Sleep staging method and system based on single-channel electroencephalogram signal multi-scale residual network

The invention discloses a sleep staging method and system based on a single-channel electroencephalogram signal multi-scale residual network. The method comprises the steps of S1, collecting original single-channel electroencephalogram signals to serve as input signals; S2, constructing a multi-scale residual sleep automatic staging network, inputting the input signals into the multi-scale residual sleep automatic staging network for training, and outputting a sleep staging result; and S3, evaluating the output result. According to the sleep staging method based on the single-channel electroencephalogram signal multi-scale residual network, disclosed by the invention, the features are automatically extracted from the original single-channel electroencephalogram signals by adopting convolution kernels of multiple scales, and the robustness of a model and the representation capability of the signal features can be improved even under the non-stationary condition. In addition, the network can effectively learn t