Abstract
Automatic modulation classification (AMC) is a challenging topic in the development of cognitive radio, which can sense and learn surrounding electromagnetic environments and help to make corresponding decisions. In this paper, we propose to complete the real-time AMC through constructing a lightweight neural network MobileViT driven by the clustered constellation images. Firstly, the clustered constellation images are transformed from I/Q sequences to help extract robust and discriminative features. Then the lightweight neural network called MobileViT is developed for the real-time constellation image classification. Experimental results on the public dataset RadioML 2016.10a with edge computing platform demonstrate the superiority and efficiency of MobileViT. Furthermore, the extensive ablation tests prove the robustness of the proposed method to the learning rate and batch size. To the best of our knowledge, this is the first attempt to deploy the deep learning model to complete the real-time classification of modulation schemes of received signals at the edge.
Similar content being viewed by others
Data availability
Data will be made available on reasonable request.
References
Akyön FC, Alp Y, Gök G, Arikan O (2018) Deep learning in electronic warfare systems: automatic intra-pulse modulation recognition. Paper presented at IEEE 26th signal processing and communications applications conference (SIU), Izmir, Turkey, pp. 1–4
Chung WH (2013) Sequential likelihood ratio test under incomplete signal model for spectrum sensing. IEEE Trans Wirel Commun 12(2):494–503
Dong B et al (2022) A lightweight decentralized learning-based automatic modulation classification method for resource-constrained edge devices. IEEE Internet Things J early access 9(24):24708–24720
Fu X et al (2021) Lightweight automatic modulation classification based on decentralized learning. IEEE Trans Cogni Commun Netw 8(1):57–70
Gui G, Liu M, Tang F, Kato N, Adachi F (2020) 6G: Opening new horizons for integration of comfort, security, and intelligence. IEEE Wirel Commun 27(5):126–132
Hermawan AP, Ginanjar RR, Kim DS, Lee J (2020) CNN-based automatic modulation classification for beyond 5G communications. IEEE Commun Lett 24(5):1038–1041
Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. Int conf mach learn PMLR 37:448–456
Jais I, Ismail A, Nisa S (2019) Adam optimization algorithm for wide and deep neural network. Knowl Eng Data Sci 2(1):41–46
Jajoo G, Kumar Y, Yadav S (2019) Blind signal PSK/QAM recognition using clustering analysis of constellation signature in flat fading channel. IEEE Commun Lett 23(10):1853–1856
Ke Z, Vikalo H (2021) Real-time radio technology and modulation classification via an LSTM auto-encoder. IEEE Trans Wirel Commun 21(1):370–382
Kim S, Moon C, Kim J, Kim D (2021) A hybrid deep learning model for automatic modulation classification. IEEE Wirel Commun Lett 11(2):313–317
Kumar Y, Sheoran M, Jajoo G, Yadav S (2020) Automatic modulation classification based on constellation density using deep learning. IEEE Commun Lett 24(6):1275–1278
Lee J, Kim K, Shin Y (2019) Feature image-based automatic modulation classification method using CNN algorithm. In: IEEE international conference on artificial intelligence in information and communication (ICAIIC), Okinawa, Japan, pp 1–4
Lin Y, Tu Y, Dou Z, Chen L, Mao S (2021) Contour stella image and deep learning for signal recognition in the physical layer. IEEE Trans Cognit Commun Netw 7(1):34–46
Liu Y, Yang M, Li J, Zheng Q, Wang D (2020) Dynamic hand gesture recognition using 2D convolutional neural network. Eng Lett 28(1):243–254
Luan S, Gao Y, Zhou J, Zhang Z (2021) Automatic modulation classification based on Cauchy-score constellation and lightweight network under impulsive noise. IEEE Wirel Commun Lett 10(11):2509–2513
Ma H et al (2020) Cross model deep learning scheme for automatic modulation classification. IEEE Access 8:78923–78931
Mehta S, Rastegari M (2022) Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. In:international conference on learning representations (ICLR), pp 1–26
O’Shea TJ, Roy T, Clancy TC (2018) Over-the-air deep learning based radio signal classification. IEEE J Sel Top Signal Process 12(1):168–179
Peng S et al (2018) Modulation classification based on signal constellation diagrams and deep learning. IEEE Trans Neural Netw Learn Syst 30(3):718–727
Peng S, Sun S, Yao Y (2021) A survey of modulation classification using deep learning: Signal representation and data preprocessing. IEEE Trans Neural Netw Learn Syst 33(12):7020–7038
Roy C et al (2021) An ensemble deep learning model for automatic modulation classification in 5G and beyond IoT networks. Comput Intell Neurosci 2021(5047355):1–8
Sandler M, Howard A, Zhu M, Chen L (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: IEEE conference on computer vision and pattern recognition (CVPR), Salt Lake City, USA, pp 4510–4520
Shi Y, Hua X, Lei J, Zisen Q (2022) ConvLSTMAE: a spatiotemporal parallel autoencoders for automatic modulation classification. IEEE Commun Lett 26(8):1804–1808
Shimbo D, Oka I (2010) A modulation classification using amplitude moments in OFDM systems. In: International Symposium on Information Theory & Its Applications, Taichung, Taiwan, pp 288-293
Sun Y, Ball EA (2022) Automatic modulation classification using techniques from image classification. IET Commun 16(11):1303–1314
Wang Y, Liu M, Yang J, Gui G (2019) Data-driven deep learning for automatic modulation recognition in cognitive radios. IEEE Trans Veh Technol 68(4):4074–4077
Wang Y, Yang J, Liu M, Gui G (2020a) LightAMC: lightweight automatic modulation classification via deep learning and compressive sensing. IEEE Trans Veh Technol 69(3):3491–3495
Wang Y et al (2020b) Distributed learning for automatic modulation classification in edge devices. IEEE Wirel Commun Lett 9(12):2177–2181
Wang D et al (2021) Multiple high-order cumulants-based spectrum sensing in full-duplex-enabled cognitive IoT networks. IEEE Internet Things J 8(11):9330–9343
Xu Y, Xu G, Ma C (2022) A novel blind high-order modulation classifier using accumulated constellation temporal convolution for OSTBC-OFDM systems. IEEE Trans Circuits Syst II Express Briefs 10(11):2509–2513
Yan X, Feng G, Wu H-C, Xiang W, Wang Q (2017) Innovative robust modulation classification using graph-based cyclic-spectrum analysis. IEEE Commun Lett 21(1):16–19
Yan X, Zhang G, Wu H (2018) A novel automatic modulation classifier using graph-based constellation analysis for M-ary QAM. IEEE Commun Lett 23(2):298–301
You L, et al. (2022) GPU-accelerated faster mean shift with euclidean distance metrics. In: IEEE 46th annual computers, software, and applications conference (COMPSAC),Los Alamitos, USA, pp 211-216
Zhang Z, Wang C, Gan C, Sun S, Wang M (2019) Automatic modulation classification using convolutional neural network with features fusion of SPWVD and BJD. IEEE Trans Signal Inf Process over Netw 5(3):469–478
Zhang Z, Luo H, Wang C, Gan C, Xiong Y (2020) Automatic modulation classification using CNN-LSTM based dual-stream structure. IEEE Trans Veh Technol 69(11):13521–13531
Zhang X et al (2022) NAS-AMR: neural architecture search-based automatic modulation recognition for integrated sensing and communication systems. IEEE Trans Cognit Commun Netw 8(3):1374–1386
Zhao M, Chang CH, Xie W, Xie Z, Hu J (2020) “Cloud shape classification system based on multi-channel CNN and improved fdm. IEEE Access 8:44111–44124
Zheng J, Lv Y (2018) Likelihood-based automatic modulation classification in OFDM with index modulation”. IEEE Trans Veh Technol 67(9):8192–8204
Zheng Q, Yang M, Yang J, Zhang Q, Zhang X (2018) Improvement of generalization ability of deep CNN via implicit regularization in two-stage training process. IEEE Access 6:15844–15869
Zheng Q, Tian X, Yang M, Su H (2020a) CLMIP: cross-layer manifold invariance based pruning method of deep convolutional neural network for real-time road type recognition. Multidimens Syst Signal Process 32(1):239–262
Zheng Q et al (2020b) PAC-bayesian framework based drop-path method for 2D discriminative convolutional network pruning. Multidimens Syst Signal Process 31(3):793–827
Zheng Q, Zhao P, Zhang D, Wang H (2021) MR-DCAE: manifold regularization-based deep convolutional autoencoder for unauthorized broadcasting identification. Int J Intell Syst 36(12):7204–7238
Zheng Q, Zhao P, Wang H, Elhanashi A, Saponara S (2022) Fine-grained modulation classification using multi-scale radio transformer with dual-channel representation. IEEE Commun Lett 26(6):1298–1302
Acknowledgements
This research was supported by Shandong Provincial Natural Science Foundation, grant number ZR2023QF125.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zheng, Q., Saponara, S., Tian, X. et al. A real-time constellation image classification method of wireless communication signals based on the lightweight network MobileViT. Cogn Neurodyn 18, 659–671 (2024). https://doi.org/10.1007/s11571-023-10015-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11571-023-10015-7