{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T10:46:11Z","timestamp":1775645171659,"version":"3.50.1"},"reference-count":21,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T00:00:00Z","timestamp":1661817600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Modulation recognition is the indispensable part of signal interception analysis, which has always been the research hotspot in the field of radio communication. With the increasing complexity of the electromagnetic spectrum environment, interference in signal propagation becomes more and more serious. This paper proposes a modulation recognition scheme based on multimodal feature fusion, which attempts to improve the performance of modulation recognition under different channels. Firstly, different time- and frequency-domain features are extracted as the network input in the signal preprocessing stage. The residual shrinkage building unit with channel-wise thresholds (RSBU-CW) was used to construct deep convolutional neural networks to extract spatial features, which interact with time features extracted by LSTM in pairs to increase the diversity of the features. Finally, the PNN model was adapted to make the features extracted from the network cross-fused to enhance the complementarity between features. The simulation results indicated that the proposed scheme has better recognition performance than the existing feature fusion schemes, and it can also achieve good recognition performance in multipath fading channels. The test results of the public dataset, RadioML2018.01A, showed that recognition accuracy exceeds 95% when the signal-to-noise ratio (SNR) reaches 8dB.<\/jats:p>","DOI":"10.3390\/s22176539","type":"journal-article","created":{"date-parts":[[2022,8,31]],"date-time":"2022-08-31T00:13:56Z","timestamp":1661904836000},"page":"6539","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Modulation Recognition of Communication Signals Based on Multimodal Feature Fusion"],"prefix":"10.3390","volume":"22","author":[{"given":"Xinliang","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information Systems Engineering, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, China"}]},{"given":"Tianyun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Systems Engineering, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, China"}]},{"given":"Pei","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Information Systems Engineering, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, China"}]},{"given":"Renwei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Systems Engineering, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, China"}]},{"given":"Xiong","family":"Zha","sequence":"additional","affiliation":[{"name":"School of Information Systems Engineering, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,8,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"67366","DOI":"10.1109\/ACCESS.2020.2986330","article-title":"Deep learning for modulation recognition: A survey with a demonstration","volume":"8","author":"Zhou","year":"2020","journal-title":"IEEE Access"},{"key":"ref_2","unstructured":"Weaver, C., Cole, C., and Krumland, R. (1969). The Automatic Classification of Modulation Types by Pattern Recognition, Defense Technical Information Center. Stanford University Technical Report."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e4762","DOI":"10.1002\/dac.4762","article-title":"A survey of traditional and advanced automatic modulation classification techniques, challenges, and some novel trends","volume":"34","year":"2021","journal-title":"Int. J. Commun. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1109\/LCOMM.2019.2894400","article-title":"A faster maximum-likelihood modulation classification in flat fading non-gaussian channels","volume":"23","author":"Chen","year":"2019","journal-title":"IEEE Commun. Lett."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"042073","DOI":"10.1088\/1755-1315\/692\/4\/042073","article-title":"Modulation type recognition algorithm based on modulation instantaneous structure difference and deep learning","volume":"692","author":"Wang","year":"2021","journal-title":"IOP Conf. Ser. Earth Environ. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"106386","DOI":"10.1109\/ACCESS.2020.3000358","article-title":"Modulation order reduction method for improving the performance of amc algorithm based on sixth-order cumulants","volume":"8","author":"Pajic","year":"2020","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.phycom.2018.12.019","article-title":"Wavelet transform based modulation classification for 5 g and uav communication in multipath fading channel","volume":"34","author":"Li","year":"2019","journal-title":"Phys. Commun."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"138512","DOI":"10.1109\/ACCESS.2019.2943300","article-title":"Automatic modulation classification architectures based on cyclostationary features in impulsive environments","volume":"7","author":"Lima","year":"2019","journal-title":"IEEE Access"},{"key":"ref_9","first-page":"213","article-title":"Convolutional radio modulation recognition networks","volume":"629","author":"Corgan","year":"2016","journal-title":"Commun. Comput. Inf. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1109\/JSTSP.2018.2797022","article-title":"Over-the-air deep learning based radio signal classification","volume":"12","author":"Roy","year":"2018","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zha, X., Peng, H., Qin, X., Li, G., and Yang, S. (2019). A deep learning framework for signal detection and modulation classification. Sensors, 19.","DOI":"10.3390\/s19184042"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Sun, X., Su, S., Zuo, Z., Guo, X., and Tan, X. (2020). Modulation classification using compressed sensing and decision tree\u2013support vector machine in cognitive radio system. Sensors, 20.","DOI":"10.3390\/s20051438"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Liu, K., Gao, W., and Huang, Q. (2021). Automatic modulation recognition based on a Dcn-Bilstm network. Sensors, 21.","DOI":"10.3390\/s21051577"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Chen, H., Guo, L., Dong, C., Cong, F., and Mu, X. (2020\u20133, January 31). Automatic modulation classification using multi-scale convolutional neural network. Proceedings of the 2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications, London, UK.","DOI":"10.1109\/PIMRC48278.2020.9217305"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TCCN.2020.3023145","article-title":"Automatic Modulation classification based on deep residual networks with multimodal information","volume":"7","author":"Qi","year":"2021","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"13521","DOI":"10.1109\/TVT.2020.3030018","article-title":"Automatic modulation classification using cnn-lstm based dual-stream structure","volume":"69","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_17","first-page":"1231","article-title":"Spectrum sensing based on signal envelope of rayleigh multi-path fading channels","volume":"42","author":"Zhou","year":"2020","journal-title":"Dianzi Yu Xinxi Xuebao\/J. Electron. Inf. Technol."},{"key":"ref_18","first-page":"1679","article-title":"Optimization design of generalized psam format over rician channel","volume":"43","author":"Wang","year":"2021","journal-title":"Syst. Eng. Electron."},{"key":"ref_19","first-page":"31","article-title":"The wireless channel","volume":"Volume 2","author":"Tse","year":"2005","journal-title":"Fundamentals of Wireless Communication"},{"key":"ref_20","first-page":"197","article-title":"Deep learning modulation recognition based on instantaneous amplitude and phase","volume":"38","author":"Guanye","year":"2021","journal-title":"Comput. Appl. Softw."},{"key":"ref_21","unstructured":"Zamrodah, Y. (2015, January 19\u201324). Convolutional, long short-term memory, fully connected deep neural networks. Proceedings of the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, QLD, Australia."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/17\/6539\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:20:12Z","timestamp":1760142012000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/17\/6539"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,30]]},"references-count":21,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2022,9]]}},"alternative-id":["s22176539"],"URL":"https:\/\/doi.org\/10.3390\/s22176539","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,30]]}}}