Predictive Modeling for Soybean Germination Conditions Based on FNN and GPNN with Sensor-Based Data Analysis

Abstract

The rapid advancement of Internet of Things (IoT) technology has enabled the development of sophisticated electronic systems for concurrent environmental monitoring and data analysis. This paper presents an IoT-based electronic system designed to predict and classify germ development conditions based on weather parameters using machine learning techniques. The system integrates a network of sensors to continuously capture weather including temperature, humidity, air pressure, and other relevant environmental factors. The collected data is processed using a cloud-based machine learning model, which classifies conditions conducive to the growth and spread of germs.

By leveraging predictive algorithms, the system provides early warnings of potential germ outbreaks, which can be critical for applications in agriculture and healthcare. The model's accuracy is enhanced through the use of various classification techniques, including neural networks and decision trees, trained on historical weather and germ proliferation datasets. The system also offers real-time predictions and visual analytics, enabling decision-makers to implement timely preventive measures. The experimental results demonstrate the system's effectiveness in accurately predicting and classifying germ development conditions, showcasing the potential of IoT and machine learning in proactive environmental health monitoring