Dempster Shafer Theory

The importance of the Dempster-Shafer theory (DST) for modeling and propagating uncertainty has grown in the recent past. An obstacle for wider application of this theory in industrial practice is the lack of software support for analysts. The few tools available depend on floating point arithmetic and do not consider the inherently interval-based nature of the DST to the full extent. Therefore, we combine the DST ideas with those from interval arithmetic. An additional advantage of employing interval methods is the guarantee that the results obtained on a computer are mathematically correct. 


We developed a new verified DST implementation for MATLAB called DSI Toolbox which is based on the older software IPP Toolbox. DSI extends IPP using interval arithmetic and simultaneously takes care of the rounding errors.

 

Features (Beta Version)

Methods for constructing basic probability assignments (BPA):

  • Aggregation rules: Dempster's rule, (un)weighted mixing
  • Fast evaluation of (non-)monotonic system functions with Monte-Carlo sampling
  • Quantile-Quantile plots and plotting of BPAs
  • Verified results by using directed rounding and verified INTLAB functions
  • New: Verified fault tree analysis
Druckversion
@ Universität Duisburg-Essen, Fak. IngWi, Abt. INKO, Fachgebiet SCG Kontakt webmaster (at) inf.uni-due.de -- Login