Select Lab Publications

Fault identification via non-parametric belief propagation (2011)

By: D. Bickson, D. Baron, A. Ihler, H. Avissar, and D. Dolev

Abstract: We consider the problem of identifying a pattern of faults from a set of noisy linear measurements. Unfortunately, maximum a posteriori probability estimation of the fault pattern is computationally intractable. To solve the fault identification problem, we propose a non-parametric belief propagation approach. We show empirically that our belief propagation solver is more accurate than recent state-of-the-art algorithms including interior point methods and semidefinite programming. Our superior performance is explained by the fact that we take into account both the binary nature of the individual faults and the sparsity of the fault pattern arising from their rarity.

Download Information
D. Bickson, D. Baron, A. Ihler, H. Avissar, and D. Dolev (2011). "Fault identification via non-parametric belief propagation." IEEE Tran. on Signal Processing. pdf            
BibTeX citation

title="Fault identification via non-parametric belief propagation",
author = "D. Bickson and D. Baron and A. Ihler and H. Avissar and D. Dolev",
booktitle= "IEEE Tran. on Signal Processing",
year = "2011",
wwwfilebase = {tsp11-bickson},
wwwtopic = {Graphical Models},

full list