Electromagnetic Signal Classification Based on Deep Sparse Capsule Networks

dc.contributor.authorLiu, Mingqianen
dc.contributor.authorLiao, Guiyueen
dc.contributor.authorYang, Zhutianen
dc.contributor.authorSong, Haoen
dc.contributor.authorGong, Fengkuien
dc.contributor.departmentElectrical and Computer Engineeringen
dc.date.accessioned2019-08-14T14:59:15Zen
dc.date.available2019-08-14T14:59:15Zen
dc.date.issued2019en
dc.description.abstractIn complex electromagnetic environments, electromagnetic signal classification rates are low as long time have to be the cost to extract features. To cope with the issue, in this paper, an electromagnetic signal classification method is proposed based on deep sparse capsule networks. In the proposed method, received signals are frequency reduced and sampled processing first. Subsequently, a cross ambiguity function based on linear canonical transformation, a cross ambiguity function based on linear canonical domain, and higher-order spectrum are estimated, respectively. The maximum value of each section of the cross ambiguity function is combined with the maximum value of equally spaced cross sections of higher order amplitude spectrum to obtain the two-dimensional feature information. Finally, electromagnetic signals are classified by the deep sparse capsule networks. The simulation results show that the proposed method not only has good classification performance but also can automatically get a hierarchical feature representation by learning. Moreover, the corresponding time cost can be effectively reduced.en
dc.description.notesThis work was supported in part by the National Natural Science Foundation of China under Grant 61501348, Grant 61601145, and Grant 61801363, in part by the Shaanxi Provincial Key Research and Development Program Grant 2019GY-043, in part by the Joint Fund of Ministry of Education of the People's Republic of China under Grant 6141A02022338, in part by the China Postdoctoral Science Foundation under Grant 2017M611912, in part by the Jiangsu Planned Projects for Postdoctoral Research Funds under Grant 1701059B, in part by the 111 Project under Grant B08038, and in part by the China Scholarship Council under Grant 201806965031.en
dc.description.sponsorshipNational Natural Science Foundation of China [61501348, 61601145, 61801363]; Shaanxi Provincial Key Research and Development Program [2019GY-043]; Ministry of Education of the People's Republic of China [6141A02022338]; China Postdoctoral Science Foundation [2017M611912]; Jiangsu Planned Projects for Postdoctoral Research Funds [1701059B]; 111 Project [B08038]; China Scholarship Council [201806965031]en
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.1109/ACCESS.2019.2924798en
dc.identifier.eissn2169-3536en
dc.identifier.urihttp://hdl.handle.net/10919/93125en
dc.identifier.volume7en
dc.language.isoenen
dc.publisherIEEEen
dc.rightsCreative Commons Attribution 3.0 Unporteden
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/en
dc.subjectSignal classificationen
dc.subjectcapsule networksen
dc.subjectsparse filteringen
dc.subjectcross ambiguity functionen
dc.subjecthigher order amplitude spectrumen
dc.titleElectromagnetic Signal Classification Based on Deep Sparse Capsule Networksen
dc.title.serialIEEE Accessen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
dc.type.dcmitypeStillImageen
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
08744513.pdf
Size:
6.82 MB
Format:
Adobe Portable Document Format
Description: