Title :
Multiuser detection using simulated annealing Hopfield neural network for DS-UWB systems
Author :
Yao, Yung-cheng ; Cheng, Chia-Hsin ; Wen, Guo-jun ; Wen, Jyh-horng
Author_Institution :
Dept. of Electr. Eng., Nat. Chung Cheng Univ., Chiayi, Taiwan
Abstract :
The authors introduced the simulated annealing Hopfield neural network and applied it to multiuser detection in direct sequence-ultra-wideband (DS-UWB) systems in this paper. The conventional HNN algorithm may converge easily to local minimum. In order to solve this problem, the authors proposed modified HNN based on simulated annealing (SA) method which can avoid local minimum problem. From simulation results, the HNN detector based on SA method provided an attractive performance. The HNN detector based on SA method could be implemented easily on hardware circuit in the multiuser DS-UWB systems.
Keywords :
Hopfield neural nets; simulated annealing; ultra wideband communication; DS-UWB systems; HNN algorithm; HNN detector; direct sequence-ultra-wideband systems; hardware circuit; multiuser detection; simulated annealing Hopfield neural network; Channel models; Cooling; Detectors; Hopfield neural networks; Machine learning; Multiuser detection; Simulated annealing; Hopfield; Neural network; SA;
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2011 International Conference on
Conference_Location :
Guilin
Print_ISBN :
978-1-4577-0305-8
DOI :
10.1109/ICMLC.2011.6016758