H. Lin and K. Yamashita (Japan)
blind equalization, RBF equalizer, decision feedback, cluster map
Recently, a cluster map based blind RBF equalizer (CM BRE) has been proposed. By utilizing the underlying struc ture characteristics of RBF equalizer, the CM-BRE can be implemented by the combination of neural-gas algorithm (NGA) with several sorting operations. Although it can achieve identical performance with the optimal RBF equal izer, the high computational load mainly caused by NGA limits it's application. In this paper, we propose a downsiz ing method that employs the inter-relation among RBF cen ters and significantly reduce the NGA's computational load. Furthermore, a method for determine the feedback vector is derived, then CM-BRE is extended to a cluster map based blind RBF decision feedback equalizer (CM-BRDFE). The proposed CM-BRDFE also shows the close performance with the optimal RBF decision feedback equalizer in simu lations.
Important Links:
Go Back
