Abstract
Equalizer in communication system plays an important role for reducing ISI (inter-symbol-interference) which is caused by multi-path fading and Doppler shift. The author introduce BP neural network as an equalizer, one is the same as traditional adaptive LMS in methodology but having more complicated character in detail. Firstly, we study the performance in training sets and find LMS behave more rapid in convergence with lower percentage of error for our considering system. But as the taps (the number of input layer nodes) increasing, NNE (neural network equalizer) show more robust. Then, effects caused by number of nodes in input layer and hidden layer are studied by introducing overshoot zero line. We find that the hidden nodes are more susceptible to it. Finally, we simulate and compare the BER (bit error ratio) performance in different SNR, it shows that lower BER caused by NNE although one is inferior to LMS in training. Furthermore, a mathematic expression is derived both for NNE and LMS because of an approximately Iinearly relationship between BER performance with SNR in log-field.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
