FEATURE SELECTION FOR CYCLOSTATIONARY-BASED SIGNAL CLASSIFICATION
AffiliationUniversity of Arizona
MetadataShow full item record
RightsCopyright © held by the author; distribution rights International Foundation for Telemetering
Collection InformationProceedings from the International Telemetering Conference are made available by the International Foundation for Telemetering and the University of Arizona Libraries. Visit http://www.telemetry.org/index.php/contact-us if you have questions about items in this collection.
AbstractCognitive radio (CR) is a concept that imagines a radio (wireless transceiver) that contains an embedded intelligent agent that can adapt to its spectral environment. Using a software deﬁned radio (SDR), a radio can detect the presence of other users in the spectrum and adapt accordingly, but it is important in many applications to discern between individual transmitters and this can be done using signal classiﬁcation. The use of cyclostationary features have been shown to be robust to many common channel conditions. One such cyclostationary feature, the spectral correlation density(SCD),hasseenlimiteduseinsignalclassiﬁcationuntilnowbecauseitisacomputationally intensive process. This work demonstrates how feature selection techniques can be used to enable real-time classiﬁcation. The proposed technique is validated using 8 common modulation formats that are generated and collected over the air.
SponsorsInternational Foundation for Telemetering