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.