Abstract
In order to solve the problem of insufficient labeled samples in modulation recognition, this paper proposes a few-shot modulation recognition algorithm based on pseudo-label semi-supervised learning (pseudo-label algorithm). First of all, high quality artificial feature, excellent classifier and data-labeling method are used to build efficient pseudo label system, and then the pseudo label system is combined with signal classification method based on the deep learning to realize the modulation classification under the condition of a small number of labeled samples and a large number of unlabeled samples. The simulation results show that the pseudo-label algorithm can improve the model recognition performance by 5%-10% when the six kinds of digital signals are classified and identified and its SNR is greater than 5 dB. At the same time, the algorithm has a simple network design and is of great application value.
Highlights
ä¼Ŗę ē¾ē®ę³äøęčæ代å¢å ęę ē¾ę ·ę¬ę°é,å½ ęę ē¾ę ·ę¬ę°éę»”č¶³čæ代č¦ę±ę¶,čæå „ę·±åŗ¦å¦ä¹ č® ē»éØå,å°ęęåø¦ę ē¾ēę ·ę¬ę°ę®ē»åę°ēč®ē»é, ä½æēØåē±»č½åę“å¼ŗēę·±åŗ¦å¦ä¹ ē±»ę¹ę³åƹęęę ē¾ę · ę¬čæč”čåč®ē»,ęåå©ēØč®ē»å„½ēęØ”ååƹęµčÆäæ” å·čæč”é¢ęµć ę¬ęéå BP ē„ē»ē½ē»ä½äøŗēęä¼Ŗę ē¾ēé«ę§č½åē±»åØ,éå CNN å·ē§Æē„ē»ē½ē»ä½äøŗę·± åŗ¦å¦ä¹ ę¹ę³č®ē»ēå®ę ē¾ę ·ę¬äøä¼Ŗę ē¾ę ·ę¬ē åéć
å°(14) å¼åø¦å „ęę°ēµč®”ē®å ¬å¼,å³åÆå¾å°å„å¼ č°±ęę°ēµć ęę°ēµēč®”ē®å ¬å¼äøŗ: H = E[e1-pi] =
BP ē½ē»ē»ęå¦å¾ 3 ęē¤ŗ,ę¬ęč®¾č®”ē BP ē½ē» ē± 1 å±č¾å „å±,4 å±å Øčæę„å±ä»„å softmax åē±»åØę ę,č¾å „å±å¤§å°äøŗ 1ā13,åå«ä»£č”Ø 13 ē§äŗŗå·„ęå ēē¹å¾,åå Øčæę„å±ē„ē»å äøŖę°åå«äøŗ 16,32,64, 32,åē„ē»å åéēØ ReLU ęæę“»å½ę°ć äøŗęåē½ē»
Summary
č„æåå·„äø大å¦å¦ę„ Journal of Northwestern Polytechnical University https: / / doi.org / 10.1051 / jnwpu / 20203851074 ę č¦:éåƹęę ē¾ę ·ę¬č¾å°ę”件äøēéäæ”äæ”å·č°å¶čÆå«é®é¢,ęåŗäŗäøē§åŗäŗä¼Ŗę ē¾åēē£å¦ä¹ ę ęÆēå°ę ·ę¬č°å¶ę¹å¼åē±»ē®ę³,éčæä¼éäŗŗå·„ē¹å¾éćč®¾č®”é«ę§č½åē±»åØ仄ååŗäŗč¾åŗę¦ēēä¼Ŗę ē¾ ę°ę®éę©ę¹ę³,ęå»ŗé«ęēä¼Ŗę ē¾ę ę³Øē³»ē»,ē¶åéčæčÆ„ä¼Ŗę ē¾ę ę³Øē³»ē»äøåŗäŗę·±åŗ¦å¦ä¹ ēäæ”å·åē±» ę¹ę³é å,å®ē°åØå°éęę ē¾ę ·ę¬å大éę ę ē¾ę ·ę¬ę”件äøēč°å¶ę¹å¼åē±»ć ä»æēē»ęč”Øę,åƹ 6 ē§ ę°åäæ”å·čæč”č°å¶čÆå«,åØäæ”åŖęÆ大äŗ 5 dB ę¶,ä¼Ŗę ē¾ē®ę³åÆå°ęØ”åčÆå«ę§č½ęé« 5% ~ 10%,čÆ„ē®ę³ č®¾č®”ē®å,å ·ęč¾å¤§åŗēØä»·å¼ć å ³ é® čÆ:č°å¶čÆå«; ä¼Ŗę ē¾; åēē£å¦ä¹ äøå¾åē±»å·:TN975 ęē®ę åæē :A ęē« ē¼å·:1000ā2758(2020)05ā1074ā10
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.