基于轻量级深度神经网络的电磁信号调制识别技术
TN971; 针对6G时代将会是移动通信与人工智能紧密结合的时代,产生数量庞大的边缘智能信号处理节点的趋势,提出了一种可部署于资源受限的边缘设备上的高效智能电磁信号识别模型.首先,通过绘制电磁信号的星座图将电磁信号具象为二维图像,并根据归一化点密度对星座图上色以实现特征增强;然后,使用二值化深度神经网络对其进行识别,在保证识别准确率的同时明显降低了模型存储开销以及计算开销.采用电磁信号调制识别问题进行验证,实验选取常用的8种数字调制信号,选择加性高斯白噪声为信道环境.实验结果表明,所提方案可以在信噪比为-6～6 dB的噪声条件下获得96.1％的综合识别率,网络模型大小仅为166 KB,部署于树...
Saved in:
| Published in | 通信学报 Vol. 41; no. 11; pp. 12 - 21 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
哈尔滨工程大学信息与通信工程学院,黑龙江 哈尔滨 150001%奥本大学电子和计算机工程学院,奥本 36849
25.11.2020
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1000-436X |
| DOI | 10.11959/j.issn.1000-436x.2020237 |
Cover
| Abstract | TN971; 针对6G时代将会是移动通信与人工智能紧密结合的时代,产生数量庞大的边缘智能信号处理节点的趋势,提出了一种可部署于资源受限的边缘设备上的高效智能电磁信号识别模型.首先,通过绘制电磁信号的星座图将电磁信号具象为二维图像,并根据归一化点密度对星座图上色以实现特征增强;然后,使用二值化深度神经网络对其进行识别,在保证识别准确率的同时明显降低了模型存储开销以及计算开销.采用电磁信号调制识别问题进行验证,实验选取常用的8种数字调制信号,选择加性高斯白噪声为信道环境.实验结果表明,所提方案可以在信噪比为-6～6 dB的噪声条件下获得96.1％的综合识别率,网络模型大小仅为166 KB,部署于树莓派4B的执行时间为290 ms,相比于同规模的全精度网络,准确率提升了0.6％,模型缩减到1/26.16,运行时间缩减到1/2.37. |
|---|---|
| AbstractList | TN971; 针对6G时代将会是移动通信与人工智能紧密结合的时代,产生数量庞大的边缘智能信号处理节点的趋势,提出了一种可部署于资源受限的边缘设备上的高效智能电磁信号识别模型.首先,通过绘制电磁信号的星座图将电磁信号具象为二维图像,并根据归一化点密度对星座图上色以实现特征增强;然后,使用二值化深度神经网络对其进行识别,在保证识别准确率的同时明显降低了模型存储开销以及计算开销.采用电磁信号调制识别问题进行验证,实验选取常用的8种数字调制信号,选择加性高斯白噪声为信道环境.实验结果表明,所提方案可以在信噪比为-6～6 dB的噪声条件下获得96.1％的综合识别率,网络模型大小仅为166 KB,部署于树莓派4B的执行时间为290 ms,相比于同规模的全精度网络,准确率提升了0.6％,模型缩减到1/26.16,运行时间缩减到1/2.37. |
| Author | 涂涯 张思成 Shiwen Mao 林云 |
| AuthorAffiliation | 哈尔滨工程大学信息与通信工程学院,黑龙江 哈尔滨 150001%奥本大学电子和计算机工程学院,奥本 36849 |
| AuthorAffiliation_xml | – name: 哈尔滨工程大学信息与通信工程学院,黑龙江 哈尔滨 150001%奥本大学电子和计算机工程学院,奥本 36849 |
| Author_FL | ZHANG Sicheng TU Ya Shiwen Mao LIN Yun |
| Author_FL_xml | – sequence: 1 fullname: ZHANG Sicheng – sequence: 2 fullname: LIN Yun – sequence: 3 fullname: TU Ya – sequence: 4 fullname: Shiwen Mao |
| Author_xml | – sequence: 1 fullname: 张思成 – sequence: 2 fullname: 林云 – sequence: 3 fullname: 涂涯 – sequence: 4 fullname: Shiwen Mao |
| BookMark | eNrjYmDJy89LZWBQNDTQMzS0NLXUz9LLLC7O0zM0MDDQNTE2q9AzMgBCY3MWBk6YWAQHA29xcWaSgamhsbmZgbEhJ4PT0_m7nuzqe7F398v2_ue7lj_bvvHprmXPl857vrv_-d6Jz3fPeT6r5fmUrc8XNz7Zv_Bp__YXG5qfdmx7sb7tacfqZ10Nz-as52FgTUvMKU7lhdLcDKFuriHOHro-_u6ezo4-usVA-410k5JTLI0sjVLSLJIsLU0szQ0NEo3NLFKTjNKSzAwsjZPNkg1MzZITU8xSDAyMkywNLEyTDJPNjUxSjZPNEw1Sko25GVQh5pYn5qUl5qXHZ-WXFuUBbYwvqahIAvnWEGSRMQAdEmdf |
| ClassificationCodes | TN971 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.11959/j.issn.1000-436x.2020237 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| DocumentTitle_FL | Electromagnetic signal modulation recognition technology based on lightweight deep neural network |
| EndPage | 21 |
| ExternalDocumentID | txxb202011002 |
| GrantInformation_xml | – fundername: (国家自然科学基金资助项目); (中央高校基本科研业务费基金资助项目) funderid: (国家自然科学基金资助项目); (中央高校基本科研业务费基金资助项目) |
| GroupedDBID | -0Y 2B. 4A8 92I 93N ALMA_UNASSIGNED_HOLDINGS CCEZO CUBFJ GROUPED_DOAJ PSX TCJ |
| ID | FETCH-LOGICAL-s1002-bcd9292df8b9949710a368eb2fb6093c6c056cad6d003b9085b1c724e3c7a0dc3 |
| ISSN | 1000-436X |
| IngestDate | Thu May 29 04:00:48 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 11 |
| Keywords | 6G 图像具象化 二值化深度神经网络 边缘智能 电磁信号调制识别 |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1002-bcd9292df8b9949710a368eb2fb6093c6c056cad6d003b9085b1c724e3c7a0dc3 |
| PageCount | 10 |
| ParticipantIDs | wanfang_journals_txxb202011002 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-11-25 |
| PublicationDateYYYYMMDD | 2020-11-25 |
| PublicationDate_xml | – month: 11 year: 2020 text: 2020-11-25 day: 25 |
| PublicationDecade | 2020 |
| PublicationTitle | 通信学报 |
| PublicationTitle_FL | Journal on Communications |
| PublicationYear | 2020 |
| Publisher | 哈尔滨工程大学信息与通信工程学院,黑龙江 哈尔滨 150001%奥本大学电子和计算机工程学院,奥本 36849 |
| Publisher_xml | – name: 哈尔滨工程大学信息与通信工程学院,黑龙江 哈尔滨 150001%奥本大学电子和计算机工程学院,奥本 36849 |
| SSID | ssib051376031 ssj0002912165 ssib058759023 ssib001102965 ssib023646527 ssib023168036 ssib036439991 ssib050281523 ssib000968473 |
| Score | 2.4247699 |
| Snippet | TN971; 针对6G时代将会是移动通信与人工智能紧密结合的时代,产生数量庞大的边缘智能信号处理节点的趋势,提出了一种可部署于资源受限的边缘设备上的高效智能电磁信号识别模... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 12 |
| Title | 基于轻量级深度神经网络的电磁信号调制识别技术 |
| URI | https://d.wanfangdata.com.cn/periodical/txxb202011002 |
| Volume | 41 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources issn: 1000-436X databaseCode: M~E dateStart: 19800101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://road.issn.org omitProxy: true ssIdentifier: ssib058759023 providerName: ISSN International Centre |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1Na9RANJQK4kUUFT9LBee0bM1MksnMMdnNUoR6aqG3svlY62ULdoulB1EULR4sgicpioh68FA9aGFL8c90m_ovfO8lm6Rl1Sos4e2bmTfvYzLz3u7MPMO4AeNCWaqj62YYJXU70g68c46sw7TAhSnjtqvxgPPMbTk9Z9-ad-bHxmcru5ZWeuFUtDbyXMn_WBVwYFc8JfsPli2IAgJgsC88wcLwPJaNWeAw3WK-xwIbnypggWJ-k_k-CzSDOF-1WOBikeeyQDIfYI6tECOxyAMKAdXxh5WbTPMcoxsIaKBsEwC9ONTKAg-UOm0xjwhCWyCOvZtMWYQBWCLGazElc4znIxvKww0WAAB979DGQmLbxB6rxL0mcUsNPWc4RkgOIECUsFGTAMW0WVaRKJ52cwVpXi0B9pTIAa_c4bx4937Src20l6q_iED4y3k9Oz1NY5h0b2F3yIaJukFKPvMyDKkWVaWY8kkIm4xQSFPIJ1GXoCTEKLLhKB2MIJjR0Uxr5gl4VxBGo3ECAsQjSxzGSO0P7NY4pquAFc0hqvTJbdMYxXgxDgijTSItmGqQsQPi10VAuzkdHKDHlOAoAzVLquy22XzpxDsKbIvyUhZra3ap2XAO4ZWVMt88n-TL5ujVXDualnPsYGrYweoUGl1kdwUduSy9t7oaYilehAiO2QnhSol5TWYeBNWgHVyy6mlyU-jyv36BqdzAryu_S1s6onDSLfThdXnDlAMeOjjBBT2H4z6z8r91B-Y-nWfmIv9QaC445bgtVHbSuD6U9-bvpKVThd1Ou3un4gDPnjFO55HrpJdNQ2eNsbXFc4Y_eNvf67842N35-Wwj7X_a3_466H9MP7xJdzbS3Zfpzmb6-kn66lv6_tHej3eDje2DL48H698Ptp4O1j_vP3-4v7l13phrBbON6XqelqW-jFqth1EMMZWIOyrU2tYQorRhKCSh6ITS1FYkIwiqonYsY_AYQg0xXcgjV9iJFbltM46sC8Z4d6mbXDQmwxiiB9cNleCxnZgSkwCBrHYoO7aOlLpkTOQyL-TT7vLCIRNf_luFK8apcoq4aoz37q0k1yCM6IUTNCp-AfjBzTE |
| linkProvider | ISSN International Centre |
| 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=%E5%9F%BA%E4%BA%8E%E8%BD%BB%E9%87%8F%E7%BA%A7%E6%B7%B1%E5%BA%A6%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E7%94%B5%E7%A3%81%E4%BF%A1%E5%8F%B7%E8%B0%83%E5%88%B6%E8%AF%86%E5%88%AB%E6%8A%80%E6%9C%AF&rft.jtitle=%E9%80%9A%E4%BF%A1%E5%AD%A6%E6%8A%A5&rft.au=%E5%BC%A0%E6%80%9D%E6%88%90&rft.au=%E6%9E%97%E4%BA%91&rft.au=%E6%B6%82%E6%B6%AF&rft.au=Shiwen+Mao&rft.date=2020-11-25&rft.pub=%E5%93%88%E5%B0%94%E6%BB%A8%E5%B7%A5%E7%A8%8B%E5%A4%A7%E5%AD%A6%E4%BF%A1%E6%81%AF%E4%B8%8E%E9%80%9A%E4%BF%A1%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E9%BB%91%E9%BE%99%E6%B1%9F+%E5%93%88%E5%B0%94%E6%BB%A8+150001%25%E5%A5%A5%E6%9C%AC%E5%A4%A7%E5%AD%A6%E7%94%B5%E5%AD%90%E5%92%8C%E8%AE%A1%E7%AE%97%E6%9C%BA%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E5%A5%A5%E6%9C%AC+36849&rft.issn=1000-436X&rft.volume=41&rft.issue=11&rft.spage=12&rft.epage=21&rft_id=info:doi/10.11959%2Fj.issn.1000-436x.2020237&rft.externalDocID=txxb202011002 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Ftxxb%2Ftxxb.jpg |