Fault identification with compressed sensing -
This webpage describes the
used in our work on fault identification with compressed sensing,
described in the following paper,
The software was written almost entirely by
Harel Avissar and
Danny's website describing our implementation appears
implemented the computation of the MMSE bound using results
from his work below with Guo and Shamai,
based on an earlier implementation by
for his work with
H. Avissar, and
"Fault Identification via Non-parametric Belief Propagation,"
IEEE Transactions on Signal Processing
vol. 59, no. 6, pp. 2602-2603, June 2011
The "new" files that we iplemented are highlighted below.
Several external files were kindy provided by other researchers,
as mentioned below.
D. Baron, and
"Single-letter Characterization of Signal Estimation
from Linear Measurements"
(pdf of talk; no paper).
D. Baron, and
"A Single-letter Characterization of Optimal
Noisy Compressed Sensing,"
Proceedings of the 47th Allerton Conference on Communication,
Control, and Computing,
Monticello, IL, September 2009
Any comments will be appreciated.
Dror Baron, July 2011
Feel free to also browse through other
software packages developed by our group.
Dror, October 2011
this subdirectory contains the computation of the theory for
minimum mean square error (MMSE) and bit error rate (BER).
Generate_SuccRate.m: generates figure 2,3,4,5
Generate_2D.m: generates figure 6
Generate_NBPvsIP.m: generates internal iteration comparison
Generate_Dongning_b.m: computes NBP to the info theoretic bound (figure 7)
L.m: computes the likelikhood
NBP.m: modified version for Non-Parametric BP which stored intermediate values
CoSaMP.m: Volkan Cevher.
GPSR_BB.m: (Copyright 2007) Mario Figueiredo, Robert Nowak, Stephen Wright.
hard_IO_Mterm.m: (Copyright 2007) Thomas Blumensath.
cgsolve.m: Justin Romberg.
armap_gabp.m: A. Zymnis.
Round_and_Local.m A. Zymnis.
Back to my homepage.