IoT Data Analysis for Predicting Bacillus Levels by using Recurrent Neural Network

Abstract: This study explores IoT data analysis for predicting Bacillus levels in turmeric farms, utilizing Recurrent Neural Networks (RNNs) to enhance soil health and crop management. IoT sensors collect real-time soil parameters, including moisture, pH, temperature, and electrical conductivity, which serve as input features for predictive modelling. Initial regression models establish baseline relationships between these parameters and Bacillus levels. Subsequently, RNNs are employed to capture temporal patterns and dependencies in the data, improving prediction accuracy over time. The findings indicate that RNNs significantly outperform traditional machine learning approaches, particularly in scenarios with limited data. This research highlights the potential of IoT and advanced deep learning techniques in automating Bacillus monitoring and enhancing crop health management in turmeric farming.