In the field of sleep medicine, identifying sleep-wake stages is crucial for evaluate of sleep quality. Until now, numerous methods have been proposed for sleep-wake classification. These methods predominantly utilize electroencephalogram (EEG) signals, achieving competitive performance in sleep-wake stage classification. However, acquiring EEG signals is both cumbersome and inconvenient. At the same time, EEG signals are very weak and are easily disturbed. In contrast EEG signal, collecting electrocardiogram (ECG) signals is relatively simple and convenient. Therefore, based on the ECG signals, we propose a simple and effective sleep-wake stages model that can be used for wearable devices. In order to extract multi-scale features of ECG signals, convolutional kernels of different sizes are designed. Then, a novel dynamic connection convolutional neural network (DCCNN) is proposed to classify sleep-wake stages. First, the DCCNN calculates the goodness of feature maps from each layer. Second, according to the goodness of different layers, select the optimal layer to form a residual module with the current layer. The proposed method was tested on sleep data from a publicly accessible databases, namely the MIT-BIH Polysomnographic Database, resulting in an best accuracy of 92.21%. The findings are similar and higher performance to those models trained with EEG signals. Moreover, when compared to state-of-the-art methods, the proposed approach's effectiveness is further demonstrated. In conclusion, this research offers a novel approach for sleep monitoring.