Recursive DLS solution for extreme learning machine-based channel equalizer

Recently, a new learning algorithm for a single-hidden-layer feedforward neural network (SLFN), named the complex extreme learning machine (C-ELM), has been proposed in Li et al. [Fully complex extreme learning machine, Neurocomputing 68 (2005) 306–314]. Although it shows potential applicability in many areas, there is still room for improvement in performance, especially in training-based equalization applications in which the noise is only within the received data. In this paper, we propose a new solution applying the data least squares (DLS) method. Simulations show that DLS-based C-ELM outperforms the ordinary-least-square-based one in channel equalization problems.