Tu?cu, EminKaya, IsmailÖzen, Ali2025-02-242025-02-242012978-146730056-810.1109/SIU.2012.62046302-s2.0-84863470709https://doi.org/10.1109/SIU.2012.6204630https://hdl.handle.net/20.500.14440/5842012 20th Signal Processing and Communications Applications Conference -- SIU 2012 -- 18 April 2012 through 20 April 2012 -- Fethiye -- Mugla -- 90786As an alternative technique to well-known constant modulus algorithm (CMA), a Decision Feedback Equalizer via Channel Matched Filter (CMF-DFE) based blind channel estimation and equalization algorithm is proposed in this paper. The proposed technique employs Particle Swarm Optimization (PSO) in training, where the conventional CMA and least mean squares (LMS) based training algorithms are found slow and their convergence strictly depend on the step size parameter. On the other hand, if the PSO training algorithm is employed, it provides a faster convergence and less sensitivity to training parameters. Thus, a rapid converging high performance blind channel estimation and equalization method is obtained, as it is compared to CMF-DFE based blind LMS and CMA algorithm. Here, the price is paid for more complexity, however the obtained performance promises to compete with reference training sequence based parameter estimation techniques. © 2012 IEEE.trinfo:eu-repo/semantics/closedAccessAlgorithmsParameter estimationParticle swarm optimization (PSO)Blind channel estimationChannel matched filtersConstant modulus algorithmsEqualization algorithmsEstimation techniquesFaster convergenceLeast mean square(LMS)Step sizeTraining algorithmsTraining parametersTraining sequencesBlind equalizationConference ObjectN/A