摘要
根据克服数字通信中码间干扰(ISI)的最佳均衡解一般表达式,提出了一种新的自适应神经网络均衡器结构,然后导出了基于该结构的一种自适应算法和相应的学习规则,最后对这种自适应神经网络均衡器进行了计算机模拟。研究结果表明:文中提出的神经网络均衡器非常有效,比传统线性均衡器和Gibson等人提出的多层感知均衡器(MLPE)性能更优越,更具实用性。
This paper suggests a novel adaptive neural network channel equalizer to overcome the inter-symbol interference (ISI) existing in various digital communication systems based on the general optimum equalization solutions, derives its adaptive algorithms and learning rules, and investigates the performance of the novel neural network equalizer applied to some communication systems by means of computer simulations. It is concluded that the novel neural network equalizer is very effective in implementing the optimum channel equalization and it has superior performances over both the traditional linear equalizers and the multilayer perceptron equalizers (MLPE) suggested by Gibson, etc.
出处
《电子科技大学学报》
EI
CAS
CSCD
北大核心
1993年第3期243-247,共5页
Journal of University of Electronic Science and Technology of China
关键词
数字通信
自适应均衡
神经网络
digital communication
intersymbol interferences
adaptive equalizations
neural networks
learning rules
