Smart agriculture: precision farming through sensor-based crop monitoring and control system

Mohamad Hakhrani, Asyful Azhim and Abdul Hamid, Syamsul Bahrin (2024) Smart agriculture: precision farming through sensor-based crop monitoring and control system. Journal of Mechatronics and Intelligent Manufacturing, 6 (2). pp. 52-65. E-ISSN 2637-0883

PDF (Article) - Published Version Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

The escalation of the global population and the depletion of natural resources have propelled the evolution of smart agriculture and precision farming, underpinned by sensor-based crop monitoring and control systems, which are anticipated to revolutionize the agricultural sector. Notably, prevalent smart agriculture systems predominantly emphasize either IoT components for data monitoring and control or machine learning components for data analysis. Consequently, this project endeavours to develop a system that seamlessly integrates both IoT and machine learning components, culminating in an advanced system capable of real-time crop monitoring and growth prediction. Collaborating with the Urban Farming Farm under the auspices of the Kulliyyah of Economics and Management Science, an IoT system comprising soil moisture, temperature, and humidity sensors, alongside an actuator, is devised to facilitate data acquisition and required intervention specifically for Okra Fruit during the pre-harvesting stage. Subsequently, four distinct algorithms are trained with the collected dataset to ascertain the most optimal algorithm for predicting crop growth and harvesting time, resulting in the selection of the Random Forest Regression model, which attains the highest model score of 86%. Upon its integration into the comprehensive system for monitoring new data and predicting fruit growth, the model achieves an impressive 98% accuracy score. Future endeavours for this project aim to enhance its applicability and predictive capabilities through the incorporation of diverse datasets from various plant species, the expansion of crop predictions to encompass the entire growth cycle, the integration of additional sensors, and the enhancement of the system's scalability to cover larger areas.

Item Type:	Article (Journal)
Uncontrolled Keywords:	IoTSmart farmingCrop predictionPrecision farmingMachine learning
Subjects:	S Agriculture > S Agriculture (General) S Agriculture > S Agriculture (General) > S494.5.S86 Sustainable agriculture
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering > Department of Mechatronics Engineering Kulliyyah of Engineering
Depositing User:	Dr. Syamsul Bahrin Abdul Hamid
Date Deposited:	18 Feb 2025 12:36
Last Modified:	18 Feb 2025 14:14
URI:	http://irep.iium.edu.my/id/eprint/119724

Actions (login required)

View Item