<![CDATA[The conventional drying process of chili peppers (Capsicum frutescens) still faces challenges related to low energy efficiency and inconsistent product quality due to its dependence on weather conditions and limited control over environmental parameters. This study aims to optimize energy efficiency and the quality of dried chili peppers through the implementation of an intelligent Solar Tunnel Dryer (STD) system based on the Internet of Things (IoT) and Machine Learning (ML). The IoT system is designed to monitor environmental parameters in real time, including temperature, relative humidity, and solar radiation intensity, using DHT22 and LDR sensors integrated with an ESP32 microcontroller. The collected data are then analyzed using an exergy analysis approach to evaluate the thermodynamic performance of the drying system and modeled using a Machine Learning algorithm, namely the Random Forest Regressor, to predict energy efficiency and drying quality. The results indicate that the developed system is capable of significantly improving exergy efficiency and reducing the moisture content of chili peppers. Furthermore, the Machine Learning model demonstrates high predictive accuracy with low error values. This research is expected to provide a more efficient, intelligent, and sustainable solution for chili drying and to support the development of renewable energy–based post-harvest technologies.]]>
