论文部分内容阅读
心室纤颤信号必须准确而及时地识别,如果不使用除颤器及时进行除颤,病人会迅速死亡。另一方面,如果心室纤颤信号没有发生,而误判为心室纤颤信号,给予电击,则病人的心脏受到不应有的损伤,这也属于严重的医疗事故。因此快速与准确的识别显得十分重要。自70年代以来,世界上许多科学家都在探讨各种方法,以期望使用计算机自动识别心室纤颤信号,但均因达不到实时判别的要求或准确率不够高而不能用于自动除颤器检测的设计方案。本文介绍了一种准确率高而又较简易的快速识别法。这一方法是取一秒心电信号,进行有限长度离散信号的自相关,然后对该自相关函数作零切割,让自相关函数变成一串二进制脉冲串,接着以一秒信号的脉冲串数作为特征参数,设计分类器。经证明,心室纤颤信号(VF信号)(Ventricular Fibrillation)和心动过速信号(VT信号)(Ventricular Tachycar-dia)的特征参数均属于高斯分布。因此可用Wald时间序列检测方法对VF信号和VT信号分类。这个算法可用于计算机进行实时处理和分析,同时此法与取样率无关,适用于各种取样系统,是一个较理想的方法。
Ventricular fibrillation signals must be recognized accurately and in time, and the patient dies quickly if defibrillation is not defibrillated. On the other hand, if the ventricular fibrillation signal does not occur, and the miscarriage of ventricular fibrillation signal, given the electric shock, the patient’s heart suffered undue damage, which also belongs to a serious medical accident. Therefore, fast and accurate identification is very important. Since the 1970s, many scientists in the world have been exploring ways to use computers to automatically identify ventricular fibrillation signals, but they are not suitable for automatic defibrillators because they fail to meet the requirements of real-time discrimination or the accuracy is not high enough Test design. This article describes a high accuracy and simple method of rapid identification. This method takes a second ECG signal to autocorrelate a finite length discrete signal, then zero-cuts the autocorrelation function so that the autocorrelation function becomes a series of binary bursts followed by a burst of one second signals Number as a feature parameter, design classifier. The characteristic parameters of ventricular fibrillation signals and ventricular tachycardia (VT) signals have been proved to belong to the Gaussian distribution. Therefore, the Wald time series detection method can be used to classify the VF signal and the VT signal. This algorithm can be used for real-time computer processing and analysis, at the same time this method has nothing to do with the sampling rate, suitable for a variety of sampling systems, is an ideal method.