Conference Agenda

Given the increasing environmental crisis and the logistical challenges inherent in municipal solid waste management in modern cities, due to population growth and limitations in final disposal, it has become essential to evaluate advanced technological solutions. Therefore, this Systematic Literature Review (SLR) aimed to analyze and compare the performance of Artificial Intelligence (AI) algorithms applied to waste generation prediction, waste classification, and collection route optimization, against conventional methods. The methodology involved an SLR without meta-analysis, structured using the PICOC strategy and adhering to PRISMA guidelines, resulting in the selection of 56 studies from the Scopus and Scilit databases for synthesis. The findings revealed the consistent superiority of AI approaches. In the prediction domain, Deep Learning and Boosting models (XGBoost, DNN) achieved R² coefficients near 1.00 and predictive error reductions exceeding 40% compared to traditional linear regression. For classification, computer vision architectures like Swin Transformer V2 and hybrid CNN + Morph-HSV models achieved accuracies above 97% (up to 99.58%). In the logistics domain, metaheuristics such as I-ACO and PSO, integrated with IoT, demonstrated high operational efficiency, achieving average reductions of 25% to 42% in distance traveled, fuel consumption, and CO₂ emissions. It is concluded that AI is an essential tool for sustainability, demonstrating high adaptability in diverse urban contexts. However, critical challenges have been identified, such as methodological and metric heterogeneity in studies, which complicate generalization, and the persistent difficulty in discriminating waste based on visual similarity.