has not yet been investigated. This study proposes a BC-powered IoNT (BC-IoNT) system for sensing chemicals level in the context of farm management. This is a critical application for smart farming, which aims to improve sustainable farm practices through controlled delivery of chemicals. BC-IoNT system includes a novel machine learning model formed by using the Langmuir molecular binding model and the Bayesian theory, and is used as a smart contract for sensing the level of the chemicals. A credit model is used to quantify the traceability and credibility of farms to determine if they are compliant with the chemical standards. The accuracy of detecting the chemicals of the distributed BC-IoNT approach was >90% and the centralized approach was <80%. Also, the efficiency of sensing the level of chemicals depends on the sampling frequency and variability in chemical level among farms.