Automatic Modulation Classification Using Time-Frequency Features in a GNU Radio-Based Framework
| International Journal of Electrical and Electronics Engineering |
| © 2026 by SSRG - IJEEE Journal |
| Volume 13 Issue 3 |
| Year of Publication : 2026 |
| Authors : Raman R, Deepa N Reddy, S.Vishali, Rama Krishna Prasadh H |
10.14445/23488379/IJEEE-V13I3P104
How to Cite?
Raman R, Deepa N Reddy, S.Vishali, Rama Krishna Prasadh H, "Automatic Modulation Classification Using Time-Frequency Features in a GNU Radio-Based Framework," SSRG International Journal of Electrical and Electronics Engineering, vol. 13, no. 3, pp. 38-50, 2026. Crossref, https://doi.org/10.14445/23488379/IJEEE-V13I3P104
Abstract:
Automatic Modulation Classification (AMC) is one of the most crucial functions in the advanced wireless communication systems. Mainly, it is used in applications such as cognitive radio, dynamic spectrum access, and interference monitoring, where the knowledge of the transmitted signals is lacking. In the current work, we scrutinize an AMC framework with BPSK, QPSK, and 16-QAM as candidates for modulation under diverse Signal to Noise Ratio (SNR) conditions in detail. A synthetic dataset is produced by means of self-made GNU Radio flowgraphs with the addition of white Gaussian noise in order to mimic real-world wireless transmission situations. Time-frequency features are retrieved with the Short-Time Fourier Transform (STFT) and discrete wavelet transform, and three classical machine learning algorithms, Naive Bayes, Random Forest, and Support Vector Machine (SVM), are applied to classification. The framework is rated in terms of both classification accuracy and computational efficiency at varying SNR levels. The outcomes show that SVM coupled with wavelet features reaches the peak classification accuracy of 97.0% at 10 dB SNR, while the Naive Bayes classifier is the fastest in training time, and hence it can be deployed in real-time and resource-scarce applications. The findings indicate that combining lightweight machine learning methods with suitable time-frequency features can be an effective and efficient alternative to deep learning AMC frameworks in terms of computational cost.
Keywords:
Modulation Classification, Wavelet Transform, Short-Term Fourier transform, Machine learning, Signal to Noise Ratio.
References:
[1] Min Wu et al., “Automatic Modulation Classification based on Wavelet Analysis and Convolution Neural Network,” Electronics, vol. 14, no. 19, pp. 1-16, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Fan Wang et al., “Automatic Modulation Classification using Hybrid Data Augmentation and Lightweight Neural Network,” Sensors, vol. 23, no. 9, pp. 1-16, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Anwr Hasan Yahya Hasan Abohadi et al., “Automatic Modulation Classification using Fractional S-Transform and Semi-Supervised Learning with Confidence-Guided Consistency Regularization,” Knowledge-based Systems, vol. 336, 2026.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Asif Shakil Ahamed et al., “Zero-Shot Short Time Fourier Transform Radar and Communication Signal Classification,” Discover Electronics, vol. 2, no. 1, pp. 1-17, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Wenwen Li et al., “Wavelet Transform based Modulation Classification for 5G and UAV Communication in Multipath Fading Channel,” Physical Communication, vol. 34, pp. 272-282, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Longmei Zhou, Zhuo Sun, and Wenbo Wang, “Learning to Short-Time Fourier Transform in Spectrum Sensing,” Physical Communication, vol. 25, pp. 420-425, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Qinghe Zheng et al., “Recent Advances in Automatic Modulation Classification Technology: Methods, Results, and Prospects,” International Journal of Intelligent Systems, vol. 2025, no. 1, pp. 1-28, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Haithem Ben Chikha, Alaa Alaerjan, and Randa Jabeur, “Deep Learning for Enhancing Automatic Classification of M-PSK and M-QAM Waveform Signals Dedicated to Single-Relay Cooperative MIMO 5G Systems,” Scientific Reports, vol. 15, no. 1, pp. 1-11, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Peng Wu et al., “Automatic Modulation Classification based on Deep Learning for Software-Defined Radio,” Mathematical Problems in Engineering, vol. 2020, no. 1, pp. 1-13, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Luke Boegner et al., “Large Scale Radio Frequency Signal Classification,” arXiv preprint, pp. 1-29, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Surendra Solanki, Banalaxmi Brahma, and Yadvendra Pratap Singh, “Automatic Modulation Classification for CR using Deep Learning,” SN Computer Science, vol. 5, no. 8, pp. 1-19, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Ramiro Utrilla, “MIGOU-MOD: A Dataset of Modulated Radio Signals Acquired with MIGOU, A Low-Power IoT Experimental Platform,” Mendeley Data, vol. 1, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Fuxin Zhang et al., “Deep Learning based Automatic Modulation Recognition: Models, Datasets, and Challenges,” Digital Signal Processing, vol. 129, pp. 1-19, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Hamza Ouamna et al., “Deep Learning-Assisted Automatic Modulation Classification using Spectrograms,” Engineering, Technology and Applied Science Research, vol. 15, no. 1, pp. 19925-19932, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Faheem Ur Rehman, Qamar Abbas, and M. Karam Shehzad, “DL-AMC: Deep Learning for Automatic Modulation Classification,” arXiv preprint, pp. 1-5, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[16] To Truong An et al., “Efficient Automatic Modulation Classification for Next-Generation Wireless Networks,” IEEE Transactions on Green Communications and Networking, vol. 10, pp. 249-259, 2026.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Xiaoqian Qin et al., “Multilevel Adaptive Wavelet Decomposition Network-based Automatic Modulation Recognition: Exploiting Time-Frequency Multiscale Correlations,” IEEE Transactions on Cognitive Communications and Networking, vol. 11, no. 5, pp. 3218-3231, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Soyabul Islam, and Mirza Mohd Shahriar Maswood, “Designing Novel Deep Learning based Frameworks for Performance Improvement of Automatic Modulation Classification,” Engineering Applications of Artificial Intelligence, vol. 152, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Noureddine El-Haryqy et al., “Improved Automatic Modulation Recognition using Deep Learning with Additive Attention,” Results in Engineering, vol. 26, pp. 1-14, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Bachir Jdid et al., “Machine Learning based Automatic Modulation Recognition for Wireless Communications: A Comprehensive Survey,” IEEE Access, vol. 9, pp. 57851-57873, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[21] To Truong An, and Byung Moo Lee, “Robust Automatic Modulation Classification in Low Signal to Noise Ratio,” IEEE Access, vol. 11, pp. 7860-7872, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Xiaoya Zuo et al., “An Automatic Modulation Recognition Algorithm based on Time-Frequency Features and Deep Learning with Fading Channels,” Remote Sensing, vol. 16, no. 23, pp. 1-20, 2024.
[CrossRef] [Google Scholar] [Publisher Link]