Citation

Sanmiquel L, Rossell JM, Bascompta M, Vintró C, Yousefian M. Heliyon 2024; 10(2): e24716.

Copyright

(Copyright © 2024, Elsevier Publishing)

DOI

10.1016/j.heliyon.2024.e24716

PMID

38312579

PMCID

PMC10835313

Abstract

Underground mining is currently one of the Spanish economic sectors with the worst accident rates. Besides, the most frequent type of accident, and with the most serious consequences, is the one in which the injured worker is hit by a moving object. For this reason, this study focuses on the analysis of this type of accident, divided into 3 subgroups to better understand the behavioural patterns. Data mining techniques were applied using the Apriori algorithm to extract as much information as possible about the genesis of these accidents. Similarly, each subset of accidents was processed in two different ways to improve the data analysis, depending on the causal variables used in each case, so that a study of six different scenarios was carried out. The five best association rules or behaviour patterns for each of the six scenarios are shown as a function of their frequency for each rule with 1-4 causal variables.

Language: en

Keywords

Data-mining; Mine drift; Type of accident (TA); Underground mining; Weka