Organic and Recyclable Waste Classification Using Integrated Feature Selection Method

This paper suggests a new approach to enhancing waste classification performance using deep learning algorithms. Specifically, the proposed approach integrates an autoencoder network with a feature selection method in convolutional neural network models. This approach aims to identify valuable features from waste material images while reducing noise and improving the accuracy of the model. Autoencoder networks are utilised to learn a compressed representation of input data, which can be used as a feature vector for classification tasks. The feature selection method is then applied to remove irrelevant features, improving the accuracy of the model. The proposed approach has the potential to provide an efficient and effective solution for waste classification tasks, contributing to sustainable waste management and environmental conservation. Experimental results demonstrate the effectiveness of the proposed approach in enhancing the accuracy of waste classification tasks.