Informationslogistik: IPP Toolbox
Imprecise Probability Propagation Toolbox (IPP Toolbox, version: 1.0
What is IPP Toolbox?
The IPP Toolbox is a collection of methods for uncertainty quantification and propagation using Dempster-Shafer Theory and imprecise probabilities. It runs under MATLAB 6.5 and higher.
Why IPP Toolbox?
The IPP Toolbox provides all necessary functions to conduct an uncertainty analysis in the imprecise probabilistic framework. For those, who are looking for an alternative method to probabilistic uncertainty modelling, the toolbox offers a set of helpful functions. Methods for the quantification of uncertainty by imprecise distributions and the propagation through complex system models are supported. This toolbox is a library of functions that are highly configurable to the user's needs. Uncertainty measures are included, as are sensitivity analysis methods. In the documentation section, some tutorials illustrate how to use the different functions.
IPP Toolbox Resources
IPP Toolbox Features
- Methods for constructing Dempster-Shafer structures (DSS) by different sampling strategies.
- Propagation methods using deterministic and Monte-Carlo sampling. Supports Matlab's optimization toolbox routines for solving nonlinear interval optimization problems.
- Input dependencies using Gaussian Copulas.
- Aggregation rules: Dempster's rule, Yager's rule, weighted mixing.
- Uncertainty measures.
- Sensitivity analysis.
- Plotting and size-reduction techniques
IPP Toolbox References
Fault tree analysis executed using the IPP Toolbox:
P. Limbourg, R. Savić, J. Petersen, H.-D. Kochs
Fault Tree Analysis in an Early Design Stage using the Dempster-Shafer Theory of Evidence
European Safety and Reliability Conference, ESREL 2007, pp. 713-722, Stavanger, Norway, (c) 2007 Taylor & Francis Group. Used with permission.
Matlab 6.5 or later running under any operating system (Linux, Windows, Unix, Macintosh). The Matlab optimization toolbox is recommended for complex nonlinear system functions.
The IPP Toolbox is under active open-source development. Features currently developed are enhanced visualization methods and support for sensitivity analysis. User-contributed features and suggestions are welcome. To make suggestions or participate in open-source development, please contact firstname.lastname@example.org
Please send comments and suggestions to email@example.com