TY  - JOUR
PY  - 2024//
TI  - Data mining of accidents in Spanish underground mines in the period 2003-2021 caused by a collision with a moving object
JO  - Heliyon
A1  - Sanmiquel, Lluis
A1  - Rossell, Josep M.
A1  - Bascompta, Marc
A1  - Vintró, Carla
A1  - Yousefian, Mohammad
SP  - e24716
EP  - e24716
VL  - 10
IS  - 2
N2  - 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.<p />  <p>Language: en</p>
LA  - en
SN  - 2405-8440
UR  - http://dx.doi.org/10.1016/j.heliyon.2024.e24716
ID  - ref1
ER  -