Bibliographische Detailangaben
| 1. Verfasser: |
Bergamin, Mateus Zanatta |
| Publikationsdatum: |
2025 |
| Format: |
Bachelor thesis
|
| Sprache: |
por |
| Quelle: |
Repositório Institucional da UPF |
| Download full: |
https://repositorio.upf.br/handle/123456789/9533
|
Zusammenfassung: |
This study investigates the application of machine learning techniques to the clustering of georeferenced data, focusing on a case study related to the management of Municipal Solid Waste (MSW) in the state of Rio Grande do Sul, Brazil. Data from different towns in the area was merged with details about waste disposal sites, and clustering methods like K-Means, K-Nearest Neighbors (KNN), DBSCAN, and Random Forest were used. The objective was to identify coherent territorial groupings that could support more effective public policies. The resulting regionalizations were compared with a baseline study for validation and comparative analysis of the models. The results show that spatial clustering methods perform satisfactorily, with K-Means and DBSCAN standing out, demonstrating the potential of machine learning techniques in spatial analysis applied to georeferenced data. |
