Decentralised and Predictive System for Efficient Agri-Transactions Through Blockchain Technology

Remegius Praveen SAHAYARAJ¹*, Muthurajkumar SANNASY²
¹ Loyola-ICAM College of Engineering and Technology, Chennai – 600034, India
pravinsahayaraj@gmail.com (*Corresponding author)
² Madras Institute of Technology (MIT) Campus, Anna University, Chennai – 600044, India
muthurajkumarss@gmail.com

Abstract: Agriculture is an art, a craftsmanship and a scientific way of cultivation, growth and maintenance of edible crops and livestock. Majority of the current farming communities do not have prior knowledge of predicting the suitable crop for their soil and climatic conditions. Difficulty in raising the initial investment for crop cultivation is also one of the serious concerns of these communities. The difficulties faced by the civic agriculture, the insecure monetary transactions, along with the concerns related to the financial process have been identified and listed. The paper proposes a feasible solution by predicting the appropriate crops that could be grown in a specific scenario or environmental conditions using the machine-learning model of Support Vector Classifier and provides data related to quality yields using Fuzzy Decision Merkle Tree (FDMT) Regressor. Additionally, a transparent and secure fund transfer mechanism is provided using Ethereum blockchain-based technology. The proposed model implements a secured, translucent and tamper-resistant digital platform for the farming communities to host their products. A fortified consensus can be formed between the farmer and the investor bounded with a rating mechanism to build the credibility of both the farmer and the investor7 based on the prior knowledge obtained in the Agri-market.

Keywords: Blockchain, Fuzzy, Agriculture, Machine learning, SVM.

>>FULL TEXT: PDF

CITE THIS PAPER AS:
Remegius Praveen SAHAYARAJ, Muthurajkumar SANNASY, Decentralised and Predictive System for Efficient Agri-Transactions Through Blockchain Technology, Studies in Informatics and Control, ISSN 1220-1766, vol. 31(3), pp. 125-140, 2022. https://doi.org/10.24846/v31i3y202212