printlogo
http://www.ethz.ch/
Professur für Risiko und Sicherheit
 
print
  

Bayesian networks and Bayesian hierarchical analysis in engineering

PhD Seminar Autumn Semester 2009

Prof. Dr. Marc Maes, Prof. Dr. Michael Havbro Faber and Kazuyoshi Nishijima

101-1110-00L Probabilistics in Engineering
Wednesday 16:45-18:00, HIL E 6

 

Mode

The seminar will be conducted as a study group under the responsibility of Prof. Faber. All participants will in turn be responsible for presenting a part of the material and for developing the example. Self study, presentations and discussions will constitute main components of the course.

Who should attend?

Researchers, Ph. D. students, post-docs and graduate students as well as practitioners interested in the probabilistic assessment of natural hazard events and the applications to engineering decision making. No experience on the assessment of natural hazard events is required. The participants should, however, have basic skills for probability calculations.

Assistant

Kazuyoshi Nishijima
nishijima@ibk.baug.ethz.ch 044 633 43 16
HIL E 22.3

Agenda

Date Topic Lecturer Presentations
30.09.09

Introduction

Prof. M. Maes
K. Nishijima
Seminar introduction
07.10.09

BN* 1: model building

K. Nishijima Presentation
14.10.09
BN 2: decision making A. Anders Presentation
Example
21.10.09 Variability within multi-component systems
(+ easy application using HBM**)
S. Zhang Presentation
28.10.09 Spatial GLM*** networks and hierarchies
(+ easy application in human error analysis)
K. Kraemer
E. Sabiote
Presentation
Winbugs file
04.11.09 Spatial discrete hazards using HBM
(+ easy application in accident)
M. Graf Presentation
Winbugs files
11.11.09 No seminar    
18.11.09 Spatial variability: classical vs Bayesian
kriging (+ easy application in simple
geostatistics using HBM)
T. Doppler Presentation
25.11.09 No seminar    
02.12.09 Hazard modeling using BN and HBM
(+ easy application on earthquakes)
K. Nishijima Presentation
Winbugs file
09.12.09 HBM for environmental problems
(+ easy application)
A. Qureshi
A. Erath
Presentation
16.12.09 Session 1 HBM for noisy/dirty data in integrity and
lifetime extension assessment
(+ easy application in pipeline deterioration)
M. Sandomeer Presentation
16.12.09 Session 2 HBM for extremes G. Fink
J. Braendle
H. Narasimhan
R. Jockwer
J. Vuillaume
F. Rhys

     

(BN*: Bayesian network, HBN**: Hierarchical Bayesian model, GLM***: Generalized linear model.)

 

Wichtiger Hinweis:
Diese Website wird in älteren Versionen von Netscape ohne graphische Elemente dargestellt. Die Funktionalität der Website ist aber trotzdem gewährleistet. Wenn Sie diese Website regelmässig benutzen, empfehlen wir Ihnen, auf Ihrem Computer einen aktuellen Browser zu installieren. Weitere Informationen finden Sie auf
folgender Seite.

Important Note:
The content in this site is accessible to any browser or Internet device, however, some graphics will display correctly only in the newer versions of Netscape. To get the most out of our site we suggest you upgrade to a newer browser.
More information

© 2015 ETH Zürich | Impressum | Disclaimer | 17.12.2009
top