提出一种新的算法：逆主元法，利用高斯点扩展函数的特性，在径向基神经网络的模型下，对图像进行盲目复原。-a new algorithm : inverse main element method using Gaussian point spread function of the characteristics the RBF neural network model, the image blind rehabilitation.

现有数字信号自动调制识别方法大多只适用于无记忆信号，如PSK、ASK、FSK信号等。将有记忆 信号(MSK信号)和无记忆信号一起考虑，提出了一种改进的数字信号自动识别方法。该方法采用信号的瞬时统 计量作为特征参数，采用多层神经网络作为分类器。计算机仿真表明：当噪声采用高斯白噪声，并且信噪比大于 l5 dB时，识别率高于96％ ；当信噪比不低于l0 dB时，识别率不低于90％。,Existing digital signal automatic modulation recognition

very good Gaussian Mixture Models and Probabilistic Decision-Based Neural Networks for Pattern Classification - A Comparative Study document -very good Gaussian Mixture Models and Probabilistic Decision-Based Neural Networks for Pattern Classificatio