INORGANIC WASTE MULTI CLASSIFICATION SYSTEM USING TRANSFER LEARNING

Abstract

Waste management is one of the main challenges faced by society today in efforts to maintain environmental cleanliness and protect natural resources. Rapid population growth, lifestyle changes, and increased consumption have led to an increase in the volume of waste generated. Therefore, it is important to develop effective solutions for managing waste in order to achieve a clean and sustainable environment. Good waste management requires knowledge of waste classification, and with the help of Artificial Intelligence (AI), the process of waste classification can be done effectively. Therefore, this study aims to classification of 10 types of inorganic waste, including (battery, biological, cardboard, clothes, glass, metal, paper, plastic, shoes, and trash), using a Convolutional Neural Network (CNN) model designed with the ResNet-50 architecture. The training results of the ResNet-50 model with Adam optimizer and a learning rate of 0.00005 achieved an accuracy of 97.73%, indicating that it can effectively classify inorganic waste types.