Combined Modelling of Sparse and Dense noise improves Bayesian RVM
2014 (English)In: Proceedings of the 22nd European Signal Processing Conference (EUSIPCO), 2014, IEEE conference proceedings, 2014, 1841-1845 p.Conference paper, Abstract (Refereed)
Using a Bayesian approach, we consider the problem of recovering sparse signals under additive sparse and dense noise. Typically, sparse noise models outliers, impulse bursts or data loss. To handle sparse noise, existing methods simultaneously estimate sparse noise and sparse signal of interest. For estimating the sparse signal, without estimating the sparse noise, we construct a Relevance Vector Machine (RVM). In the RVM, sparse noise and ever present dense noise are treated through a combined noise model. Through simulations, we show the efficiency of new RVM for three applications: kernel regression, housing price prediction and compressed sensing.
Place, publisher, year, edition, pages
IEEE conference proceedings, 2014. 1841-1845 p.
Robust regression, Bayesian learning, Relevance vector machine, Compressed sensing
Research subject Electrical Engineering
IdentifiersURN: urn:nbn:se:kth:diva-165603OAI: oai:DiVA.org:kth-165603DiVA: diva2:808656
The 22nd European Signal Processing Conference (EUSIPCO), 1-5 Sep. 2014,Lisbon
QC 201505122015-04-292015-04-292015-10-20Bibliographically approved