Identifying the severity of sleep disorders such as the Obstructive Sleep Apnea (OSA) based on overnight polysomnography (PSG) recordings plays an important role in diagnosing and treating sleep disorder patients. This diagnosis traditionally has been done by experts manually through visual inspections, which can be tedious, time consuming, and is prone to subjective errors. Currently, there are many machine learning solutions used for analyzing and classifying PSG data. One of the proposed solutions is to use deep learning architectures such as Convolutional Neural Networks (CNNs) where the convolutional and pooling layers behave as feature extractors and some fully-connected (FCN) layers are used for making final predictions for the OSA severity. In this project, a CNN architecture with 1D convolutional layers and FCN layers for classification is presented. The PSG data for this project are from the Cleveland Children’s Sleep and Health Study database and classification results confirm the effectiveness of the proposed CNN method. The proposed model of 1D CNN achieves excellent classification results without manually pre-processsing PSG signals such as feature extraction and feature reduction.