Fractional Order Stochastic Pairwise Conjugate Gradient Algorithm For Adaptive Filtering

in this paper, we propose Fractional order Stochastic Pairwise Conjugate Gradient Algorithm (FSPCGA) by introducing fractional order gradient in weight adaptation relation of Stochastic Pairwise Conjugate Gradient AAlgorithm (SPCGA) for adaptive filtering. Performance analysis of the proposed algorithm is compared with Least Mean Square (LMS) algorithm and SQCGA by appling over channel equalization problem. Convergence rate of FSPCGA is better than convergence rates SPCGA and LMS under certain conditions. FSPCGA offers best filetr weights estimation as long as fractional order of the gradient increase and hence leads to achieve global minima in stochastic setting.