Page 241 - Contributed Paper Session (CPS) - Volume 2

CPS1845 Devni P.S. et al.
From Figure 3 we can conclude that the level of damage to buildings for
state Slight, Moderate, and Heavy are 35.46%, 35.14%, and 29.4%
respectively.

4. Discussion and Conclusion
We can conclude from the results section above that the formation of the
BN model is faster and more efficient with the role of bnlearn and GeNIe
packages. Package bnlearn is an R package that is very suitable for dealing
with cases of analysis in experimental data. For both discrete and continuous
data, as well as combination data, this package is very flexible to use. This
package is good for learning structure and parameters. Whereas GeNIe, the
Graphical Network Interface, is designed to enhance the appearance of BN
Models. This software can also increase flexibility for model. Users can also use
GeNIe to choose alternative decisions that have the highest profit or utility
expected.

References
1. Bayraktarli, Y. Y., Ulfkjaer, J. P., Yazgan, U., & Faber, M. H. (2005). On the
application of Bayesian probabilistic networks for earthquake risk
management. Safety and reliability of engineering systems and
structures : proceedings of the Ninth International Conference on
Structural Safety and Reliability (hal. 3505-3512). Rome: Millpress.
2. Bayraktarli, Y., Baker, J., & Faber, M. (2011). Uncertainty treatment in
earthquake modeling using Bayesian probabilistic networks. Georisk,
5(1), 44-58.
3. Blaser, L., Ohrnberger, M., Riggelsen, C., Babeyko, A., & & Scherbaum, F.
(2011). Bayesian networks for tsunami early warning. Geophysical
Journal International, 185(3), 1431–1443. doi:10.1111/j.1365-
246X.2011.05020.x

4. Druzdzel, M., & Flynn, R. (2002). Decision Support Systems. Encyclopedia
of Library and Information Science (2nd ed.). New York: Marcel Dekker,
Inc.
5. Fenton, N., & Neil, M. (2013). Risk Assessment and Decision Analysis with
Bayesian Networks. CRC Press.
6. Flores, M. J., Nicholson, A. E., Brunskill, A., Korb, K. B., & Mascaro, S.
(2011). Incorporating expert knowledge when learning Bayesian network
structure: A medical case study. Artificial Intelligence In Medicine, 53,
181– 204.
7. Li, L., Wang, J.-F., & Leung, H. (2010). Using spatial analysis and Bayesian
network to model the vulnerability and make insurance pricing of

230 | I S I W S C 2 0 1 9