Signal Surface Augmentation for Artificial Intelligence-Based Automatic Modulation Classification

[en] Automatic modulation recognition has regained attention as a critical application for cognitive radio, combining artificial intelligence with physical layer monitoring of wireless transmissions. This paper formalizes signal surface augmentation (SSA), a process that decomposes signals into informative subcomponents to enhance AI-based analysis. We employ Bivariate Empirical Mode Decomposition (BEMD) to break signals into intrinsic modes while addressing challenges like adjacent trends in long sample decompositions and introducing the concept of data overdispersion. Using a modern, publicly available dataset of synthetic modulated signals under realistic conditions, we validate that the presentation of BEMD-derived components improves recognition accuracy by 13% compared to raw IQ inputs. For extended signal lengths, gains reach up to 36%. These results demonstrate the value of signal surface augmentation for improving the robustness of modulation recognition, with potential applications in real-world scenarios.

Research center :

CRTI - Centre de Recherche en Technologie de l'Information

Disciplines :

Electrical & electronics engineering
Computer science

Author, co-author :

Gros, Alexander ; Université de Mons - UMONS > Faculté Polytechnique > Service d'Electromagnétisme et Télécommunications

MOEYAERT, Véronique ; Université de Mons - UMONS > Faculté Polytechnique > Service d'Electromagnétisme et Télécommunications

MEGRET, Patrice ; Université de Mons - UMONS > Faculté Polytechnique > Service d'Electromagnétisme et Télécommunications

Language :

English

Title :

Signal Surface Augmentation for Artificial Intelligence-Based Automatic Modulation Classification

Publication date :

03 December 2025

Journal title :

Electronics

eISSN :

2079-9292

Publisher :

MDPI AG

Volume :

Issue :

Pages :

4760

Peer reviewed :

Peer Reviewed verified by ORBi

Additional URL :

https://www.mdpi.com/2079-9292/14/23/4760/pdf

Research unit :

F108 - Electromagnétisme et Télécommunications

Research institute :

Infortech

Funders :

Walloon Region research project “CyberExcellence”
F.R.S.-FNRS - Fonds de la Recherche Scientifique

Available on ORBi UMONS :

since 05 December 2025

Statistics

Number of views

58 (4 by UMONS)

Number of downloads

182 (3 by UMONS)

More statistics

Scopus citations^®

Scopus citations^®
without self-citations

OpenCitations

OpenAlex citations

Bibliography

Ulversoy T. Software Defined Radio: Challenges and Opportunities IEEE Commun. Surv. Tutor. 2010 12 531 550 10.1109/SURV.2010.032910.00019
Zhu Z. Nandi A.K. Automatic Modulation Classification: Principles, Algorithms and Applications 1st ed. Wiley Publishing Hoboken, NJ, USA 2015
Abdel-Moneim M. El-Shafai W. El-Salam N. El-Rabaie E.S. Abd El-Samie F. A Survey of Traditional and Advanced Automatic Modulation Classification Techniques, Challenges and Some Novel Trends Int. J. Commun. Syst. 2021 34 e4762 10.1002/dac.4762
Yongjun S. Wu W. Survey of Research on Application of Deep Learning in Modulation Recognition Wirel. Pers. Commun. 2024 133 1483 1515 10.1007/s11277-023-10826-1
Gros A. Moeyaert V. Megret P. Joint use of Bivariate Empirical Mode Decomposition and Convolutional Neural Networks for Automatic Modulation Recognition Proceedings of the 2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) Kyoto, Japan 12–15 September 2022 957 962 10.1109/PIMRC54779.2022.9977690
O’Shea T. West N. Radio Machine Learning Dataset Generation with GNU Radio Proc. GNU Radio Conf. 2016 1 Available online: https://api.semanticscholar.org/CorpusID:114654356 (accessed on 28 November 2025)
O’Shea T.J. Roy T. Clancy T.C. Over-the-Air Deep Learning Based Radio Signal Classification IEEE J. Sel. Top. Signal Process. 2018 12 168 179 10.1109/JSTSP.2018.2797022
Rajendran S. Meert W. Giustiniano D. Lenders V. Pollin S. Deep Learning Models for Wireless Signal Classification with Distributed Low-Cost Spectrum Sensors IEEE Trans. Cogn. Commun. Netw. 2018 4 433 445 10.1109/TCCN.2018.2835460
O’Shea T.J. Corgan J. Clancy T.C. Convolutional Radio Modulation Recognition Networks arXiv 2016 1602.04105 10.48550/arXiv.1602.04105
Spooner C. An Analysis of DeepSig’s 2016.10A Data Set Available online: https://cyclostationary.blog/2020/04/29/all-bpsk-signals/ (accessed on 14 April 2022)
radioML radioML/Dataset Available online: https://github.com/radioML/dataset/issues (accessed on 28 November 2025)
Spooner C. Dataset for the Machine-Learning Challenge [CSPB.ML.2018] Available online: https://cyclostationary.blog/2019/02/15/data-set-for-the-machine-learning-challenge/ (accessed on 28 November 2025)
Latshaw J.A. Popescu D.C. Snoap J.A. Spooner C.M. Using Capsule Networks to Classify Digitally Modulated Signals with Raw I/Q Data Proceedings of the 2022 14th International Conference on Communications (COMM) Bucharest, Romania 16–18 June 2022 1 6 10.1109/COMM54429.2022.9817229
Snoap J.A. Popescu D.C. Latshaw J.A. Spooner C.M. Deep-Learning-Based Classification of Digitally Modulated Signals Using Capsule Networks and Cyclic Cumulants Sensors 2023 23 5735 10.3390/s23125735 37420905
Snoap J.A. Popescu D.C. Spooner C.M. Deep-Learning-Based Classifier With Custom Feature-Extraction Layers for Digitally Modulated Signals IEEE Trans. Broadcast. 2024 70 763 773 10.1109/TBC.2024.3391056
Rashvand N. Witham K. Maldonado G. Katariya V. Marer Prabhu N. Schirner G. Tabkhi H. Enhancing Automatic Modulation Recognition for IoT Applications Using Transformers IoT 2024 5 212 226 10.3390/iot5020011
Chen H. Guo L. Dong C. Cong F. Mu X. 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 31 August–3 September 2020 1 6 10.1109/PIMRC48278.2020.9217305
Zhang J. Feng F. Marti-Puig P. Caiafa C.F. Sun Z. Duan F. Solé-Casals J. Serial-EMD: Fast empirical mode decomposition method for multi-dimensional signals based on serialization Inf. Sci. 2021 581 215 232 10.1016/j.ins.2021.09.033
Li X. Li Y. Tang C. Li Y. Modulation recognition network of multi-scale analysis with deep threshold noise elimination Front. Inf. Technol. Electron. Eng. 2023 24 742 758 10.1631/FITEE.2200253
Shorten C. Khoshgoftaar T. A survey on Image Data Augmentation for Deep Learning J. Big Data 2019 6 60 10.1186/s40537-019-0197-0
Huang N. Shen Z. Long S. Wu M. Shih H. Zheng Q. Yen N.C. Tung C.C. Liu H. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis Proc. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci. 1998 454 903 995 10.1098/rspa.1998.0193
Huang N.E. Shen S.S.P. Hilbert–Huang Transform and Its Applications 2nd ed. World Scientific Singapore 2014 10.1142/8804
Carnì D. Balestrieri E. Tudosa I. Lamonaca F. Application of machine learning techniques and empirical mode decomposition for the classification of analog modulated signals ACTA IMEKO 2020 9 66 10.21014/acta_imeko.v9i2.800
O’Shea T.J. Hoydis J. An Introduction to Deep Learning for the Physical Layer arXiv 2017 1702.00832 10.1109/TCCN.2017.2758370
Tanaka T. Mandic D.P. Complex Empirical Mode Decomposition IEEE Signal Process. Lett. 2007 14 101 104 10.1109/LSP.2006.882107
Bin Altaf M.U. Gautama T. Tanaka T. Mandic D.P. Rotation Invariant Complex Empirical Mode Decomposition Proceedings of the 2007 IEEE International Conference on Acoustics, Speech and Signal Processing—ICASSP ’07 Honolulu, HI, USA 15–20 April 2007 Volume 3 III–1009 III–1012 10.1109/ICASSP.2007.366853
Rilling G. Flandrin P. Goncalves P. Lilly J.M. Bivariate Empirical Mode Decomposition IEEE Signal Process. Lett. 2007 14 936 939 10.1109/LSP.2007.904710
Rilling G. Flandrin P. Gonçalves P. On empirical mode decomposition and its algorithms Proc. IEEE-EURASIP Workshop Nonlinear Signal Image Process. NSIP-03 2003 3 Available online: https://api.semanticscholar.org/CorpusID:16054541 (accessed on 28 November 2025)
Lilly J. Olhede S. Bivariate Instantaneous Frequency and Bandwidth Signal Process. IEEE Trans. 2009 58 591 603 10.1109/TSP.2009.2031729
Fleureau J. Kachenoura A. Nunes J.C. Albera L. Senhadji L. 3A-EMD: A Generalized Approach for Monovariate and Multivariate EMD Proceedings of the Information Sciences, Signal Processing and their Applications Kuala Lumpur, Malaysia 10–13 May 2010 300 303 10.1109/ISSPA.2010.5605465
Gros A. Moeyaert V. Mégret P. The influence of Bivariate Empirical Mode Decomposition parameters on AI-based Automatic Modulation Recognition accuracy Proceedings of the 43rd Symposium on Information Theory and Signal Processing in the Benelux Brussels, Belgium 11 May 2023
Gros A. SSA_IMFs_Energy Available online: https://github.com/AlexanderGros/SSA_IMFs_Energy (accessed on 28 November 2025)
Available online: https://www.ceci-hpc.be/clusters.html (accessed on 24 January 2025)
Iqbal H. HarisIqbal88/PlotNeuralNet v1.0.0 2018 Available online: https://zenodo.org/records/2526396 (accessed on 28 November 2025)