Estimation of microbial load in Ganoderma lucidum using a solar-electric hybrid dryer enhanced by machine learning and IoT

This study focuses on developing a hybrid-powered dryer that uses both solar and electric energy to dry Ganoderma lucidum mushrooms. Integrated with an Internet of Things (IoT) platform, the system enables real-time monitoring of temperature, time, and humidity. The analysis evaluated reductions in weight, moisture content, water activity, and microbial counts (bacteria, fungus, and yeast) across temperatures ranging from 40 °C to 80 °C over 480 min. The results indicated that higher temperatures, particularly 80 °C, were most effective in reducing microbial counts, achieving near-zero levels after 240 to 480 min. Machine learning (ML) models random forest regression (RFR), decision tree regression (DTR), and multiple linear regression (MLR) were trained to estimate microbial levels based on input variables such as time, temperature, and weight. RFR had the highest accuracy for estimating bacteria, while DTR excelled for fungus and yeast. However, MLR proved most suitable for IoT applications due to its simplicity in real-time implementation on devices. Therefore, the ML models were selected based on accuracy performance (RFR and DTR) and ease of integration into IoT systems (MLR). This study demonstrates the hybrid dryer's efficiency and the potential of ML models to optimize the drying process, contributing to energy efficiency and product quality control. Initially designed for small-scale on-farm use, the system also has the potential for future scaling to industrial processing facilities.