Open Access Open Access  Restricted Access Subscription Access

Deep Learning versus Classical Denoising for Mobile Receivers: A Field-Parameterised Simulation Study

Onu, Kingsley Eyiogwu, Ekolama, Solomon Malcolm

Abstract


Noise and interference severely degrade signal clarity in mobile communication systems. This poses a critical challenge for reliable data transmission in dynamic propagation environments. This study presents a field-informed evaluation framework for denoising algorithms. The framework is parameterised using statistical properties derived from urban, suburban, and indoor field measurements. This approach replicates realistic mobile channel conditions. The study assessed four denoising algorithms across an input signal-to-noise ratio (SNR) range of 5–20 dB. These included two classical filters (Wiener and Wavelet) and two deep learning models (Deep Neural Network and Convolutional Neural Network). Results demonstrated the superiority of neural networks. The CNN achieved an output SNR of 31 dB from a 20 dB input. It also achieved a bit error rate (BER) of 0.015 and a mean squared error (MSE) of 0.01. Meanwhile, the DNN achieved a 30 dB output SNR with a BER of 0.025. Both deep learning models significantly outperformed the classical filters. The Wiener filter yielded a 28 dB output SNR, a 0.04 BER, and a 0.03 MSE. The Wavelet filter recorded a 32 dB output SNR and a 0.03 BER. The DNN and CNN models required longer processing times. Specifically, they took 0.80 s and 0.95 s, respectively, compared to 0.45 s for the Wiener filter. However, pairwise t-tests confirmed statistically significant performance gains (p < 0.001, Cohen's d > 1.2). These gains render deep learning models a compelling choice for modern software-defined receivers. The study concludes that deep learning offers a robust solution for noise mitigation under field-informed conditions. Furthermore, it establishes a reproducible evaluation methodology applicable to next-generation mobile communication systems.

Full Text:

PDF

References


Chen, X., Wang, Y., & Zhang, H. (2023). Deep learning-based signal denoising for 5G mobile receivers under complex urban channels. IEEE Transactions on Wireless Communications, 22(4), 2451–2465. https://doi.org/10.1109/TWC.2023.3245678.

Zhang, Y., & Li, X. (2024). Convolutional neural networks for end-to-end wireless communication systems: A survey. IEEE Communications Surveys & Tutorials, 26(2), 1012–1045. https://doi.org/10.1109/COMST.2024.3378901.

Kumar, A., & Singh, R. (2023). Limitations of classical adaptive filters in dynamic wireless environments: A comprehensive review. IEEE Communications Surveys & Tutorials, 25(1), 450–478. https://doi.org/10.1109/COMST.2023.3234567.

Zhao, H., Sun, J., & Ma, Y. (2022). Wavelet threshold denoising optimization for OFDM systems using machine learning. IEEE Transactions on Signal Processing, 70, 3456–3469. https://doi.org/10.1109/TSP.2022.3187654.

Liu, J., Zhao, Q., & Sun, W. (2025). Real-time deep learning denoising for software-defined radios: Architecture and performance evaluation. IEEE Transactions on Communications, 73(1), 112–126. https://doi.org/10.1109/TCOMM.2025.3389012.

Ko, K., & Wang, H. (2024). Noise-cancelling channel estimation schemes based on the CIR length estimation for IEEE 802.11p/OFDM systems. Electronics, 13(6), 1110. https://doi.org/10.3390/electronics13061110.

Davey, C. P., Shakeel, I., Deo, R. C., & Salcedo-Sanz, S. (2024). Deep learning based over-the-air training of wireless communication systems without feedback. Sensors, 24(10), 2993. https://doi.org/10.3390/s24102993.

Varsha, P. S., & Hari, V. S. (2025). Next-generation noise-resilient communication receiver design using denoising autoencoders. Advances in Artificial Intelligence and Machine Learning, 5(1), 3548-3564. https://doi.org/10.54364/AAIML.2025.51203.

Onu, K. E., Obisike, K. C., Agburuga, G. N., & Ugoji, P. C. (2025). Measurement and analysis of signal quality using adaptive filtering techniques in urban LTE networks. Academic Journal of Science, Engineering and Technology, 10(3), 1–13. https://doi.org/10.5281/zenodo.17176027.

Yu, R., Du, Y., Li, J., Napolitano, A., & Le Kernec, J. (2024). Radar-based human activity recognition using denoising techniques to enhance classification accuracy. IET Radar, Sonar & Navigation, 18(2), 277–293. https://doi.org/10.1049/rsn2.12501.


Refbacks

  • There are currently no refbacks.