Method for designing adaptive decision feedback equalizer based on support vector machine

Abstract

The invention discloses a method for designing an adaptive decision feedback equalizer based on a support vector machine. The method comprises the following steps of: (1) inputting a training data sequence agreed by a transmitting end and a receiving end of a digital wireless communication system into an adaptive decision feedback equalizer; (2) initializing; (3) obtaining an optimal weight vector; (4) selecting a radial basis function as a support vector machine kernel function, solving a penalty factor in the support vector machine kernel function and an index coefficient of the radial basis kernel function by a cross validation way, and obtaining the optimal coefficient of the support vector machine; (5) initializing again; and (6) obtaining the final output signal of the equalizer. Through the invention, the shortcoming of low decision accuracy of the adaptive decision feedback equalizer in the prior art can be effectively overcome, the equalizing effect of the adaptive decision feedback equalizer is effectively improved, and the bit error rate of the system is obviously reduced.

Description

technical field [0001] The invention belongs to the technical field of wireless communication signal processing, and further relates to a design method of an adaptive decision feedback equalizer based on a support vector machine. The invention can effectively compensate the influence of the communication channel and noise on the transmission signal, reduce the bit error rate, and can be applied to the digital wireless communication system working under bad communication channel conditions to improve its reliability. Background technique [0002] In digital wireless communication systems, due to the influence of multipath fading channels, digital signals will generate intersymbol interference during transmission, which will cause distortion and distortion of the received signals, which will cause the signals at the receiving end to be restored by mistake, significantly Increase the bit error rate of the system and reduce the quality of service QoS of the wireless communicatio...

AI Technical Summary

Problems solved by technology

[0005] The above two authorized patents belong to the traditional adaptive decision feedback channel equalizer, and the decision part adopts the traditional decision method (such as hard decision) to divide the equalized signal. Although this method is simple and easy to implement, the decision accuracy is low , the signal obtained after its decision has a high error rate, if these signals are fed back to the equalizer as a "reference signal" to process the subsequent signal sequence, it will lead to a high error rate in the subsequent output signal sequence of the equalizer Error rate, which will seriously reduce the equalization effect of the traditional adaptive decision feedback channel equalizer, resulting in a high bit error rate of the digital communication system, affecting the reliability of the system

Images