Revista: | Journal of applied research and technology |
Base de datos: | PERIÓDICA |
Número de sistema: | 000427678 |
ISSN: | 1665-6423 |
Autores: | Campos, Cintia Isabel de1 Santos, Murilo Castanho dos2 Pitombo, Cira Souza1 |
Instituciones: | 1Universidade de Sao Paulo, Escola de Engenharia de Sao Carlos, Sao Carlos, Sao Paulo. Brasil 2Universidade do Porto, Faculdade de Engenharia, Porto. Portugal |
Año: | 2018 |
Periodo: | Abr |
Volumen: | 16 |
Número: | 2 |
País: | México |
Idioma: | Inglés |
Tipo de documento: | Artículo |
Enfoque: | Aplicado, descriptivo |
Resumen en inglés | Road traffic accidents occur daily caused by different factors leading to varying degrees of injury severity. Considering this, many studies have been developed to identify and understand these factors to implement preventive actions. A Decisión Tree (DT) is one of the techniques that can genérate classifications and predictions by detecting a priori imknown patterns. This study aims to identify the characteristics of municipalities with high and very high fatality rates caused by traffic accidents, using a macro level dataset and a DT algorithm (CART - Classification And Regression Tree). Therefore, macro level data from the municipalities of Sao Paulo state (Brazil) were used, such as demographic and socioeconomic data, fatality rates and other variables related to traffic. The results indicated the Gross Domestic Product (GDP) as the most important variable, and the municipalities were characterized mainly considering the size of the highway network and vehicle ffeet (trucks, minibuses, cars, motorcycles). These characteristics could provide support to the government to plan mitigating actions in municipalities with the highest tendency to high traffic fatality rates |
Disciplinas: | Ingeniería |
Palabras clave: | Ingeniería de transportes, Urbanismo, Seguridad vial, Accidentes de tránsito, Planeación urbana |
Keyword: | Transportation engineering, Urbanism, Road safety, Traffic accidents, Urban planning |
Texto completo: | Texto completo (Ver HTML) Texto completo (Ver PDF) |