Domestic Solid Waste Classification Using Convolutional Neural Networks

The overwhelming amount of household solid waste generated daily is alarming, and this contributes to the rise in pollution and drastic climate change. In such a context, automated waste classification at the initial stage of disposal can be an effective solution to separate recyclable items. Convolutional Neural Networks based on deep learning are often used for automated waste classification, but however, research works are limited to insufficient categories of waste such as the TrashNet dataset consisting of 2,527 images and 6 categories of waste. This dataset does not include other important categories such as battery, biological, and clothing items to reflect real-life environmental problems. Therefore, in this paper, a larger dataset consisting of 15,515 images and 12 categories of common household solid waste was used to evaluate the performance of DenseNet121, DenseNet169, EfficientNetB0, InceptionV3, MobileNetV2, ResNet50, VGG16, VGG19, and Xception Convolutional Neural Network models. Data augmentation was applied to solve the problem of class imbalance, and findings of my first research showed that the Xception model compiled with Adam optimiser outperformed all other models with an accuracy of 88.77% and an F1-score of 0.89. The performance of the model was improved to 89.57% with an F1-score of 0.90 when compiled with Nadam optimiser. However, further experimentation showed that the model did not generalise well despite reaching an accuracy of 93.42% and an F1-score of 0.93 when trained without data augmentation. This demonstrates the feasibility of the proposed model for real-life environmental problems.