Publication

Abstract : In recent years, artificial intelligence (AI) and the Internet of Things (IoT) have become increasingly popular topics in the tech world, as many fields recognise the potential that these technologies offer for improved efficiency and productivity. Specifically, AI and IoT have been used in agriculture to help increase crop yield, conserve water and energy, reduce environmental risks, and analyse data for more precise decision-making. Intelligent sensor techniques make it possible to collect data in real time, which gives farmers valuable information about the soil, water levels, and other factors that affect crop health. Due to human errors and the poor performance of sensors, current soil management systems are unable to provide an accurate forecast of the soil conditions and require further development in order to increase their accuracy. IoT is commonly used for soil monitoring. At the same time, the IoT cannot predict soil fertility or advise farmers on nutrition levels on its own. In order to address these issues, soil management systems need to be enhanced with the integration of AI algorithms and machine learning techniques. In this chapter, an upgraded multilayer perceptron (MLP) model is proposed to enhance the soil management system. The model is based on data collected from an IoT-enabled soil monitoring system. The performance of the proposed methodology is assessed through the use of various evaluation metrics, including mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE), as well as several statistical tests. The experimental outcomes indicate that the MLP model proposed in this study outperforms traditional machine learning algorithms.