Automatic Mass Waste Sorting System Using Inductive Proximity Sensor, Water Level Sensor and Image Processing using MobileNet Algorithm

Abstract

The global municipal solid waste is predicted to increase by threefold in 2050. Indonesia’s most wastes are unsorted and only end up in landfill and the waste management is less than ideal. An automatic mass waste sorting system is proposed to answer such problems. The automatic mass waste sorting system is designed to be able to identify and separate metal, plastic and organic waste using electrical sensors and image processing. The electrical sensors was able to identify waste types with 65% accuracy and the image processing system was able to identify waste types with 86.67% accuracy. The result doesn’t offer much advantage compared to other research on waste management system, however it is hoped that this research may inspire other researches on mass waste sorting systems.