Signal classification method and device

The invention provides a signal classification method and device, and the method comprises the steps: carrying out the wavelet transformation of a to-be-classified signal after the to-be-classified signal is obtained, and generating input data according to the original data of the to-be-classified signal and a wavelet transformation result. And inputting the input data into the neural network model, and calculating an output classification probability through the neural network model. Wherein the input data comprises original data of the to-be-classified signals, transformation data obtained after wavelet transformation of the to-be-classified signals and composite data formed by stacking the original data and the transformation data, the time sequence relation in the to-be-classified signals can be reserved, and the characteristics of the data input into the neural network model are increased; therefore, the accuracy of signal classification is improved. 本申请提供一种信号分类方法及装置，所述方法在获取待分类信号后，对待分类信号执行小波变换，并根据待分类信号原始