基于仿生模式识别和PCA/ICA的DOA估计方法

A DOA Estimation Method Based on Biomimetic Pattern Recognition and PCA/ICA

本文提出了一种基于仿生模式识别和PCA/ICA的DOA估计方法 .这种方法的建模过程是用在实际环境下采集的训练样本构造人工神经网络模型 ,对环境的适应能力较强 ;且这种方法采用PCA/ICA进行特征提取 ,使数据得到有效压缩 ,可以实现系统实时处理 .实验结果表明 :在信噪比为 2 0dB和 0dB时 ,该方法的正确估计率可达10 0 % ;在信噪比降为 - 2 0dB时 ,该方法仍有 83%的可识别率 .

The applicability of biomimetic pattern recognition to information processing of abstract objects is studied,and then a DOA estimation method based on biomimetic pattern recognition and PCA/ICA is advanced.In this method,the output signals of antenna array are collected in practical conditions and expressed as feature vectors by using PCA/ICA.These feature vectors are studied with the method of high dimensional geometry and the principle of biomimetic pattern recognition.By using the feature vectors as training samples ANN models are constructed.In our experiments,when SNR is 20dB or 0dB,the correct estimation rate is 100%;when SNR is -20dB,the correct estimation rate is 83%;The experimental results show that the proposed method has the great advantage of preferable robustness and fast computation.