Deep radio signal clustering with interpretability analysis based on saliency map

With the development of information technology, radio communication technology has made rapid progress. Many radio signals that have appeared in space are difficult to classify without manually labeling. Unsupervised radio signal clustering methods have recently become an urgent need for this situat...

Full description

Saved in:
Bibliographic Details
Published in:Digital communications and networks Vol. 10; no. 5; pp. 1448 - 1458
Main Authors: Zhou, Huaji, Bai, Jing, Wang, Yiran, Ren, Junjie, Yang, Xiaoniu, Jiao, Licheng
Format: Journal Article
Language:English
Published: Elsevier B.V 01.10.2024
KeAi Communications Co., Ltd
Subjects:
ISSN:2352-8648, 2352-8648
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract With the development of information technology, radio communication technology has made rapid progress. Many radio signals that have appeared in space are difficult to classify without manually labeling. Unsupervised radio signal clustering methods have recently become an urgent need for this situation. Meanwhile, the high complexity of deep learning makes it difficult to understand the decision results of the clustering models, making it essential to conduct interpretable analysis. This paper proposed a combined loss function for unsupervised clustering based on autoencoder. The combined loss function includes reconstruction loss and deep clustering loss. Deep clustering loss is added based on reconstruction loss, which makes similar deep features converge more in feature space. In addition, a features visualization method for signal clustering was proposed to analyze the interpretability of autoencoder utilizing Saliency Map. Extensive experiments have been conducted on a modulated signal dataset, and the results indicate the superior performance of our proposed method over other clustering algorithms. In particular, for the simulated dataset containing six modulation modes, when the SNR is 20 ​dB, the clustering accuracy of the proposed method is greater than 78%. The interpretability analysis of the clustering model was performed to visualize the significant features of different modulated signals and verified the high separability of the features extracted by clustering model.
AbstractList With the development of information technology, radio communication technology has made rapid progress. Many radio signals that have appeared in space are difficult to classify without manually labeling. Unsupervised radio signal clustering methods have recently become an urgent need for this situation. Meanwhile, the high complexity of deep learning makes it difficult to understand the decision results of the clustering models, making it essential to conduct interpretable analysis. This paper proposed a combined loss function for unsupervised clustering based on autoencoder. The combined loss function includes reconstruction loss and deep clustering loss. Deep clustering loss is added based on reconstruction loss, which makes similar deep features converge more in feature space. In addition, a features visualization method for signal clustering was proposed to analyze the interpretability of autoencoder utilizing Saliency Map. Extensive experiments have been conducted on a modulated signal dataset, and the results indicate the superior performance of our proposed method over other clustering algorithms. In particular, for the simulated dataset containing six modulation modes, when the SNR is 20 ​dB, the clustering accuracy of the proposed method is greater than 78%. The interpretability analysis of the clustering model was performed to visualize the significant features of different modulated signals and verified the high separability of the features extracted by clustering model.
Author Wang, Yiran
Ren, Junjie
Jiao, Licheng
Yang, Xiaoniu
Bai, Jing
Zhou, Huaji
Author_xml – sequence: 1
  givenname: Huaji
  surname: Zhou
  fullname: Zhou, Huaji
  email: 19172110640@stu.xidian.edu.cn
  organization: School of Artificial Intelligence, Xidian University, Xi'an, 710071, China
– sequence: 2
  givenname: Jing
  orcidid: 0000-0001-5412-7793
  surname: Bai
  fullname: Bai, Jing
  email: baijing@mail.xidian.edu.cn
  organization: School of Artificial Intelligence, Xidian University, Xi'an, 710071, China
– sequence: 3
  givenname: Yiran
  surname: Wang
  fullname: Wang, Yiran
  email: yrwang_xd@stu.xidian.edu.cn
  organization: School of Artificial Intelligence, Xidian University, Xi'an, 710071, China
– sequence: 4
  givenname: Junjie
  surname: Ren
  fullname: Ren, Junjie
  email: renjunjie@stu.xidian.edu.cn
  organization: School of Artificial Intelligence, Xidian University, Xi'an, 710071, China
– sequence: 5
  givenname: Xiaoniu
  surname: Yang
  fullname: Yang, Xiaoniu
  email: yxn2117@126.com
  organization: Science and Technology on Communication Information Security Control Laboratory, Jiaxing, 314033, China
– sequence: 6
  givenname: Licheng
  surname: Jiao
  fullname: Jiao, Licheng
  email: lchjiao@xidian.edu.cn
  organization: School of Artificial Intelligence, Xidian University, Xi'an, 710071, China
BookMark eNp9UNtKAzEQDVLBWvsDPuUHWnPZSxZ8kXorFETQ5zCbTGrKdrckq7J_b9aK-CQMzMxhzpmZc04mbdciIZecLTnjxdVuaQ20S8GEXDKegp2QqZC5WKgiU5M_9RmZx7hjjPFKsExmU_J8i3igAazvaPTbFhpqmvfYY_Dtln76_o36NnWHgD3UvvH9QCFNDdFHWkNES7uWRmg8tmagezhckFMHTcT5T56R1_u7l9XjYvP0sF7dbBZGFrxflFlRSVsKhzLjStVSGmHLonaqNI45mYMFp2ydYy2sUlCCzZ2CSmFR2SpTckbWR13bwU4fgt9DGHQHXn8DXdhqCL03DWoJDpwQVZYzlhkFyubMCp6AWjmels2IOGqZ0MUY0P3qcaZHj_VOjx7r0WPNeAqWSNdHEqYvPzwGHc3oAlof0PTpDP8f_QvrUYeh
Cites_doi 10.1109/TCCN.2020.3024610
10.23919/JCC.2020.10.011
10.12700/APH.15.8.2018.8.2
10.1016/j.patcog.2018.05.019
10.1002/nav.20053
10.1016/j.cja.2021.08.016
10.1016/j.cja.2021.07.014
10.1007/s11222-007-9033-z
10.1109/COMST.2018.2871099
10.23915/distill.00010
10.1109/TCCN.2020.3023145
10.1109/TNN.2005.845141
10.1109/JSAC.2017.2692307
10.1109/TII.2022.3171349
10.1109/JSEN.2021.3113376
10.1109/TVCG.2016.2598831
10.1016/j.neunet.2020.07.005
10.1109/TNN.2008.2005601
10.1109/TR.2021.3062045
10.1109/TKDE.2010.165
10.1109/MWC.2017.1600304WC
10.4208/cicp.OA-2020-0085
ContentType Journal Article
Copyright 2024 Chongqing University of Posts and Telecommunications
Copyright_xml – notice: 2024 Chongqing University of Posts and Telecommunications
DBID 6I.
AAFTH
AAYXX
CITATION
DOA
DOI 10.1016/j.dcan.2023.01.010
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DOAJ Directory of Open Access Journals (ODIN)
DatabaseTitle CrossRef
DatabaseTitleList

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2352-8648
EndPage 1458
ExternalDocumentID oai_doaj_org_article_3afaf22945004c8a8d50d21294b8f10f
10_1016_j_dcan_2023_01_010
S2352864823000238
GroupedDBID 0R~
0SF
4.4
457
5VS
6I.
AACTN
AAEDW
AAFTH
AALRI
AAXUO
ABMAC
ADBBV
ADEZE
ADVLN
AEXQZ
AFTJW
AGHFR
AITUG
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
BCNDV
EBS
EJD
FDB
GROUPED_DOAJ
IPNFZ
KQ8
M41
NCXOZ
O9-
OK1
RIG
ROL
SSZ
-SI
-S~
AAYWO
AAYXX
CAJEI
CITATION
Q--
U1G
U5S
ID FETCH-LOGICAL-c361t-74693d72fe34188b33c2d76bf87cf0f35adaf8db5eb2d88a7ad5f8a98e69d9483
IEDL.DBID DOA
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001359011500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2352-8648
IngestDate Fri Oct 03 12:15:30 EDT 2025
Sat Nov 29 05:53:42 EST 2025
Sat Nov 09 16:00:29 EST 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 5
Keywords Clustering features visualization
Unsupervised radio signal clustering
Autoencoder
Deep learning interpretability
Language English
License This is an open access article under the CC BY-NC-ND license.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c361t-74693d72fe34188b33c2d76bf87cf0f35adaf8db5eb2d88a7ad5f8a98e69d9483
ORCID 0000-0001-5412-7793
OpenAccessLink https://doaj.org/article/3afaf22945004c8a8d50d21294b8f10f
PageCount 11
ParticipantIDs doaj_primary_oai_doaj_org_article_3afaf22945004c8a8d50d21294b8f10f
crossref_primary_10_1016_j_dcan_2023_01_010
elsevier_sciencedirect_doi_10_1016_j_dcan_2023_01_010
PublicationCentury 2000
PublicationDate October 2024
2024-10-00
2024-10-01
PublicationDateYYYYMMDD 2024-10-01
PublicationDate_xml – month: 10
  year: 2024
  text: October 2024
PublicationDecade 2020
PublicationTitle Digital communications and networks
PublicationYear 2024
Publisher Elsevier B.V
KeAi Communications Co., Ltd
Publisher_xml – name: Elsevier B.V
– name: KeAi Communications Co., Ltd
References MacQueen (bib13) 1967; vol. 1
Huaji, Jing, Yiran, Licheng, Zheng, Weiguo, Jie, Xiaoniu (bib37) 2022; 35
Khorov, Kiryanov, Lyakhov, Bianchi (bib39) 2018; 21
Nguyen, Bui, Duong, Bui, Luu (bib10) 2021
G. Chen, Deep Learning with Nonparametric Clustering, arXiv preprint arXiv:1501.03084.
Li, Zhao, Zhou, Ding, Chen, Wang, Zhang (bib2) 2017; 24
Zhou, Khosla, Lapedriza, Oliva, Torralba (bib24) 2016
Yu, Li (bib3) 2021; 21
Xu, Wunsch (bib12) 2005; 16
Ribeiro, Singh, Guestrin (bib31) 2016
Qi, Zhou, Zheng, Li (bib38) 2020; 7
Cai, He, Han (bib40) 2010; 23
Yang, Fu, Sidiropoulos, Hong (bib16) 2017
Selvaraju, Cogswell, Das, Vedantam, Parikh, Batra (bib25) 2017
Mrabah, Khan, Ksantini, Lachiri (bib17) 2020; 130
Olah, Satyanarayan, Johnson, Carter, Schubert, Ye, Mordvintsev (bib30) 2018; 3
Yang, Parikh, Batra (bib36) 2016
Lin, Tu, Dou, Chen, Mao (bib6) 2020; 7
Li, Qiao, Zhang (bib35) 2018; 83
Ramaswamy (bib28) 2020
Zhou, Jiao, Zheng, Yang, Shen, Yang (bib5) 2020; 17
Chattopadhay, Sarkar, Howlader, Balasubramanian (bib26) 2018
Ya, Yun, Haoran, Zhang, Yu, Guan, Shiwen (bib7) 2022; 35
Von Luxburg (bib14) 2007; 17
Garson (bib22) 1991; 6
Yao, Newson, Gousseau, Hellier (bib9) 2021
Zhang, Yun, Ya, Mao (bib8) 2020; 41
Kuhn (bib42) 2005; 52
Lundberg, Lee (bib23) 2017
Xu (bib33) 2020; 28
Estévez, Tesmer, Perez, Zurada (bib41) 2009; 20
Zhang, Yang, Ma, Wu (bib19) 2019
Pinaya, Vieira, Garcia-Dias, Mechelli (bib15) 2020
Wang, Wang, Du, Yang, Zhang, Ding, Mardziel, Hu (bib27) 2020
Wang, Lin, Tian, Si (bib4) 2021; 70
Károly, Fullér, Galambos (bib11) 2018; 15
Liu, Shi, Li, Li, Zhu, Liu (bib29) 2016; 23
Shafi, Molisch, Smith, Haustein, Zhu, De Silva, Tufvesson, Benjebbour, Wunder (bib1) 2017; 35
M. R. Zafar, N. M. Khan, Dlime: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems, arXiv preprint arXiv:1906.10263.
Zeiler, Fergus (bib20) 2014
Bai, Wang, Xiao, Alazab (bib18) 2022; 18
J. T. Springenberg, A. Dosovitskiy, T. Brox, M. Riedmiller, Striving for Simplicity: the All Convolutional Net, arXiv preprint arXiv:1412.6806.
Yang (10.1016/j.dcan.2023.01.010_bib16) 2017
Yu (10.1016/j.dcan.2023.01.010_bib3) 2021; 21
Bai (10.1016/j.dcan.2023.01.010_bib18) 2022; 18
Zhou (10.1016/j.dcan.2023.01.010_bib24) 2016
Yang (10.1016/j.dcan.2023.01.010_bib36) 2016
Xu (10.1016/j.dcan.2023.01.010_bib12) 2005; 16
Garson (10.1016/j.dcan.2023.01.010_bib22) 1991; 6
Zeiler (10.1016/j.dcan.2023.01.010_bib20) 2014
Olah (10.1016/j.dcan.2023.01.010_bib30) 2018; 3
Wang (10.1016/j.dcan.2023.01.010_bib27) 2020
Cai (10.1016/j.dcan.2023.01.010_bib40) 2010; 23
Li (10.1016/j.dcan.2023.01.010_bib2) 2017; 24
Károly (10.1016/j.dcan.2023.01.010_bib11) 2018; 15
Shafi (10.1016/j.dcan.2023.01.010_bib1) 2017; 35
10.1016/j.dcan.2023.01.010_bib34
Liu (10.1016/j.dcan.2023.01.010_bib29) 2016; 23
10.1016/j.dcan.2023.01.010_bib32
Ya (10.1016/j.dcan.2023.01.010_bib7) 2022; 35
Khorov (10.1016/j.dcan.2023.01.010_bib39) 2018; 21
Yao (10.1016/j.dcan.2023.01.010_bib9) 2021
Selvaraju (10.1016/j.dcan.2023.01.010_bib25) 2017
Zhang (10.1016/j.dcan.2023.01.010_bib8) 2020; 41
Zhang (10.1016/j.dcan.2023.01.010_bib19) 2019
Lin (10.1016/j.dcan.2023.01.010_bib6) 2020; 7
Xu (10.1016/j.dcan.2023.01.010_bib33) 2020; 28
Qi (10.1016/j.dcan.2023.01.010_bib38) 2020; 7
Ramaswamy (10.1016/j.dcan.2023.01.010_bib28) 2020
Li (10.1016/j.dcan.2023.01.010_bib35) 2018; 83
Pinaya (10.1016/j.dcan.2023.01.010_bib15) 2020
Von Luxburg (10.1016/j.dcan.2023.01.010_bib14) 2007; 17
Zhou (10.1016/j.dcan.2023.01.010_bib5) 2020; 17
Huaji (10.1016/j.dcan.2023.01.010_bib37) 2022; 35
Kuhn (10.1016/j.dcan.2023.01.010_bib42) 2005; 52
MacQueen (10.1016/j.dcan.2023.01.010_bib13) 1967; vol. 1
Chattopadhay (10.1016/j.dcan.2023.01.010_bib26) 2018
Lundberg (10.1016/j.dcan.2023.01.010_bib23) 2017
10.1016/j.dcan.2023.01.010_bib21
Ribeiro (10.1016/j.dcan.2023.01.010_bib31) 2016
Nguyen (10.1016/j.dcan.2023.01.010_bib10) 2021
Mrabah (10.1016/j.dcan.2023.01.010_bib17) 2020; 130
Estévez (10.1016/j.dcan.2023.01.010_bib41) 2009; 20
Wang (10.1016/j.dcan.2023.01.010_bib4) 2021; 70
References_xml – volume: 15
  start-page: 29
  year: 2018
  end-page: 53
  ident: bib11
  article-title: Unsupervised clustering for deep learning: a tutorial survey
  publication-title: Acta Polytechnica Hungarica.
– volume: 35
  start-page: 35
  year: 2022
  end-page: 48
  ident: bib7
  article-title: Large-scale real-world radio signal recognition with deep learning
  publication-title: Chin. J. Aeronaut.
– start-page: 193
  year: 2020
  end-page: 208
  ident: bib15
  article-title: Autoencoders
  publication-title: Machine Learning
– start-page: 24
  year: 2020
  end-page: 25
  ident: bib27
  article-title: Score-cam: score-weighted visual explanations for convolutional neural networks
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
– volume: 17
  start-page: 395
  year: 2007
  end-page: 416
  ident: bib14
  article-title: A tutorial on spectral clustering
  publication-title: Stat. Comput.
– start-page: 1135
  year: 2016
  end-page: 1144
  ident: bib31
  article-title: Why should i trust you?” explaining the predictions of any classifier
  publication-title: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
– start-page: 5147
  year: 2016
  end-page: 5156
  ident: bib36
  article-title: Joint unsupervised learning of deep representations and image clusters
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– volume: 35
  start-page: 49
  year: 2022
  end-page: 57
  ident: bib37
  article-title: Few-shot electromagnetic signal classification: a data union augmentation method
  publication-title: Chin. J. Aeronaut.
– volume: 23
  start-page: 902
  year: 2010
  end-page: 913
  ident: bib40
  article-title: Locally consistent concept factorization for document clustering
  publication-title: IEEE Trans. Knowl. Data Eng.
– volume: 18
  start-page: 7910
  year: 2022
  end-page: 7919
  ident: bib18
  article-title: Rffae-s: autoencoder based on random fourier feature with separable loss for unsupervised signal modulation clustering
  publication-title: IEEE Trans. Ind. Inf.
– start-page: 618
  year: 2017
  end-page: 626
  ident: bib25
  article-title: Grad-cam: visual explanations from deep networks via gradient-based localization
  publication-title: Proceedings of the IEEE International Conference on Computer Vision
– volume: 6
  start-page: 46
  year: 1991
  end-page: 51
  ident: bib22
  article-title: Interpreting Neural Network Connection Weights
  publication-title: AI Expert
– volume: 130
  start-page: 206
  year: 2020
  end-page: 228
  ident: bib17
  article-title: Deep clustering with a dynamic autoencoder: from reconstruction towards centroids construction
  publication-title: Neural Network.
– volume: 21
  start-page: 24440
  year: 2021
  end-page: 24452
  ident: bib3
  article-title: An accurate wifi indoor positioning algorithm for complex pedestrian environments
  publication-title: IEEE Sensor. J.
– volume: vol. 1
  start-page: 281
  year: 1967
  end-page: 297
  ident: bib13
  article-title: Some methods for classification and analysis of multivariate observations
  publication-title: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability
– start-page: 6261
  year: 2019
  end-page: 6270
  ident: bib19
  article-title: Interpreting cnns via decision trees
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 17
  start-page: 157
  year: 2020
  end-page: 169
  ident: bib5
  article-title: Generative adversarial network-based electromagnetic signal classification: a semi-supervised learning framework
  publication-title: Chin. Commun.
– volume: 52
  start-page: 7
  year: 2005
  end-page: 21
  ident: bib42
  article-title: The Hungarian method for the assignment problem
  publication-title: Nav. Res. Logist.
– volume: 7
  start-page: 34
  year: 2020
  end-page: 46
  ident: bib6
  article-title: Contour stella image and deep learning for signal recognition in the physical layer
  publication-title: IEEE Trans. Cognitive Commun. Network.
– start-page: 818
  year: 2014
  end-page: 833
  ident: bib20
  article-title: Visualizing and understanding convolutional networks
  publication-title: European Conference on Computer Vision
– start-page: 4768
  year: 2017
  end-page: 4777
  ident: bib23
  article-title: A unified approach to interpreting model predictions
  publication-title: Proceedings of the 31st International Conference on Neural Information Processing Systems
– volume: 7
  start-page: 21
  year: 2020
  end-page: 33
  ident: bib38
  article-title: Automatic modulation classification based on deep residual networks with multimodal information
  publication-title: IEEE Trans. Cognitive Commun. Network.
– start-page: 10847
  year: 2021
  end-page: 10856
  ident: bib10
  article-title: Clusformer: a transformer based clustering approach to unsupervised large-scale face and visual landmark recognition
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 83
  start-page: 161
  year: 2018
  end-page: 173
  ident: bib35
  article-title: Discriminatively boosted image clustering with fully convolutional auto-encoders
  publication-title: Pattern Recogn.
– volume: 24
  start-page: 175
  year: 2017
  end-page: 183
  ident: bib2
  article-title: Intelligent 5g: when cellular networks meet artificial intelligence
  publication-title: IEEE Wireless Commun.
– start-page: 3861
  year: 2017
  end-page: 3870
  ident: bib16
  article-title: Towards k-means-friendly spaces: simultaneous deep learning and clustering
  publication-title: International Conference on Machine Learning
– reference: M. R. Zafar, N. M. Khan, Dlime: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems, arXiv preprint arXiv:1906.10263.
– start-page: 13789
  year: 2021
  end-page: 13798
  ident: bib9
  article-title: A latent transformer for disentangled face editing in images and videos
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision
– reference: J. T. Springenberg, A. Dosovitskiy, T. Brox, M. Riedmiller, Striving for Simplicity: the All Convolutional Net, arXiv preprint arXiv:1412.6806.
– reference: G. Chen, Deep Learning with Nonparametric Clustering, arXiv preprint arXiv:1501.03084.
– start-page: 983
  year: 2020
  end-page: 991
  ident: bib28
  article-title: Ablation-cam: visual explanations for deep convolutional network via gradient-free localization
  publication-title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
– start-page: 2921
  year: 2016
  end-page: 2929
  ident: bib24
  article-title: Learning deep features for discriminative localization
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– volume: 16
  start-page: 645
  year: 2005
  end-page: 678
  ident: bib12
  article-title: Survey of clustering algorithms
  publication-title: IEEE Trans. Neural Network.
– volume: 21
  start-page: 197
  year: 2018
  end-page: 216
  ident: bib39
  article-title: A tutorial on ieee 802.11 ax high efficiency wlans
  publication-title: IEEEn Commun. Survey Tutorial.
– volume: 20
  start-page: 189
  year: 2009
  end-page: 201
  ident: bib41
  article-title: Normalized mutual information feature selection
  publication-title: IEEE Trans. Neural Network.
– volume: 70
  start-page: 790
  year: 2021
  end-page: 807
  ident: bib4
  article-title: Transfer learning promotes 6g wireless communications: recent advances and future challenges
  publication-title: IEEE Trans. Reliab.
– start-page: 839
  year: 2018
  end-page: 847
  ident: bib26
  article-title: Grad-cam++: generalized gradient-based visual explanations for deep convolutional networks
  publication-title: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE
– volume: 3
  start-page: e10
  year: 2018
  ident: bib30
  article-title: The building blocks of interpretability
  publication-title: Distill
– volume: 28
  start-page: 1746
  year: 2020
  end-page: 1767
  ident: bib33
  article-title: Frequency principle: fourier analysis sheds light on deep neural networks
  publication-title: Commun. Comput. Phys.
– volume: 41
  start-page: 12
  year: 2020
  end-page: 21
  ident: bib8
  article-title: Electromagnetic signal modulation recognition technology based on lightweight deep neural network
  publication-title: J. Commun.
– volume: 35
  start-page: 1201
  year: 2017
  end-page: 1221
  ident: bib1
  article-title: 5g: a tutorial overview of standards, trials, challenges, deployment, and practice
  publication-title: IEEE J. Sel. Area. Commun.
– volume: 23
  start-page: 91
  year: 2016
  end-page: 100
  ident: bib29
  article-title: Towards better analysis of deep convolutional neural networks
  publication-title: IEEE Trans. Visual. Comput. Graph.
– volume: 7
  start-page: 34
  issue: 1
  year: 2020
  ident: 10.1016/j.dcan.2023.01.010_bib6
  article-title: Contour stella image and deep learning for signal recognition in the physical layer
  publication-title: IEEE Trans. Cognitive Commun. Network.
  doi: 10.1109/TCCN.2020.3024610
– volume: 17
  start-page: 157
  issue: 10
  year: 2020
  ident: 10.1016/j.dcan.2023.01.010_bib5
  article-title: Generative adversarial network-based electromagnetic signal classification: a semi-supervised learning framework
  publication-title: Chin. Commun.
  doi: 10.23919/JCC.2020.10.011
– volume: 41
  start-page: 12
  issue: 11
  year: 2020
  ident: 10.1016/j.dcan.2023.01.010_bib8
  article-title: Electromagnetic signal modulation recognition technology based on lightweight deep neural network
  publication-title: J. Commun.
– volume: 15
  start-page: 29
  issue: 8
  year: 2018
  ident: 10.1016/j.dcan.2023.01.010_bib11
  article-title: Unsupervised clustering for deep learning: a tutorial survey
  publication-title: Acta Polytechnica Hungarica.
  doi: 10.12700/APH.15.8.2018.8.2
– volume: 83
  start-page: 161
  year: 2018
  ident: 10.1016/j.dcan.2023.01.010_bib35
  article-title: Discriminatively boosted image clustering with fully convolutional auto-encoders
  publication-title: Pattern Recogn.
  doi: 10.1016/j.patcog.2018.05.019
– volume: 52
  start-page: 7
  issue: 1
  year: 2005
  ident: 10.1016/j.dcan.2023.01.010_bib42
  article-title: The Hungarian method for the assignment problem
  publication-title: Nav. Res. Logist.
  doi: 10.1002/nav.20053
– volume: 35
  start-page: 35
  issue: 9
  year: 2022
  ident: 10.1016/j.dcan.2023.01.010_bib7
  article-title: Large-scale real-world radio signal recognition with deep learning
  publication-title: Chin. J. Aeronaut.
  doi: 10.1016/j.cja.2021.08.016
– ident: 10.1016/j.dcan.2023.01.010_bib21
– start-page: 193
  year: 2020
  ident: 10.1016/j.dcan.2023.01.010_bib15
  article-title: Autoencoders
– volume: 35
  start-page: 49
  issue: 9
  year: 2022
  ident: 10.1016/j.dcan.2023.01.010_bib37
  article-title: Few-shot electromagnetic signal classification: a data union augmentation method
  publication-title: Chin. J. Aeronaut.
  doi: 10.1016/j.cja.2021.07.014
– start-page: 839
  year: 2018
  ident: 10.1016/j.dcan.2023.01.010_bib26
  article-title: Grad-cam++: generalized gradient-based visual explanations for deep convolutional networks
– volume: 17
  start-page: 395
  issue: 4
  year: 2007
  ident: 10.1016/j.dcan.2023.01.010_bib14
  article-title: A tutorial on spectral clustering
  publication-title: Stat. Comput.
  doi: 10.1007/s11222-007-9033-z
– start-page: 818
  year: 2014
  ident: 10.1016/j.dcan.2023.01.010_bib20
  article-title: Visualizing and understanding convolutional networks
– start-page: 2921
  year: 2016
  ident: 10.1016/j.dcan.2023.01.010_bib24
  article-title: Learning deep features for discriminative localization
– volume: 21
  start-page: 197
  issue: 1
  year: 2018
  ident: 10.1016/j.dcan.2023.01.010_bib39
  article-title: A tutorial on ieee 802.11 ax high efficiency wlans
  publication-title: IEEEn Commun. Survey Tutorial.
  doi: 10.1109/COMST.2018.2871099
– start-page: 3861
  year: 2017
  ident: 10.1016/j.dcan.2023.01.010_bib16
  article-title: Towards k-means-friendly spaces: simultaneous deep learning and clustering
– start-page: 10847
  year: 2021
  ident: 10.1016/j.dcan.2023.01.010_bib10
  article-title: Clusformer: a transformer based clustering approach to unsupervised large-scale face and visual landmark recognition
– start-page: 1135
  year: 2016
  ident: 10.1016/j.dcan.2023.01.010_bib31
  article-title: Why should i trust you?” explaining the predictions of any classifier
– volume: 3
  start-page: e10
  issue: 3
  year: 2018
  ident: 10.1016/j.dcan.2023.01.010_bib30
  article-title: The building blocks of interpretability
  publication-title: Distill
  doi: 10.23915/distill.00010
– start-page: 4768
  year: 2017
  ident: 10.1016/j.dcan.2023.01.010_bib23
  article-title: A unified approach to interpreting model predictions
– volume: 7
  start-page: 21
  issue: 1
  year: 2020
  ident: 10.1016/j.dcan.2023.01.010_bib38
  article-title: Automatic modulation classification based on deep residual networks with multimodal information
  publication-title: IEEE Trans. Cognitive Commun. Network.
  doi: 10.1109/TCCN.2020.3023145
– start-page: 6261
  year: 2019
  ident: 10.1016/j.dcan.2023.01.010_bib19
  article-title: Interpreting cnns via decision trees
– volume: 6
  start-page: 46
  issue: 4
  year: 1991
  ident: 10.1016/j.dcan.2023.01.010_bib22
  article-title: Interpreting Neural Network Connection Weights
  publication-title: AI Expert
– volume: vol. 1
  start-page: 281
  year: 1967
  ident: 10.1016/j.dcan.2023.01.010_bib13
  article-title: Some methods for classification and analysis of multivariate observations
– start-page: 5147
  year: 2016
  ident: 10.1016/j.dcan.2023.01.010_bib36
  article-title: Joint unsupervised learning of deep representations and image clusters
– volume: 16
  start-page: 645
  issue: 3
  year: 2005
  ident: 10.1016/j.dcan.2023.01.010_bib12
  article-title: Survey of clustering algorithms
  publication-title: IEEE Trans. Neural Network.
  doi: 10.1109/TNN.2005.845141
– start-page: 24
  year: 2020
  ident: 10.1016/j.dcan.2023.01.010_bib27
  article-title: Score-cam: score-weighted visual explanations for convolutional neural networks
– volume: 35
  start-page: 1201
  issue: 6
  year: 2017
  ident: 10.1016/j.dcan.2023.01.010_bib1
  article-title: 5g: a tutorial overview of standards, trials, challenges, deployment, and practice
  publication-title: IEEE J. Sel. Area. Commun.
  doi: 10.1109/JSAC.2017.2692307
– volume: 18
  start-page: 7910
  issue: 11
  year: 2022
  ident: 10.1016/j.dcan.2023.01.010_bib18
  article-title: Rffae-s: autoencoder based on random fourier feature with separable loss for unsupervised signal modulation clustering
  publication-title: IEEE Trans. Ind. Inf.
  doi: 10.1109/TII.2022.3171349
– volume: 21
  start-page: 24440
  issue: 21
  year: 2021
  ident: 10.1016/j.dcan.2023.01.010_bib3
  article-title: An accurate wifi indoor positioning algorithm for complex pedestrian environments
  publication-title: IEEE Sensor. J.
  doi: 10.1109/JSEN.2021.3113376
– start-page: 983
  year: 2020
  ident: 10.1016/j.dcan.2023.01.010_bib28
  article-title: Ablation-cam: visual explanations for deep convolutional network via gradient-free localization
– volume: 23
  start-page: 91
  issue: 1
  year: 2016
  ident: 10.1016/j.dcan.2023.01.010_bib29
  article-title: Towards better analysis of deep convolutional neural networks
  publication-title: IEEE Trans. Visual. Comput. Graph.
  doi: 10.1109/TVCG.2016.2598831
– volume: 130
  start-page: 206
  year: 2020
  ident: 10.1016/j.dcan.2023.01.010_bib17
  article-title: Deep clustering with a dynamic autoencoder: from reconstruction towards centroids construction
  publication-title: Neural Network.
  doi: 10.1016/j.neunet.2020.07.005
– ident: 10.1016/j.dcan.2023.01.010_bib32
– start-page: 618
  year: 2017
  ident: 10.1016/j.dcan.2023.01.010_bib25
  article-title: Grad-cam: visual explanations from deep networks via gradient-based localization
– ident: 10.1016/j.dcan.2023.01.010_bib34
– volume: 20
  start-page: 189
  issue: 2
  year: 2009
  ident: 10.1016/j.dcan.2023.01.010_bib41
  article-title: Normalized mutual information feature selection
  publication-title: IEEE Trans. Neural Network.
  doi: 10.1109/TNN.2008.2005601
– start-page: 13789
  year: 2021
  ident: 10.1016/j.dcan.2023.01.010_bib9
  article-title: A latent transformer for disentangled face editing in images and videos
– volume: 70
  start-page: 790
  issue: 2
  year: 2021
  ident: 10.1016/j.dcan.2023.01.010_bib4
  article-title: Transfer learning promotes 6g wireless communications: recent advances and future challenges
  publication-title: IEEE Trans. Reliab.
  doi: 10.1109/TR.2021.3062045
– volume: 23
  start-page: 902
  issue: 6
  year: 2010
  ident: 10.1016/j.dcan.2023.01.010_bib40
  article-title: Locally consistent concept factorization for document clustering
  publication-title: IEEE Trans. Knowl. Data Eng.
  doi: 10.1109/TKDE.2010.165
– volume: 24
  start-page: 175
  issue: 5
  year: 2017
  ident: 10.1016/j.dcan.2023.01.010_bib2
  article-title: Intelligent 5g: when cellular networks meet artificial intelligence
  publication-title: IEEE Wireless Commun.
  doi: 10.1109/MWC.2017.1600304WC
– volume: 28
  start-page: 1746
  issue: 5
  year: 2020
  ident: 10.1016/j.dcan.2023.01.010_bib33
  article-title: Frequency principle: fourier analysis sheds light on deep neural networks
  publication-title: Commun. Comput. Phys.
  doi: 10.4208/cicp.OA-2020-0085
SSID ssj0001920434
Score 2.3033605
Snippet With the development of information technology, radio communication technology has made rapid progress. Many radio signals that have appeared in space are...
SourceID doaj
crossref
elsevier
SourceType Open Website
Index Database
Publisher
StartPage 1448
SubjectTerms Autoencoder
Clustering features visualization
Deep learning interpretability
Unsupervised radio signal clustering
Title Deep radio signal clustering with interpretability analysis based on saliency map
URI https://dx.doi.org/10.1016/j.dcan.2023.01.010
https://doaj.org/article/3afaf22945004c8a8d50d21294b8f10f
Volume 10
WOSCitedRecordID wos001359011500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2352-8648
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001920434
  issn: 2352-8648
  databaseCode: DOA
  dateStart: 20150101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA4iHvQgPnF9kYM3qbabpEmOvhZPi4LC3kKe0EW7yz4E_72Tprv0pBehpzZMwkzINynffIPQVWGICJqyzAJcZLTwNNPMmMwHrWNjWOJ4ajbBh0MxGsmXTquvyAlL8sDJcbdEBx36fUkZhNMKLRzLHZy3khoRijzE0zfnsnOZGqe8JaeEtlUyidDlYK03sVt4o9MZS2Y7SNQI9ncAqQMygz2022aH-C6tah9t-PoA7XQ0Aw_R66P3UzzTrprgSL6A4fZjGeUO4DOOv1VxtSYSNszXb6xb5REcMcvhSY3nkH7Hokv8qadH6H3w9PbwnLV9ETJLymKRcbjSgg_7wQMECWEIsX3HSxMEtyEPhGmng3CGwa3ZCaG5diwILYUvpZNUkGO0WU9qf4JwHKhLa6kNYNVwYcCck6GEPApwq-yh65WP1DTJX6gVL2ysokdV9KjKC3jyHrqPblyPjNLVzQsIqGoDqv4KaA-xVRBUmwUkdAdT1S-Tn_7H5GdoG0zSxNY7R5uL2dJfoC37tajms8tmj_0AdsnXFA
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Deep+radio+signal+clustering+with+interpretability+analysis+based+on+saliency+map&rft.jtitle=Digital+communications+and+networks&rft.au=Huaji+Zhou&rft.au=Jing+Bai&rft.au=Yiran+Wang&rft.au=Junjie+Ren&rft.date=2024-10-01&rft.pub=KeAi+Communications+Co.%2C+Ltd&rft.eissn=2352-8648&rft.volume=10&rft.issue=5&rft.spage=1448&rft.epage=1458&rft_id=info:doi/10.1016%2Fj.dcan.2023.01.010&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_3afaf22945004c8a8d50d21294b8f10f
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2352-8648&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2352-8648&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2352-8648&client=summon