Design and Implementation of an IoT-based Automatic Waste Sorting System using ESP-32, Proximity Sensors, and Firebase

Abstract

Waste management remains a significant environmental challenge due to the low level of public awareness in sorting waste according to its type. Improper waste segregation reduces recycling efficiency and increases the amount of waste disposed of in landfills. This study proposes the design and implementation of an Internet of Things (IoT)-based automatic waste sorting system using an ESP32-S microcontroller. The system is capable of classifying waste into three categories, namely metal, organic, and inorganic waste. Waste identification is performed using a combination of photoelectric, inductive proximity, and capacitive proximity sensors, while HC-SR04 ultrasonic sensors are utilized to monitor the capacity of each waste compartment. The sorting mechanism is controlled by MG996R servo motors, and the collected data are transmitted to Firebase Realtime Database for real-time monitoring through a Kodular-based Android application. The system was developed using the Agile methodology and evaluated through black-box testing. Experimental results show that the proposed system achieved a maximum classification accuracy of 85%. In addition, the ultrasonic sensor demonstrated stable distance measurement performance with an average error below 0.6 cm. The integration of Firebase and Kodular enabled real-time monitoring of waste classification results and bin status. Therefore, the proposed system can improve waste management efficiency and has potential applications in smart waste management for both household and public environments.