Title :
Dynamic learning for cognitive radio sensing
Author :
Seung-Jun Kim ; Giannakis, Georgios
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Minnesota, Minneapolis, MN, USA
Abstract :
Spectrum sensing algorithms for cognitive radios that can interpolate and predict the spatio-temporal interference power distribution are proposed using the dictionary learning framework. The algorithms jointly estimate the dictionaries to capture the spatial spectrum measurements as well as their temporal dynamics via parsimoniously chosen atoms. Both batch and efficient online implementations are developed. Numerical tests verify the effectiveness of the novel approach.
Keywords :
cognitive radio; dictionaries; learning (artificial intelligence); radiofrequency interference; signal detection; cognitive radio sensing; dictionary learning framework; dynamic learning; spatiotemporal interference power distribution; spectrum sensing; temporal dynamics; Customer relationship management; Dictionaries; Robustness; Single photon emission computed tomography; Stacking;
Conference_Titel :
Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2013 IEEE 5th International Workshop on
Conference_Location :
St. Martin
Print_ISBN :
978-1-4673-3144-9
DOI :
10.1109/CAMSAP.2013.6714089
