A novel D-CNL-R classifier approach for automatic modulation classification

K Tamizhelakkiya; C.T. Manimegalai; K Tamizhelakkiya; C.T. Manimegalai

doi:10.3934/electreng.2026020

AIMS Electronics and Electrical Engineering

2026, Volume 10, Issue 3: 504-526. doi: 10.3934/electreng.2026020

Previous Article Next Article

Research article

A novel D-CNL-R classifier approach for automatic modulation classification

K Tamizhelakkiya ^,,
C.T. Manimegalai

Department of Electronics and Communication Engineering, SRM Institute of Science and Technology, Chennai, Tamil Nadu, 603203, India

Received: 09 December 2025 Revised: 17 May 2026 Accepted: 03 June 2026 Published: 02 July 2026

Automatic Modulation Classification (AMC) is a significant decision-making process in non-cooperative, 5G, and beyond communication systems. Advancements in Artificial Intelligence (AI) led to the implementation of Deep Learning (DL) to provide superior performance over the feature extraction and offline training process of AMC. In this work, we proposed a hybrid modulation classification architecture by integrating Convolutional Neural Networks (CNN) with ML classifiers such as Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost). The Radio Frequency Signal Classification (RFSC) dataset consists of data collected under different Signal-to-Noise Ratio (SNR) scenarios to analyze the resilience of the classifiers. Among all architectures, the Deep Convolutional Layer based RF (D-CNL-R) model achieved superior modulation recognition accuracy due to its enhanced capability to learn complex nonlinear feature distributions. We observed that the training overhead of the proposed D-CNL-R reduced to $ \simeq 1\times $ with better classification accuracy performance. We also presented an experimental approach for the prediction performance of real-time signals for indoor and outdoor scenarios.
- deep learning,
- modulation recognition, CNN, machine learning, SNR
Citation: K Tamizhelakkiya, C.T. Manimegalai. A novel D-CNL-R classifier approach for automatic modulation classification[J]. AIMS Electronics and Electrical Engineering, 2026, 10(3): 504-526. doi: 10.3934/electreng.2026020

Related Papers:

Abstract

Automatic Modulation Classification (AMC) is a significant decision-making process in non-cooperative, 5G, and beyond communication systems. Advancements in Artificial Intelligence (AI) led to the implementation of Deep Learning (DL) to provide superior performance over the feature extraction and offline training process of AMC. In this work, we proposed a hybrid modulation classification architecture by integrating Convolutional Neural Networks (CNN) with ML classifiers such as Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost). The Radio Frequency Signal Classification (RFSC) dataset consists of data collected under different Signal-to-Noise Ratio (SNR) scenarios to analyze the resilience of the classifiers. Among all architectures, the Deep Convolutional Layer based RF (D-CNL-R) model achieved superior modulation recognition accuracy due to its enhanced capability to learn complex nonlinear feature distributions. We observed that the training overhead of the proposed D-CNL-R reduced to $ \simeq 1\times $ with better classification accuracy performance. We also presented an experimental approach for the prediction performance of real-time signals for indoor and outdoor scenarios.

References

[1]	Fu S, Yang F, Xiao Y (2020) Ai inspired intelligent resource management in future wireless network. IEEE Access 8: 22425–22433. https://doi.org/10.1109/ACCESS.2020.2968554
[2]	Zhang Z, Xiao Y, Ma Z, Xiao M, Ding Z, Lei X, et al. (2019) 6g wireless networks: Vision, requirements, architecture, and key technologies. IEEE Vehicular Technology Magazine 14: 28–41. https://doi.org/10.1109/MVT.2019.2921208
[3]	Tang F, Kawamoto Y, Kato N, Liu J (2020) Future intelligent and secure vehicular network toward 6g: Machine-learning approaches. Proceedings of the IEEE 108: 292–307. https://doi.org/10.1109/JPROC.2019.2954595 doi: 10.1109/JPROC.2019.2954595
[4]	Salahdine F, Han T, Zhang N (2023) 5g, 6g, and beyond: Recent advances and future challenges. Annals of Telecommunications 78: 525–549.
[5]	Dobre OA, Abdi A, Bar-Ness Y, Su W (2007) Survey of automatic modulation classification techniques: classical approaches and new trends. IET communications 1: 137–156. https://doi.org/10.1049/iet-com:20050176 doi: 10.1049/iet-com:20050176
[6]	Zhu Z, Nandi AK (2015) Automatic modulation classification: principles, algorithms and applications, John Wiley & Sons.
[7]	Kulin M, Kazaz T, Moerman I, De Poorter E (2017) End-to-end learning from spectrum data a deep learning approach for wireless signal identification in spectrum monitoring applications. IEEE Access 6: 18484 – 18501. https://doi.org/10.1109/ACCESS.2018.2818794 doi: 10.1109/ACCESS.2018.2818794
[8]	Zhang W, Zheng L, Xu Y, Wang G, Wu Y (2018) Supervised learning method for link adaptation algorithm in coded mimo-ofdm systems. In IEEE 4th International Conference on Computer and Communications (ICCC), 414–419. https://doi.org/10.1109/CompComm.2018.8780721
[9]	Song M, Xin C, Zhao Y, Cheng X (2012) Dynamic spectrum access: from cognitive radio to network radio. IEEE Wireless Communications 19: 23–29. https://doi.org/10.1109/MWC.2012.6155873 doi: 10.1109/MWC.2012.6155873
[10]	Trinh HD, Giupponi L, Dini P (2018) Mobile traffic prediction from raw data using lstm networks. In IEEE 29th Annual International Symposium on Personal, Indoor and Mobile Radio Communications(PIMRC), 1827–1832. https://doi.org/10.1109/PIMRC.2018.8581000
[11]	Tang B, Tu Y, Zhang Z, Lin Y (2018) Digital signal modulation classification with data augmentation using generative adversarial nets in cognitive radio networks. IEEE Access 6: 15713–15722. https://doi.org/10.1109/ACCESS.2018.2815741 doi: 10.1109/ACCESS.2018.2815741
[12]	Ujan S, Navidi N, Landry RJ (2020) Hierarchical classification method for radio frequency interference recognition and characterization in satcom. Applied Sciences 10: 4608. https://doi.org/10.3390/app10134608 doi: 10.3390/app10134608
[13]	Jagannath J, O'Connor D, Polosky N, Sheaffer B, Foulke S, Theagarajan LN, et al. (2017) Design and evaluation of hierarchical hybrid automatic modulation classifier using software defined radios. In IEEE Annual Computing and Communication Workshop and Conference (CCWC), 1–7. https://doi.org/10.1109/CCWC.2017.7868362
[14]	Markovic GB, Dukic ML (2015) Joint cumulant estimate correction and decision for cooperative modulation classification by using multiple sensors. Annals of telecommunications-annales des télécommunications 70: 197–206. https://doi.org/10.1007/s12243-014-0437-4
[15]	Khan S, Islam N, Jan Z, Ud Din I, Rodrigues JJPC (2019) A novel deep learning based framework for the detection and classification of breast cancer using transfer learning. Pattern Recognition Letters 125: 1–6. https://doi.org/10.1016/j.patrec.2019.03.022 doi: 10.1016/j.patrec.2019.03.022
[16]	Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1, 1097–1105.
[17]	Lyu Z, Wang Y, Li W, Guo L, Yang J, Sun J, et al. (2020) Robust automatic modulation classification based on convolutional and recurrent fusion network. Physical Communication 43: 101213. https://doi.org/10.1016/j.phycom.2020.101213 doi: 10.1016/j.phycom.2020.101213
[18]	Hagos MT, Kant S (2019) Transfer learning based detection of diabetic retinopathy from small dataset. arXiv preprint arXiv: 1905.07203.
[19]	Shi Q, Gong Y, Guan YL (2008) Asynchronous classification of high-order QAMs. In IEEE Wireless Communications and Networking Conference, 1188–1193. https://doi.org/10.1109/WCNC.2008.214
[20]	O'Shea T, West N (2016) Radio machine learning dataset generation with GNU radio. Proceedings of the GNU Radio Conference 1.
[21]	Guo J, He T, Lausen L, Li M, Lin H, Shi X, et al. (2020) Gluoncv and gluonnlp: Deep learning in computer vision and natural language processing. Journal of Machine Learning Research 21: 1–7.
[22]	Kim K, Akbar IA, Bae KK, Um J, Spooner CM, Reed JH (2007) Cyclostationary approaches to signal detection and classification in cognitive radio. In 2nd IEEE International Symposium on New Frontiers in Dynamic Spectrum Access Networks, 212–215. https://doi.org/10.1109/DYSPAN.2007.35
[23]	Fehske A, Gaeddert J, Reed JH (2005) A new approach to signal classification using spectral correlation and neural networks. In First IEEE International Symposium on New Frontiers in Dynamic Spectrum Access Networks (DySPAN), 144–150. https://doi.org/10.1109/DYSPAN.2005.1542629
[24]	Chen M, Challita U, Saad W, Yin C, Debbah M (2019) Artificial neural networks-based machine learning for wireless networks: A tutorial. IEEE Communications Surveys Tutorials 21: 3039–3071.
[25]	Tekbıyık K, Ekti AR, {Görçin} A, Kurt GK, {Keçeci} C (2020) Robust and fast automatic modulation classification with CNN under multipath fading channels. IEEE Vehicular Technology Conference (VTC), 1–6. https://doi.org/10.1109/VTC2020-Spring48590.2020.9128408
[26]	Peng S, Jiang H, Wang H, Alwageed H, Yao YD (2017) Modulation classification using convolutional neural network based deep learning model. In 26th Wireless and Optical Communication Conference (WOCC), 1–5. https://doi.org/10.1109/WOCC.2017.7929000
[27]	Peng S, Jiang H, Wang H, Alwageed H, Zhou Y, Sebdani M, et al. (2018) Modulation classification based on signal constellation diagrams and deep learning. IEEE Transactions on Neural Networks and Learning Systems 30: 718–727.
[28]	Alhazmi MH, Alymani M, Alhazmi H, Almarhabi A, Samarkandi A, Yao Y (2020) 5{G} signal identification using deep learning. In Wireless and Optical Communications Conference (WOCC), 1–5. https://doi.org/10.1109/WOCC48579.2020.9114912
[29]	Shi J, Hong S, Cai C, Wang Y, Huang H, Gui G (2020) Deep learning-based automatic modulation recognition method in the presence of phase offset. IEEE Access 8: 42841–42847.
[30]	Teng CF, Chou CY, Chen CH, Wu AY (2020) Accumulated polar feature-based deep learning for efficient and lightweight automatic modulation classification with channel compensation mechanism. IEEE Transactions on Vehicular Technology 69: 15472–15485. https://doi.org/10.1109/TVT.2020.3041843
[31]	Roy D, Mukherjee T, Chatterjee M, Pasiliao E (2019) RF transmitter fingerprinting exploiting spatio-temporal properties in raw signal data. In IEEE International Conference On Machine Learning And Applications (ICMLA), 89–96. https://doi.org/10.1109/ICMLA.2019.00023
[32]	Zhang D, Ding W, {Zhang B}, Xie C, {Li H}, Liu C, et al. (2018) Automatic modulation classification based on deeplearning for unmanned aerial vehicles. Sensors 18: 924. https://doi.org/10.3390/s18030924
[33]	Hong D, Zhang Z, Xu X (2017) Automatic modulation classification using recurrent neural networks. In 3rd IEEE International Conference on Computer and Communications (ICCC), 695–700. https://doi.org/10.1109/CompComm.2017.8322633
[34]	Tamizhelakkiya, Chandhar P, Gauni S (2021) Comparison of deep architectures for indoor rf signal classification. In 2021 International Conference on Emerging Techniques in Computational Intelligence (ICETCI), 107–112. https://doi.org/10.1109/ICETCI51973.2021.9574083
[35]	Fu X, Gui G, Wang Y, Gacanin H, Adachi F (2022) Automatic modulation classification based on decentralized learning and ensemble learning. IEEE Transactions on Vehicular Technology 71: 7942–7946. https://doi.org/10.1109/TVT.2022.3164935
[36]	Zhang X, Sun J, Zhang X (2020) Automatic modulation classification based on novel feature extraction algorithms. IEEE Access 8: 16362–16371. https://doi.org/10.1109/ACCESS.2020.2966019
[37]	HackRF, https://greatscottgadgets.com/hackrf/.
[38]	Rtl-sdr, https://www.rtl-sdr.com/.
[39]	Chandhar, https://www.chandhar-labs.com/products/wi-guy/.
[40]	Wu P, Sun B, Su S, Wei J, Zhao J, Wen X (2020) Automatic modulation classification based on deep learning for software-defined radio. Mathematical Problems in Engineering 2020: 2678310. https://doi.org/10.1155/2020/2678310 doi: 10.1155/2020/2678310
[41]	Tamizhelakkiya K, Gauni S, Chandhar P (2023) Transfer learning based location-aided modulation classification in indoor environments for cognitive radio applications. Radioengineering 32. https://doi.org/10.13164/re.2023.0531
[42]	Eluri VK, Mazzuchi TA, Sarkani S (2021) Predicting long-time contributors for github projects using machine learning. Information and Software Technology 138: 106616. https://doi.org/10.1016/j.infsof.2021.106616 doi: 10.1016/j.infsof.2021.106616
[43]	RFSC Dataset for modulation classification, https://www.kaggle.com/datasets/chandharlabs/rfsc-dataset.
[44]	Tamizhelakkiya, Chandhar P, Gauni S (2021) Comparison of deep architectures for Indoor RF signal classification. In International Conference on Emerging Techniques in Computational Intelligence (ICETCI), 107–112. https://doi.org/10.1109/ICETCI51973.2021.9574083
[45]	Yang J, Mostafapour E, Aminfar A, Wang J, Huang H, Akhbari A, et al. (2019) Channel fading effect analysis on diffusion cooperation strategies over adaptive networks. KSII Transactions on Internet and Information Systems 13: 172–185. https://doi.org/10.3837/tiis.2019.01.010 doi: 10.3837/tiis.2019.01.010
[46]	Freire PJ, Osadchuk Y, Spinnler B, Napoli A, Schairer W, Costa N, et al. (2021) Performance versus complexity study of neural network equalizers in coherent optical systems. Journal of Lightwave Technology 39: 6085–6096. https://doi.org/10.1109/JLT.2021.3096286 doi: 10.1109/JLT.2021.3096286
[47]	Hassine K, Erbad A, Hamila R (2019) Important complexity reduction of random forest in multi-classification problem. In International Wireless Communications & Mobile Computing Conference (IWCMC), 226–231. https://doi.org/10.1109/IWCMC.2019.8766544
[48]	Chandhar P, Tamizhelakkiya, Babu S, Krishnakumar V, Sivakumar A, Viswanathan W (2022) 4g spectrum occupancy analysis in chennai-india. In International Conference on Emerging Techniques in Computational Intelligence (ICETCI), 132–135. https://doi.org/10.1109/ICETCI55171.2022.9921373
[49]	3GPP TS 38.211 version 15.2.0 Release 15 for 5G NR, Technical report, 3GPP, 2018.

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)