An Approach to Explore Historical Construction Accident Data Using Data Mining Techniques

• María Martínez Rojas ^[1] ; Antonio Trillo Cabello ^[1] ; Pardo Ferreira, M.ª del Carmen ^[1] ; Juan Carlos Rubio Romero ^[1]
  1. [1] Universidad de Málaga

     Universidad de Málaga

     Málaga, España

     
• Localización: Advances in engineering networks: proceedings of the 12th International Conference on Industrial Engineering and Industrial Management / Rodolfo de Castro Vila (ed. lit.), Gerusa Giménez Leal (ed. lit.), 2020, ISBN 978-3-030-44530-0, págs. 121-128
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Construction worksites are characterized by their dynamic and complex nature, making that work safety awareness a major concern during the project life cycle. In this regard, the analysis of historical data might be useful to identify the most frequent relationship between the variables of accidents in order to help safety practitioners in the task of prioritizing preventive actions. In this work, we propose an approach that will allow to explore unknown relations, expressed as association rules, among diverse variables from a database of construction accidents’ data. These association rules may be useful for efficient safety prevention and control.