MACHINE LEARNING IN PUBLIC SAFETY: AN ANALYSIS OF POSSIBLE MECHANICAL PROBLEMS IN POLICE VEHICLES

Authors

  • Ronnie Carlos Tavares Nunes UFSC https://orcid.org/0000-0002-2373-511X
  • Alexandre Leopoldo Gonçalves Universidade Federal de Santa Catarina
  • Bartholomeo Oliveira Barcelos Universidade Federal de Santa Catarina (UFSC)

DOI:

https://doi.org/10.48090/ciki.v1i1.1290

Keywords:

artificial intelligence, public security, operational vehicles, text analysis

Abstract

The purpose of this paper is to identify the feasibility of applying artificial intelligence tools to detect possible vehicular problems, reported by police officers, that have the potential to cause serious accidents. Machine learning was used as a tool to analyze textual data extracted from the system Computerized Daily Part, a system used by the Federal Highway Police that registers operational data. The methodology used employs the supervised learning approach. The results indicated the viability of the tool, and the Logistic Regression algorithm presented the best result, with an accuracy of 0.835. However, the study highlighted the need for a robust data set to train the machine learning algorithm.

Published

2023-02-15

How to Cite

Nunes, R. C. T., Gonçalves, A. L., & Barcelos, B. O. . (2023). MACHINE LEARNING IN PUBLIC SAFETY: AN ANALYSIS OF POSSIBLE MECHANICAL PROBLEMS IN POLICE VEHICLES. International Congress of Knowledge and Innovation - Ciki, 1(1). https://doi.org/10.48090/ciki.v1i1.1290

Most read articles by the same author(s)

1 2 > >>