Develop a Deep Learning Framework of 1D-CNN to Practical Application of Sleep Assessment Method

Automated decision system useful to simplify the diagnosis of sleep disorder. The feature engineering from a raw of ECG recording using deep learning based 1DCNN scheme. This study using ECG recordings has focused on the automated detection of apnea events and nonapnea events. In this case, we use the ECG signal along with a convolutional neural network (CNN)-based deep-learning architecture for the automatic identification of apnea and nonapnea events. Four scenarios of 1DCNN architecture were trained using 50 epochs with a learning rate of 0.001 and using optimizer ADAM algorithm. The optimal model 1 showed a promising diagnostic performance in an independent test set, with classification accuracy, sensitivity, and specificity 88.0%, 93.3% and 82.7% respectively.