Title :
A Blind Equalization Algorithm Based on Dynamic Fuzzy Neural Network
Author :
Hou, Yongxing ; Bu, Qinghua
Author_Institution :
Coll. of Electr. & Power Eng., Taiyuan Univ. of Technol., Taiyuan
Abstract :
The research of blind equalization algorithm based on the dynamic fuzzy neural network (DFNN) is proposed in this paper. The DFNN possesses characteristics such as dynamic mapping and restraint noise. The blind equalization is the process of dynamic equalization essentially because digital communication channel is time-varying and indeterminate. The algorithm proposed in this paper accords with the dynamic characteristic of channel because it uses current data and history data. Hence, the new algorithm possesses distinct advantages of stability, convergence speed and convergence properties over the traditional neural network (NN) blind equalization algorithm. The improved performance of the proposed models is confirmed through computer simulations.
Keywords :
blind equalisers; fuzzy neural nets; blind equalization algorithm; digital communication channel; dynamic fuzzy neural network; dynamic mapping; restraint noise; Bandwidth; Blind equalizers; Computer simulation; Convergence; Fuzzy neural networks; Heuristic algorithms; Neural networks; Signal processing algorithms; Training data; Wireless communication; blind equalization; dynamic mapping; fuzzy neural network; time-varing channel;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery, 2008. FSKD '08. Fifth International Conference on
Conference_Location :
Shandong
Print_ISBN :
978-0-7695-3305-6
DOI :
10.1109/FSKD.2008.297