| 基于ANN的声目标识别系统及其DSP实时实现 |
| |
| 引用本文： | 李云剑,张雄伟. 基于ANN的声目标识别系统及其DSP实时实现[J]. 电子工程师, 2004, 30(4): 50-52 |
| |
| 作者姓名： | 李云剑 张雄伟 |
| |
| 作者单位： | 解放军理工大学通信工程学院,江苏省,南京市,210007 |
| |
| 摘 要： | 介绍了一种基于人工神经网络(ANN)的声目标识别系统,概述了用MATLAB专用工具箱对神经网络权值进行训练及仿真的过程,叙述了ANN目标识别系统的数字信号处理器(DSP)实时实现过程,并着重分析定点实现过程中程序变量的定标、非线性运算的实现、溢出的处理等关键步骤.对不同字长的识别结果进行比较表明,基于定点实时实现的系统数据保持很高的精度,可以得到与浮点处理相同的识别率.
|
| 关 键 词： | 声目标识别系统 人工神经网络(ANN) DSP实时实现 |
| 修稿时间： | 2003-11-24 |
An Acoustic Target Recognition System Based on ANN and its DSP Real Time Implementation |
| |
| Li Yunjian,Zhang Xiongwei. An Acoustic Target Recognition System Based on ANN and its DSP Real Time Implementation[J]. Electronic Engineer, 2004, 30(4): 50-52 |
| |
| Authors: | Li Yunjian Zhang Xiongwei |
| |
| Abstract: | An acoustic target recognition system based on an artificial neural network is introduced, and the training and simulation of neural network based on matlab are also discussed. Then, the DSP real time implementation of the system is presented in detail. Some key processes, such as variables scaling, nonlinear operation and overflow protection are especially analyzed. Finally, the comparison of all recognition results shows that DSP real time implementation is accurate. |
| |
| Keywords: | acoustic target recognition system artificial neural network DSP real time implementation |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
