One of the great challenges of the information age is to transform information into knowledge. In this context, there has been impressive progress in data mining and machine learning in recent years. Machine learning, synthesis of statistics, information theory and computation has created a solid science with a firm mathematical base and with very powerful tools seeking to solve this challenge. Given this, data mining appears as the extraction of implicit information, previously unknown and potentially useful. The main objective of this work was to use the database of the Traffic Department of the Federal Highway Police and to build associations of traffic accidents seeking regularities or standards, using the free software Weka. We used accident data from BR-316 in the state of Pará between January 2007 and September 2018. The knowledge discovery occurred through association rules generated by the free software Weka through the Apriori algorithm. The program's statistical results generated graphs that show the factors that contributed the most to traffic accidents on the BR-316 highway in the last decade. The results indicate that in the initial kilometers of the captain Pedro Teixeira highway (BR-316) in Pará and more precisely in kilometers 0 and 8, in the daytime, and in the municipalities of Ananindeua, Marituba and Castanhal there is a high rate of traffic accidents.
|
