| 基于递归神经网络的卷积码解码器的研究 |
| |
| 引用本文： | 林国华,殷奎喜. 基于递归神经网络的卷积码解码器的研究[J]. 现代电子技术, 2007, 30(1): 61-62 |
| |
| 作者姓名： | 林国华 殷奎喜 |
| |
| 作者单位： | 1. 南京师范大学,物理科学与技术学院,江苏,南京,210097;解放军镇江船艇学院,江苏,镇江,212003
2. 南京师范大学,物理科学与技术学院,江苏,南京,210097 |
| |
| 摘 要： | 详细介绍了一种基于递归神经网络(RNN)的1/n卷积码解码器的原理与实现。仿真结果表明RNN解码器与Vterbi解码器效果很接近,对一些特殊的卷积码,性能非常好。并通过模拟退火技术对此解码器的性能进行了改善。
|
| 关 键 词： | 卷积码 解码 噪声能量函数 退火算法 递归神经网络 |
| 文章编号： | 1004-373X（2007）01-061-02 |
| 收稿时间： | 2006-06-16 |
| 修稿时间： | 2006-06-16 |
Research of Convolutional Decoder Based on Recurrent Neural Network(RNN) |
| |
| LIN Guohua,YIN Kuixi. Research of Convolutional Decoder Based on Recurrent Neural Network(RNN)[J]. Modern Electronic Technique, 2007, 30(1): 61-62 |
| |
| Authors: | LIN Guohua YIN Kuixi |
| |
| Abstract: | In this paper a detailed principle and application of a 1/n rate convolution decoder based on Recurrent Neural Network(RNN) are introduced.Simulation results have confirmed that the RNN decoder is capable of performing very close to the Viterbi decoder and works very well for some specially structured convolution codes.In particular,decoding capabilities of RNN decoders are improved when Simulated Annealing(SA) technique has been used. |
| |
| Keywords: | convolution codes decoding noise energy function simulated annealing recurrent neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
