RADIOELECTRONICS
An Automatic Modulation Classification Approach Based on an Efficient and Explainable Convolutional Neural Networks for Wireless Communication
Mohsin Ali Ahmed
Al-Ma‘moon University College, https://almamonuc.edu.iq/
14 Ramadan Street, Baghdad, Iraq
Email: mohsin.a.ahmed@almamonuc.edu.iq
Ikhlas M. Farhan
University of Technology, https://uotechnology.edu.iq/
Al Wehada-Neighborhood, 19006, Baghdad, Iraq
Email: ikhlas.m.farhan@uotechnology.edu.iq
Hussein M. Hussein
Ninevah University, https://uoninevah.edu.iq/
Al-Majmoua Street, 41001, Mosul, Iraq
Email: hussein.hussein@uoninevah.edu.iq
Anas Fouad Ahmed
Al-Iraqia University, https://aliraqia.edu.iq/
Al Adhmia-Haiba Khaton, 6029, Baghdad, Iraq
Email: anas.ahmed@aliraqia.edu.iq
Ahmed Sabah Noori
Al-Iraqia University, https://aliraqia.edu.iq/
Al Adhmia – Haiba Khaton, 6029, Baghdad
Email: ahmedsabahnoori@aliraqia.edu.iq
Received August 15, 2025, peer-reviewed September 01, 2025, accepted September 04, 2025, published October 21, 2025
Abstract: Automatic Modulation Classification (AMC) is an essential element of cognitive radio network that provides an awareness of the spectrum as well as adaptive communication. Nevertheless, the current deep learning-based AMC schemes frequently struggle to achieve a trade-off between classification precision, computational speed, and model explainability, which are essential to real-time execution on edge computing devices. To solve these problems, this paper presents a wavelet-augmented, pruned, and quantized convolutional neural network (CNN) framework that uses Grad-CAM explainability. Evaluations on the RadioML2016.10a dataset across SNR levels from −20 dB to +20 dB are done. The suggested model obtains 99.1% accuracy at +10 dB. Although maintaining 85.6% accuracy at −4 dB SNR, SNR shows robustness under noisy surroundings. With an average inference latency of 5.2 ms and a power consumption of 5.2 W, deployment profiling on an NVIDIA Jetson Nano with a USRP B210 confirms suitability for real-time cognitive radio applications. Transparency and trust are increased when Grad-CAM visualizations verify that the model takes into account modulation-specific characteristics like envelope variations in AM signals, amplitude clusters in 16-QAM, and phase transitions in QPSK. Compared to more recent AMC approaches (2016-2024), the proposed framework is identified as the first to be both highly accurate, lightweight edge deployable, and explainable, providing a solid base to practical AMC of next-generation wireless systems.
Keywords: Modulation Classification; Explainable AI; Light Convolutional Neural Networks (CNN); Quantization; Edge Deployment
UDC 621.391.8:004.932.2
RENSIT, 2025, 17(5):545-552e
DOI: 10.17725/j.rensit.2025.17.545
Full-text electronic version of this article - web site http://en.rensit.ru/vypuski/article/703/17(5)545-552e.pdf