Lopes, Arminda da Conceição dos Santos Guerra eMendonça, FábioRamos, Edgar Rui Lourenço Couchinho2024-09-132024-09-132024http://hdl.handle.net/10400.11/9155Dissertação apresentada à Escola Superior de Tecnologia do Instituto Politécnico de Castelo Branco para cumprimento dos requisitos necessários à obtenção do Grau de Mestre em Engenharia Informática - Desenvolvimento de Software e Sistemas Interativos.Artificial intelligence and environmental sustainability intersection has become a critical exploration domain in the contemporary era marked by rapid technological advancements and complex global challenges. This work focuses on the application of Machine Learning models, such as Regin-based Neural Networks (R-CNNs), Single Shot MultiBox Detectors (SSDs), and You Only Look Once (YOLO), to address the pressing issue of plastic waste management. By leveraging state-of-the-art computing technologies and Artificial Intelligence (AI), this research aims to enhance the efficiency and effectiveness of Plastic Waste (PW) identification, classification, and recycling processes. Considering the increasing environmental concerns and information processing potential, this thesis posits that advanced Machine Learning (ML) models can significantly contribute to more sustainable plastic waste management practices. Through systematic analysis of the performance of various ML models in detecting and classifying plastic waste, this study not only benchmarks the current state of the art but also illuminates pathways for future innovations in recycling technologies. Combining AI's analytical prowess with strategic waste management initiatives presents a promising frontier for mitigating environmental impacts, underscoring the thesis's commitment to harnessing technological evolution for the greater goodengArtificial IntelligenceMachine LearningRecyclingmaster thesis203697456