dc.contributor.author | Pinto-Orellana, Marco Antonio | |
dc.contributor.author | Hammer, Hugo Lewi | |
dc.date.accessioned | 2021-01-31T10:43:36Z | |
dc.date.accessioned | 2021-03-08T18:19:36Z | |
dc.date.available | 2021-01-31T10:43:36Z | |
dc.date.available | 2021-03-08T18:19:36Z | |
dc.date.issued | 2020-08-27 | |
dc.identifier.citation | Pinto-Orellana, Hammer. Dyadic Aggregated Autoregressive Model (DASAR) for Automatic Modulation Classification. IEEE Access. 2020 | en |
dc.identifier.issn | 2169-3536 | |
dc.identifier.uri | https://hdl.handle.net/10642/9929 | |
dc.description.abstract | In this article, we presented a novel spectral estimation method, the dyadic aggregated autoregressive model (DASAR), that characterizes the spectrum dynamics of a modulated signal. DASAR enhances automatic modulation classification (AMC) on environments where new or unknown modulation techniques are introduced, and only size-restricted data is accessible to train classification algorithms. A key component for obtaining efficient machine learning-based classification is the development of valuable knowledge-descriptive features. DASAR constructs a multi-level spectral representation by subdividing a signal into successive dyadic segments where each partition is modeled as an aggregation of single-frequency autoregressive processes. Thus, the model ensures a robust representation at the segment level, while the multi-level decomposition can capture time-varying spectra. As a feature extraction model, DASAR can provide useful learning features related to signals with complex spectra. The effectiveness of our model was tested on a dataset comprised of 11 different modulation techniques and realistic transmission medium characteristics. Using only 200 128-point samples per modulation scheme (1% of the available signal samples) and a proper selection of a classification algorithm, DASAR reaches accuracy up to 70.96% compared with a maximum accuracy of 43.62% using the state-of-art methods tested under the same conditions. | en |
dc.description.sponsorship | This work was supported by the Research Council of Norway to Project 273599, ‘Patient-Centric Engineering in Rehabilitation (PACER).’ | en |
dc.language.iso | en | en |
dc.publisher | IEEE | en |
dc.relation.ispartofseries | IEEE Access;Volume 8 | |
dc.rights | Creative Commons Attribution 4.0 International (CC BY 4.0) License | en |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
dc.subject | Automatic modulation classifications | en |
dc.subject | Signal processing | en |
dc.subject | Spectrum modeling | en |
dc.subject | Autoregressive models | en |
dc.subject | Machine learning | en |
dc.title | Dyadic Aggregated Autoregressive Model (DASAR) for Automatic Modulation Classification | en |
dc.type | Journal article | en |
dc.type | Peer reviewed | en |
dc.date.updated | 2021-01-31T10:43:36Z | |
dc.description.version | publishedVersion | en |
dc.identifier.doi | https://doi.org/10.1109/ACCESS.2020.3019243 | |
dc.identifier.cristin | 1827332 | |
dc.source.journal | IEEE Access | |
dc.relation.projectID | Norges forskningsråd: 273599 | |