A robust modulation classification method using convolutional neural networks View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-12

AUTHORS

Siyang Zhou, Zhendong Yin, Zhilu Wu, Yunfei Chen, Nan Zhao, Zhutian Yang

ABSTRACT

Automatic modulation classification (AMC) is a core technique in noncooperative communication systems. In particular, feature-based (FB) AMC algorithms have been widely studied. Current FB AMC methods are commonly designed for a limited set of modulation and lack of generalization ability; to tackle this challenge, a robust AMC method using convolutional neural networks (CNN) is proposed in this paper. In total, 15 different modulation types are considered. The proposed method can classify the received signal directly without feature extracion, and it can automatically learn features from the received signals. The features learned by the CNN are presented and analyzed. The robust features of the received signals in a specific SNR range are studied. The accuracy of classification using CNN is shown to be remarkable, particularly for low SNRs. The generalization ability of robust features is also proven to be excellent using the support vector machine (SVM). Finally, to help us better understand the process of feature learning, some outputs of intermediate layers of the CNN are visualized. More... »

PAGES

21

References to SciGraph publications

  • 2016. Convolutional Radio Modulation Recognition Networks in ENGINEERING APPLICATIONS OF NEURAL NETWORKS
  • 2015. Deep Learning Based Digital Signal Modulation Recognition in THE PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON COMMUNICATIONS, SIGNAL PROCESSING, AND SYSTEMS
  • 2011-12. Robustness of digitally modulated signal features against variation in HF noise model in EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1186/s13634-019-0616-6

    DOI

    http://dx.doi.org/10.1186/s13634-019-0616-6

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1113117024


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Harbin Institute of Technology", 
              "id": "https://www.grid.ac/institutes/grid.19373.3f", 
              "name": [
                "School of Electronics and Information Engineering, Harbin Institute of Technology, No. 92 West Dazhi Street, Nangang District, Harbin, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhou", 
            "givenName": "Siyang", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Harbin Institute of Technology", 
              "id": "https://www.grid.ac/institutes/grid.19373.3f", 
              "name": [
                "School of Electronics and Information Engineering, Harbin Institute of Technology, No. 92 West Dazhi Street, Nangang District, Harbin, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Yin", 
            "givenName": "Zhendong", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Harbin Institute of Technology", 
              "id": "https://www.grid.ac/institutes/grid.19373.3f", 
              "name": [
                "School of Electronics and Information Engineering, Harbin Institute of Technology, No. 92 West Dazhi Street, Nangang District, Harbin, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Wu", 
            "givenName": "Zhilu", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Dalian University of Technology", 
              "id": "https://www.grid.ac/institutes/grid.30055.33", 
              "name": [
                "School of Information and Communication Engineering, Dalian University of Technology, No.2 Linggong Road, Ganjingzi District, Dalian, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Chen", 
            "givenName": "Yunfei", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "University of Warwick", 
              "id": "https://www.grid.ac/institutes/grid.7372.1", 
              "name": [
                "School of Engineering, University of Warwick, CV4 7AL, Coventry, UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhao", 
            "givenName": "Nan", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Harbin Institute of Technology", 
              "id": "https://www.grid.ac/institutes/grid.19373.3f", 
              "name": [
                "School of Electronics and Information Engineering, Harbin Institute of Technology, No. 92 West Dazhi Street, Nangang District, Harbin, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Yang", 
            "givenName": "Zhutian", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/0165-1684(95)00099-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1000449102"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-44188-7_16", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1002607947", 
              "https://doi.org/10.1007/978-3-319-44188-7_16"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/1687-1499-2011-24", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028394461", 
              "https://doi.org/10.1186/1687-1499-2011-24"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-08991-1_100", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1048747784", 
              "https://doi.org/10.1007/978-3-319-08991-1_100"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1002/sat.1202", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050853018"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1049/el.2010.1893", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1056751029"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1049/el.2010.1893", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1056751029"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/mvt.2011.941893", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061431418"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/twc.2012.060412.110460", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061828243"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1142/s0218488598000094", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1062977837"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1198/106186008x318440", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1064199625"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1561/2200000006", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1068001401"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.aeue.2017.02.008", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1083864813"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/access.2017.2746140", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1091458337"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2009.5459469", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093416695"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3390/s18030924", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101621470"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2019-12", 
        "datePublishedReg": "2019-12-01", 
        "description": "Automatic modulation classification (AMC) is a core technique in noncooperative communication systems. In particular, feature-based (FB) AMC algorithms have been widely studied. Current FB AMC methods are commonly designed for a limited set of modulation and lack of generalization ability; to tackle this challenge, a robust AMC method using convolutional neural networks (CNN) is proposed in this paper. In total, 15 different modulation types are considered. The proposed method can classify the received signal directly without feature extracion, and it can automatically learn features from the received signals. The features learned by the CNN are presented and analyzed. The robust features of the received signals in a specific SNR range are studied. The accuracy of classification using CNN is shown to be remarkable, particularly for low SNRs. The generalization ability of robust features is also proven to be excellent using the support vector machine (SVM). Finally, to help us better understand the process of feature learning, some outputs of intermediate layers of the CNN are visualized.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1186/s13634-019-0616-6", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1357355", 
            "issn": [
              "1687-6172", 
              "1687-0433"
            ], 
            "name": "Applied Signal Processing", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "2019"
          }
        ], 
        "name": "A robust modulation classification method using convolutional neural networks", 
        "pagination": "21", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "d5364c58c2ed95359dde03df81de862fdd7b9732a1c5e66fe98aee6f5d36b278"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1186/s13634-019-0616-6"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1113117024"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1186/s13634-019-0616-6", 
          "https://app.dimensions.ai/details/publication/pub.1113117024"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-11T13:25", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000369_0000000369/records_68973_00000002.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1186%2Fs13634-019-0616-6"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1186/s13634-019-0616-6'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/s13634-019-0616-6'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s13634-019-0616-6'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s13634-019-0616-6'


     

    This table displays all metadata directly associated to this object as RDF triples.

    144 TRIPLES      21 PREDICATES      42 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1186/s13634-019-0616-6 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N9018f28e2c894c38909a265294d685e6
    4 schema:citation sg:pub.10.1007/978-3-319-08991-1_100
    5 sg:pub.10.1007/978-3-319-44188-7_16
    6 sg:pub.10.1186/1687-1499-2011-24
    7 https://doi.org/10.1002/sat.1202
    8 https://doi.org/10.1016/0165-1684(95)00099-2
    9 https://doi.org/10.1016/j.aeue.2017.02.008
    10 https://doi.org/10.1049/el.2010.1893
    11 https://doi.org/10.1109/access.2017.2746140
    12 https://doi.org/10.1109/iccv.2009.5459469
    13 https://doi.org/10.1109/mvt.2011.941893
    14 https://doi.org/10.1109/twc.2012.060412.110460
    15 https://doi.org/10.1142/s0218488598000094
    16 https://doi.org/10.1198/106186008x318440
    17 https://doi.org/10.1561/2200000006
    18 https://doi.org/10.3390/s18030924
    19 schema:datePublished 2019-12
    20 schema:datePublishedReg 2019-12-01
    21 schema:description Automatic modulation classification (AMC) is a core technique in noncooperative communication systems. In particular, feature-based (FB) AMC algorithms have been widely studied. Current FB AMC methods are commonly designed for a limited set of modulation and lack of generalization ability; to tackle this challenge, a robust AMC method using convolutional neural networks (CNN) is proposed in this paper. In total, 15 different modulation types are considered. The proposed method can classify the received signal directly without feature extracion, and it can automatically learn features from the received signals. The features learned by the CNN are presented and analyzed. The robust features of the received signals in a specific SNR range are studied. The accuracy of classification using CNN is shown to be remarkable, particularly for low SNRs. The generalization ability of robust features is also proven to be excellent using the support vector machine (SVM). Finally, to help us better understand the process of feature learning, some outputs of intermediate layers of the CNN are visualized.
    22 schema:genre research_article
    23 schema:inLanguage en
    24 schema:isAccessibleForFree false
    25 schema:isPartOf Nca5fabffb2d4440abbd3bc1d63834ad7
    26 Nd22c8a11c7b24413a6c355c7408ebf93
    27 sg:journal.1357355
    28 schema:name A robust modulation classification method using convolutional neural networks
    29 schema:pagination 21
    30 schema:productId N20c2ad0ec5e249c0a57095e1633351ab
    31 N3bfce43849c749dc829901b63be666f3
    32 Nfafd56e8d37a4749b49089065967cf1b
    33 schema:sameAs https://app.dimensions.ai/details/publication/pub.1113117024
    34 https://doi.org/10.1186/s13634-019-0616-6
    35 schema:sdDatePublished 2019-04-11T13:25
    36 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    37 schema:sdPublisher Ncaad9754c7044883af935632b3ab6de9
    38 schema:url https://link.springer.com/10.1186%2Fs13634-019-0616-6
    39 sgo:license sg:explorer/license/
    40 sgo:sdDataset articles
    41 rdf:type schema:ScholarlyArticle
    42 N1dd25829fd5c42d4bbc480446d2f78f1 schema:affiliation https://www.grid.ac/institutes/grid.19373.3f
    43 schema:familyName Yang
    44 schema:givenName Zhutian
    45 rdf:type schema:Person
    46 N2062edff1be4430088a87b67400ab719 rdf:first Nfcf206cd445040498f7a18c70b4109c4
    47 rdf:rest N71b94dcf75974eb2841eca78412415bd
    48 N20c2ad0ec5e249c0a57095e1633351ab schema:name dimensions_id
    49 schema:value pub.1113117024
    50 rdf:type schema:PropertyValue
    51 N3bfce43849c749dc829901b63be666f3 schema:name readcube_id
    52 schema:value d5364c58c2ed95359dde03df81de862fdd7b9732a1c5e66fe98aee6f5d36b278
    53 rdf:type schema:PropertyValue
    54 N69ff0a3269f5457a8033ff94206a4e74 schema:affiliation https://www.grid.ac/institutes/grid.19373.3f
    55 schema:familyName Wu
    56 schema:givenName Zhilu
    57 rdf:type schema:Person
    58 N71b94dcf75974eb2841eca78412415bd rdf:first N1dd25829fd5c42d4bbc480446d2f78f1
    59 rdf:rest rdf:nil
    60 N840c3ebcaad74da2b31cea1d43c9f8aa rdf:first Nf4737fcccdf844f1b8c931e82cf2bcb5
    61 rdf:rest N2062edff1be4430088a87b67400ab719
    62 N9018f28e2c894c38909a265294d685e6 rdf:first N9712920bdeb6428bab4e5f989d2cef3e
    63 rdf:rest Nbb4c5cadf1cf4eb2b9b9fcc693b312ea
    64 N9712920bdeb6428bab4e5f989d2cef3e schema:affiliation https://www.grid.ac/institutes/grid.19373.3f
    65 schema:familyName Zhou
    66 schema:givenName Siyang
    67 rdf:type schema:Person
    68 Nbb4c5cadf1cf4eb2b9b9fcc693b312ea rdf:first Nf3f95e55cb974fa7affe1b8dc7119972
    69 rdf:rest Nce63dbf695634cee959e14d7f8f7ef4c
    70 Nca5fabffb2d4440abbd3bc1d63834ad7 schema:volumeNumber 2019
    71 rdf:type schema:PublicationVolume
    72 Ncaad9754c7044883af935632b3ab6de9 schema:name Springer Nature - SN SciGraph project
    73 rdf:type schema:Organization
    74 Nce63dbf695634cee959e14d7f8f7ef4c rdf:first N69ff0a3269f5457a8033ff94206a4e74
    75 rdf:rest N840c3ebcaad74da2b31cea1d43c9f8aa
    76 Nd22c8a11c7b24413a6c355c7408ebf93 schema:issueNumber 1
    77 rdf:type schema:PublicationIssue
    78 Nf3f95e55cb974fa7affe1b8dc7119972 schema:affiliation https://www.grid.ac/institutes/grid.19373.3f
    79 schema:familyName Yin
    80 schema:givenName Zhendong
    81 rdf:type schema:Person
    82 Nf4737fcccdf844f1b8c931e82cf2bcb5 schema:affiliation https://www.grid.ac/institutes/grid.30055.33
    83 schema:familyName Chen
    84 schema:givenName Yunfei
    85 rdf:type schema:Person
    86 Nfafd56e8d37a4749b49089065967cf1b schema:name doi
    87 schema:value 10.1186/s13634-019-0616-6
    88 rdf:type schema:PropertyValue
    89 Nfcf206cd445040498f7a18c70b4109c4 schema:affiliation https://www.grid.ac/institutes/grid.7372.1
    90 schema:familyName Zhao
    91 schema:givenName Nan
    92 rdf:type schema:Person
    93 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    94 schema:name Information and Computing Sciences
    95 rdf:type schema:DefinedTerm
    96 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    97 schema:name Artificial Intelligence and Image Processing
    98 rdf:type schema:DefinedTerm
    99 sg:journal.1357355 schema:issn 1687-0433
    100 1687-6172
    101 schema:name Applied Signal Processing
    102 rdf:type schema:Periodical
    103 sg:pub.10.1007/978-3-319-08991-1_100 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048747784
    104 https://doi.org/10.1007/978-3-319-08991-1_100
    105 rdf:type schema:CreativeWork
    106 sg:pub.10.1007/978-3-319-44188-7_16 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002607947
    107 https://doi.org/10.1007/978-3-319-44188-7_16
    108 rdf:type schema:CreativeWork
    109 sg:pub.10.1186/1687-1499-2011-24 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028394461
    110 https://doi.org/10.1186/1687-1499-2011-24
    111 rdf:type schema:CreativeWork
    112 https://doi.org/10.1002/sat.1202 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050853018
    113 rdf:type schema:CreativeWork
    114 https://doi.org/10.1016/0165-1684(95)00099-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000449102
    115 rdf:type schema:CreativeWork
    116 https://doi.org/10.1016/j.aeue.2017.02.008 schema:sameAs https://app.dimensions.ai/details/publication/pub.1083864813
    117 rdf:type schema:CreativeWork
    118 https://doi.org/10.1049/el.2010.1893 schema:sameAs https://app.dimensions.ai/details/publication/pub.1056751029
    119 rdf:type schema:CreativeWork
    120 https://doi.org/10.1109/access.2017.2746140 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091458337
    121 rdf:type schema:CreativeWork
    122 https://doi.org/10.1109/iccv.2009.5459469 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093416695
    123 rdf:type schema:CreativeWork
    124 https://doi.org/10.1109/mvt.2011.941893 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061431418
    125 rdf:type schema:CreativeWork
    126 https://doi.org/10.1109/twc.2012.060412.110460 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061828243
    127 rdf:type schema:CreativeWork
    128 https://doi.org/10.1142/s0218488598000094 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062977837
    129 rdf:type schema:CreativeWork
    130 https://doi.org/10.1198/106186008x318440 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064199625
    131 rdf:type schema:CreativeWork
    132 https://doi.org/10.1561/2200000006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1068001401
    133 rdf:type schema:CreativeWork
    134 https://doi.org/10.3390/s18030924 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101621470
    135 rdf:type schema:CreativeWork
    136 https://www.grid.ac/institutes/grid.19373.3f schema:alternateName Harbin Institute of Technology
    137 schema:name School of Electronics and Information Engineering, Harbin Institute of Technology, No. 92 West Dazhi Street, Nangang District, Harbin, China
    138 rdf:type schema:Organization
    139 https://www.grid.ac/institutes/grid.30055.33 schema:alternateName Dalian University of Technology
    140 schema:name School of Information and Communication Engineering, Dalian University of Technology, No.2 Linggong Road, Ganjingzi District, Dalian, China
    141 rdf:type schema:Organization
    142 https://www.grid.ac/institutes/grid.7372.1 schema:alternateName University of Warwick
    143 schema:name School of Engineering, University of Warwick, CV4 7AL, Coventry, UK
    144 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...