颈动脉多普勒信号自回归滑动平均模型极点特征及分类应用

对颈动脉多普勒血流信号实现了一种基于自回归滑动平均(ARMA)模型、并采用反向传输(BP)神经网络分析ARMA模型极点特征的系统,以达到诊断脑梗塞疾病的目的。首先对音频颈动脉多普勒血流信号分时间段建立ARMA模型,得出模型极点分布的特征参数,研究这些特征参数对脑梗塞疾病诊断的敏感性,然后对敏感的特征参数利用BP神经网络进行分类,对是否存在脑梗塞的血流状况进行判别。共使用474例颈动脉血流信号来建立合适的神经网络,使用52例信号进行测试,结果表明:系统训练和测试的正确率均大于94%,可以满足临床的要求。

The ARMA model's pole characteristics of Doppler signals from the carotid artery and their classification application

In order to diagnose the cerebral infarction, a classification system based on the ARMA model and BP neural network is presented to analyze blood flow Doppler signals from the carotid artery. In this system, an ARMA model was firstly used to analyze the audio Doppler blood flow signals from the carotid artery. Then several characteristic parameters of the pole's distribution were estimated. After studies of these characteristic parameters' sensitivity to the cerebral infarction diagnosis, a BP neural network using sensitive parameters was established to classify the normal or abnormal state of the cerebral vessel. With 474 cases used to establish the appropriate neural network, and 52 cases used to test the network, results showed that the correct classification rate of both training and testing were over 94%. Thus this system is useful to diagnose the cerebral infarction.