Authors : Bidyutprabha Nayak; Bandita Nayak; Kanaka Naik; Udgatika Naik

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/2pbt8sd7

Scribd : https://tinyurl.com/8n9dk9y8

DOI : https://doi.org/10.38124/ijisrt/26apr2110

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Channel equalization remains a critical problem in digital communication systems under dispersive and noisy environments. Conventional adaptive techniques such as least mean square (LMS) exhibit fast convergence but suffer from local minima and performance degradation in complex channels. In contrast, genetic algorithms (GA) provide global optimization capability at the cost of high computational burden and slow convergence. This work proposes an adaptive hybrid LMS–GA equalizer that dynamically switches between local and global search based on real-time error behavior. A normalized LMS (NLMS) framework is employed for stable and rapid adaptation, while GA is selectively triggered during stagnation or performance degradation using a sliding-window mean square error criterion with cooldown control. Simulation results demonstrate that the proposed hybrid approach achieves superior convergence characteristics and reduced steady-state error compared to standalone LMS and GA methods. The equalized signal shows high correlation with the transmitted sequence, and error dynamics confirm stable adaptation with minimal oscillations. Furthermore, the adaptive switching mechanism ensures that global optimization is invoked only when necessary, thereby maintaining computational efficiency. The proposed method is particularly effective in channels with severe distortion, where conventional LMS fails to converge optimally. The study establishes that controlled hybridization, rather than continuous combination, is key to improving equalization performance. The framework can be extended to nonlinear channels and integrated with advanced interpretability-driven control strategies for next-generation adaptive communication systems.

References :

1. S. Haykin, Adaptive Filter Theory, 5th ed., Pearson, 2014.
2. B. Widrow and S. D. Stearns, Adaptive Signal Processing, Prentice Hall, 1985.
3. B. Widrow and M. E. Hoff, “Adaptive switching circuits,” IRE WESCON Convention Record, pp. 96–104, 1960.
4. A. H. Sayed, Fundamentals of Adaptive Filtering, Wiley, 2003.
5. D. E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, 1989.
6. K. Deb, Optimization for Engineering Design: Algorithms and Examples, Prentice Hall, 2004.
7. Z. Michalewicz, Genetic Algorithms + Data Structures = Evolution Programs, Springer, 1996.
8. M. Pant, R. Thangaraj, and A. Abraham, “Hybrid evolutionary algorithms for adaptive filtering,” Applied Soft Computing, vol. 10, no. 2, pp. 389–395, 2010.
9. J. R. Treichler, I. Fijalkow, and C. R. Johnson, “Fractionally spaced equalizers: How long should they really be?” IEEE Signal Processing Magazine, vol. 13, no. 3, pp. 65–81, 1996.
10. Y. Shi and R. Eberhart, “A modified particle swarm optimizer,” IEEE International Conference on Evolutionary Computation, pp. 69–73, 1998.
11. S. Chen, B. Mulgrew, and S. McLaughlin, “Adaptive Bayesian equalizer with decision feedback,” IEEE Transactions on Signal Processing, vol. 41, no. 9, pp. 2910–2917, 1993.