Abstract:

An adaptive support vector machine decision feedback equalizer (ASVM-DFE) based on the least square support vector machine (LS-SVM) is proposed, it solves linear system iteratively with less computational intensity. An adaptive non-singleton fuzzy support vector machine decision feedback equalizer (ANSFSVMDFE) is also presented, it adopts the non-singleton fuzzy Gaussian kernel function with similar characteristic of pre-filter and is modified with a space transformation based approach. Simulations under nonlinear time variant channels show that ASVM-DFE and ANSFSVM-DFE perform very well on nonlinear equalization and ANSFSVM-DFE acts especially well in resisting abrupt interference.