AI-Enabled Waste Classification as a Data-Driven Decision Support Tool for Circular Economy and Urban Sustainability

TL;DR

This study compares traditional machine learning and deep learning models for waste classification, demonstrating that transfer learning models like DenseNet121 significantly improve accuracy and can support real-time waste sorting in smart cities.

Contribution

The paper evaluates various ML and deep learning models for waste classification and demonstrates the effectiveness of transfer learning models in real-time waste sorting applications.

Findings

DenseNet121 achieved 91% accuracy and 0.98 ROC-AUC.

Transfer learning models outperform traditional classifiers by 20 percentage points.

PCA has negligible impact on classical models but transfer learning benefits from limited data.

Abstract

Efficient waste sorting is crucial for enabling circular-economy practices and resource recovery in smart cities. This paper evaluates both traditional machine-learning (Random Forest, SVM, AdaBoost) and deep-learning techniques including custom CNNs, VGG16, ResNet50, and three transfer-learning models (DenseNet121, EfficientNetB0, InceptionV3) for binary classification of 25 077 waste images (80/20 train/test split, augmented and resized to 150x150 px). The paper assesses the impact of Principal Component Analysis for dimensionality reduction on traditional models. DenseNet121 achieved the highest accuracy (91 %) and ROC-AUC (0.98), outperforming the best traditional classifier by 20 pp. Principal Component Analysis (PCA) showed negligible benefit for classical methods, whereas transfer learning substantially improved performance under limited-data conditions. Finally, we outline how these models integrate into a real-time Data-Driven Decision Support System for automated waste sorting, highlighting potential reductions in landfill use and lifecycle environmental impacts.)