Blind equalization via the use of generalized pattern search optimization and zero forcing sectionnally convex cost function

The present paper deals with the formulation of the baud spaced blind equalization in the presence of gaussian noise as an unconstrained optimization problem via the use of generalized pattern search (GPS) algorithm and sectionaly convex blind cost function. Simulation results show that the proposed approach is much more likely to outperform the classical CMA in terms of minimum square error (MSE) and intersymbl interference (ISI) quantities, however the global convergence is not warranted for baud spaced blind equalization.