Submit your articles to the African Journal of Biomedical Research, active in Scopus Q3 and Clarivate Web of Science Zoological Records. Click here to submit your manuscript.
Volume 11 (2024) | Issue 5
Volume 11 (2024) | Issue 5
Volume 11 (2024) | Issue 5
Volume 11 (2024) | Issue 5
Volume 11 (2024) | Issue 5
ABSTRACT Precision Agriculture (PA) is a trending research area since it provides a solution for increasing the productivity of farmlands using Internet of Things (IoT). This technique ensures that the farmland receives optimum amount of resources for maximum sustainability and profit using Information Technology. In this research, a novel methodology cloud enabled Internet of Things (IoT) integration and wireless sensor network is proposed for precision soil and water conservation agriculture (PSWCA) through machine learning. WSN comprises of a network of wireless sensors like moisture, temperature, ultrasonic, light detection sensors, soil nutrition sensor, etc. These sensors are used for determining optimum amount of water and fertilizer required by the plants. The entire framework with all the sensors and irrigation system was integrated using Arduino Uno Microcontroller and Raspberry Pi module. A novel Machine Learning based Automated Irrigation System using IoT (MLAIS-IoT) algorithm is proposed for Precision Soil and Water Conservation Agriculture (PSWCA). In this scheme, the machine learning algorithm embedded in the Raspberry Pi module is used to predict the amount of water and fertilizer required by the plants for irrigation. To validate the proposed methodology, the amount of water and fertilizer required using this MLAIS-IoT method is compared with that of scheduled and automatic irrigation. It was observed that, the proposed technique required lesser amount of water and fertilizer compared to that of scheduled and automatic irrigation. In this way, water logging can be avoided. This technology also aided in saving huge quantities of water. Thus, this system achieved optimum conservation based on the soil and climatic conditions as well. This also helps in achieving healthy growth of the plants. The experimental results prove that the logistic regression provide better efficiency and accuracy than other methodologies.