Details
| Original language | English |
|---|---|
| Pages (from-to) | 58-70 |
| Number of pages | 13 |
| Journal | Safety Science |
| Volume | 99 |
| Issue number | A |
| Early online date | 18 Mar 2017 |
| Publication status | Published - Nov 2017 |
Abstract
Major accidents are complex, multi-attribute events, originated from the interactions between intricate systems, cutting-edge technologies and human factors. Usually, these interactions trigger very particular accident sequences, which are hard to predict but capable of producing exacerbated societal reactions and impair communication channels among stakeholders. Thus, the purpose of this work is to convert high-dimensional accident data into a convenient graphical alternative, in order to overcome barriers to communicate risk and enable stakeholders to fully understand and learn from major accidents. This paper first discusses contemporary views and biases related to human errors in major accidents. The second part applies an artificial neural network approach to a major accident dataset, to disclose common patterns and significant features. The complex data will be then translated into 2-D maps, generating graphical interfaces which will produce further insight into the conditions leading to accidents and support a novel and comprehensive “learning from accidents” experience.
Keywords
- Accident analysis, Human factors, Learning from accidents, MATA-D, Self-organising maps
ASJC Scopus subject areas
- Engineering(all)
- Safety, Risk, Reliability and Quality
- Social Sciences(all)
- Safety Research
- Medicine(all)
- Public Health, Environmental and Occupational Health
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Safety Science, Vol. 99, No. A, 11.2017, p. 58-70.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Learning from major accidents
T2 - Graphical representation and analysis of multi-attribute events to enhance risk communication
AU - Moura, Raphael
AU - Beer, Michael
AU - Patelli, Edoardo
AU - Lewis, John
N1 - Funding information: The authors gratefully acknowledge the insights from Dr. Franz Knoll (NCK Inc.). This study was partially funded by CAPES [Grant n° 5959/13-6].
PY - 2017/11
Y1 - 2017/11
N2 - Major accidents are complex, multi-attribute events, originated from the interactions between intricate systems, cutting-edge technologies and human factors. Usually, these interactions trigger very particular accident sequences, which are hard to predict but capable of producing exacerbated societal reactions and impair communication channels among stakeholders. Thus, the purpose of this work is to convert high-dimensional accident data into a convenient graphical alternative, in order to overcome barriers to communicate risk and enable stakeholders to fully understand and learn from major accidents. This paper first discusses contemporary views and biases related to human errors in major accidents. The second part applies an artificial neural network approach to a major accident dataset, to disclose common patterns and significant features. The complex data will be then translated into 2-D maps, generating graphical interfaces which will produce further insight into the conditions leading to accidents and support a novel and comprehensive “learning from accidents” experience.
AB - Major accidents are complex, multi-attribute events, originated from the interactions between intricate systems, cutting-edge technologies and human factors. Usually, these interactions trigger very particular accident sequences, which are hard to predict but capable of producing exacerbated societal reactions and impair communication channels among stakeholders. Thus, the purpose of this work is to convert high-dimensional accident data into a convenient graphical alternative, in order to overcome barriers to communicate risk and enable stakeholders to fully understand and learn from major accidents. This paper first discusses contemporary views and biases related to human errors in major accidents. The second part applies an artificial neural network approach to a major accident dataset, to disclose common patterns and significant features. The complex data will be then translated into 2-D maps, generating graphical interfaces which will produce further insight into the conditions leading to accidents and support a novel and comprehensive “learning from accidents” experience.
KW - Accident analysis
KW - Human factors
KW - Learning from accidents
KW - MATA-D
KW - Self-organising maps
UR - http://www.scopus.com/inward/record.url?scp=85015390337&partnerID=8YFLogxK
U2 - 10.1016/j.ssci.2017.03.005
DO - 10.1016/j.ssci.2017.03.005
M3 - Article
AN - SCOPUS:85015390337
VL - 99
SP - 58
EP - 70
JO - Safety Science
JF - Safety Science
SN - 0925-7535
IS - A
ER -