Comparative Study of ML Algorithms for Garbage Classification

Abstract

In today's world, the escalating waste crisis demands effective garbage classification strategies. As population growth and evolving needs contribute to unprecedented waste generation, repurposing items through recycling, reproduction, or reuse becomes imperative. Proper garbage classification is pivotal in realizing these goals. This paper presents a concise yet comprehensive comparative study of machine learning algorithms for garbage classification. The primary objectives include comparing the performance of MobileNetV2, InceptionV3, and ResNet in garbage classification and scrutinizing optimal algorithms employed by researchers. The dataset comprises six garbage classes: cardboard, metal, paper, plastic, glass, and trash. Through rigorous evaluation, insights into algorithmic performance are presented. MobileNetV2 stands out, achieving a remarkable 94.48% accuracy on the validation set with minimal loss. InceptionV3 and ResNet50 yield accuracies of 86.08% and 88.54%, respectively. This study not only contributes to garbage classification knowledge but also highlights the real-world potential of the top-performing algorithm. As we address waste management complexities, this research signifies a step toward implementing efficient and accurate garbage classification systems for a sustainable future.