AI-DRIVEN SIGNAL QUALITY ASSESSMENT AND INTELLIGENT NOISE REDUCTION IN DIGITAL COMMUNICATION SYSTEMS USING DEEP LEARNING

Authors

  • MD. SAIRA BANU Author

DOI:

https://doi.org/10.62643/ijerst.2026.v22.n4.4844

Keywords:

Artificial Intelligence, Digital Communication Systems, Signal Quality Assessment, Noise Reduction, Deep Learning, Convolutional Neural Network, Autoencoder, Signal-to-Noise Ratio, Bit Error Rate, Adaptive Filtering.

Abstract

Digital communication systems are frequently affected by noise, interference, fading, and channel impairments that degrade signal quality and reduce the reliability of transmitted information. These impairments can increase the bit error rate (BER), reduce the signal-to-noise ratio (SNR), and negatively affect the overall communication performance. Conventional noise reduction techniques, including fixed digital filters and traditional statistical estimation methods, may provide satisfactory performance under specific noise conditions but can become less effective when the noise characteristics vary dynamically. To address these challenges, this paper proposes an artificial intelligence (AI)-based framework for signal quality assessment and intelligent noise reduction in digital communication systems. The proposed framework processes received digital signals to estimate signal quality using parameters such as SNR, BER, and signal distortion. A deep learning model, such as a convolutional neural network (CNN) or an autoencoder, can be employed to identify signal patterns and suppress unwanted noise while preserving useful signal information. An adaptive filtering mechanism can be incorporated to improve the system's response to changing noise conditions. The enhanced signal is subsequently evaluated using SNR improvement, mean squared error (MSE), BER, and signal reconstruction quality. The proposed framework can be implemented and evaluated using simulated digital modulation schemes, such as binary phase-shift keying (BPSK) and quadrature phase-shift keying (QPSK), under different additive white Gaussian noise and fading-channel conditions. Performance comparisons with conventional filtering techniques can establish the effectiveness of the AI-based approach. The framework aims to improve received signal quality, reduce communication errors, and enhance the reliability of digital communication systems operating under varying noise conditions.

Downloads

Published

21-10-2026

How to Cite

AI-DRIVEN SIGNAL QUALITY ASSESSMENT AND INTELLIGENT NOISE REDUCTION IN DIGITAL COMMUNICATION SYSTEMS USING DEEP LEARNING. (2026). International Journal of Engineering Research and Science & Technology, 22(4), 436-448. https://doi.org/10.62643/ijerst.2026.v22.n4.4844