Noise detection method and system based on artificial intelligence

The invention discloses a noise detection method and system based on artificial intelligence, and relates to the technical field of neural network models, and the method comprises the following steps: obtaining ECG signal data; preprocessing the ECG signal data to obtain tensor data; building a noise recognition model based on a deep residual network; performing data processing on the tensor data through the noise vibration recognition model to obtain a binary classification output result; and identifying noise signals in the ECG signal data according to the dichotomy output result. The method has the effect that the characteristic waveform of the ECG signal is not affected when the noise signal in the ECG signal is recognized. 本申请公开了一种基于人工智能的噪声检测方法及系统，其涉及神经网络模型技术领域，该方法包括如下步骤：获取ECG信号数据；对所述ECG信号数据进行预处理，得到张量数据；基于深度残差网络搭建噪声识别模型；通过所述噪声颤动识别模型对所述张量数据进行数据处理，得到二分类输出结果；根据所述二分类输出结果识别所述ECG信号数据中的噪声信号。本申请具有识别ECG信号中的噪声信号时不会影响ECG信号的特征波形的效果。