DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Kyung-Su | ko |
dc.contributor.author | Chung, Sae-Young | ko |
dc.date.accessioned | 2019-10-02T10:20:31Z | - |
dc.date.available | 2019-10-02T10:20:31Z | - |
dc.date.created | 2019-10-01 | - |
dc.date.issued | 2019-10 | - |
dc.identifier.citation | IEEE SIGNAL PROCESSING LETTERS, v.26, no.10, pp.1506 - 1510 | - |
dc.identifier.issn | 1070-9908 | - |
dc.identifier.uri | http://hdl.handle.net/10203/267732 | - |
dc.description.abstract | We consider the problem of sparse phase retrieval from Fourier transform magnitudes to recover the k-sparse signal vector and its support T. We exploit extended support estimate epsilon with size larger than k satisfying epsilon superset of T and obtained by a trained deep neural network (DNN). To make the DNN learnable, it provides epsilon as the union of equivalent solutions of T by utilizing modulo Fourier invariances. Set epsilon can be estimated with short running time via the DNN, and support T can he determined from the DNN output rather than from the full index set by applying hard thresholding to epsilon. Thus, the DNN-based extended support estimation improves the reconstruction performance of the signal with a low complexity burden dependent on k. Numerical results verify that the proposed scheme has a superior performance with lower complexity compared to local search-based greedy sparse phase retrieval and a state-of-the-art variant of the Fienup method. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Fourier Phase Retrieval With Extended Support Estimation via Deep Neural Network | - |
dc.type | Article | - |
dc.identifier.wosid | 000485740400004 | - |
dc.identifier.scopusid | 2-s2.0-85072228898 | - |
dc.type.rims | ART | - |
dc.citation.volume | 26 | - |
dc.citation.issue | 10 | - |
dc.citation.beginningpage | 1506 | - |
dc.citation.endingpage | 1510 | - |
dc.citation.publicationname | IEEE SIGNAL PROCESSING LETTERS | - |
dc.identifier.doi | 10.1109/LSP.2019.2935814 | - |
dc.contributor.localauthor | Chung, Sae-Young | - |
dc.contributor.nonIdAuthor | Kim, Kyung-Su | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Deep neural network | - |
dc.subject.keywordAuthor | extended support estimation | - |
dc.subject.keywordAuthor | Fourier transform | - |
dc.subject.keywordAuthor | sparse phase retrieval | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.