TY - JOUR
T1 - Smart waste classification in IoT-enabled smart cities using VGG16 and Cat Swarm Optimized random forest
AU - Gaurav, Akshat
AU - Gupta, Brij Bhooshan
AU - Arya, Varsha
AU - Attar, Razaz Waheeb
AU - Bansal, Shavi
AU - Alhomoud, Ahmed
AU - Chui, Kwok Tai
N1 - Publisher Copyright:
© 2025 Gaurav et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
PY - 2025/2
Y1 - 2025/2
N2 - Effective waste management is becoming a crucial component of sustainable urban development as smart technologies are used by smart cities more and more. Smart trash categorization systems provided by IoT may greatly enhance garbage sorting and recycling mechanisms. In this context, this work presents a waste categorization model based on transfer learning using the VGG16 model for feature extraction and a Random Forest classifier tuned by Cat Swarm Optimization (CSO). On a Kaggle garbage categorization dataset, the model outperformed conventional models like SVM, XGBoost, and logistic regression. With an accuracy of 85% and a high AUC of 0.85 the Random Forest model shows better performance in precision, recall, and F1-score as compared to standard machine learning models.
AB - Effective waste management is becoming a crucial component of sustainable urban development as smart technologies are used by smart cities more and more. Smart trash categorization systems provided by IoT may greatly enhance garbage sorting and recycling mechanisms. In this context, this work presents a waste categorization model based on transfer learning using the VGG16 model for feature extraction and a Random Forest classifier tuned by Cat Swarm Optimization (CSO). On a Kaggle garbage categorization dataset, the model outperformed conventional models like SVM, XGBoost, and logistic regression. With an accuracy of 85% and a high AUC of 0.85 the Random Forest model shows better performance in precision, recall, and F1-score as compared to standard machine learning models.
UR - https://www.scopus.com/pages/publications/105000023598
U2 - 10.1371/journal.pone.0316930
DO - 10.1371/journal.pone.0316930
M3 - Article
C2 - 40019915
AN - SCOPUS:105000023598
VL - 20
JO - PLoS ONE
JF - PLoS ONE
IS - 2 February
M1 - e0316930
ER -
