Abstract | ||
---|---|---|
We propose and design two classes of robust subspace classifiers for classification of multidimensional signals. Our classifiers are based on robust M-estimators and the least-median-of-squares principle, and we show that they may be unified as iterated reweighted oblique subspace classifiers. The performance of the proposed classifiers are demonstrated by two examples: noncoherent detection of space-time frequency-shift keying signals, and shape classification of partially occluded two-dimensional (2-D)_ objects. In both cases, the proposed robust subspace classifiers outperform the conventional subspace classifiers |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/TSP.2006.887560 | IEEE Transactions on Signal Processing |
Keywords | Field | DocType |
conventional subspace classifier,least-median-of-squares principle,shape recognition,robust estimation,proposed classifier,iterated reweighted oblique subspace,robust multidimensional matched subspace,proposed robust subspace classifier,weighted least-squares,robust m-estimators,robust subspace classifier,index terms—noncoherent receivers,noncoherent detection,subspace classification.,shape classification,multidimensional signal,frequency shift keying,gaussian noise,weighted least squares,indexing terms,pattern recognition,detectors,multidimensional signal processing,robust estimator,interference,shape,signal detection,multidimensional systems | Least squares,Multidimensional signal processing,Weighting,Detection theory,Subspace topology,Pattern recognition,Iterative method,Random subspace method,Keying,Artificial intelligence,Mathematics | Journal |
Volume | Issue | ISSN |
55 | 3 | 1053-587X |
Citations | PageRank | References |
5 | 0.63 | 16 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Arnt-Brre Salberg | 1 | 5 | 0.63 |
Alfred Hanssen | 2 | 134 | 17.48 |
Louis L. Scharf | 3 | 2525 | 414.45 |