 Sleep specialists often manually score patients' neurophysiological signals collected from sleep labs. This process is time-consuming, tedious, and difficult. As a result, there has been increased demand for automatic sleep stage classification, ASSE, systems. Sleep stage classification refers to identifying the different stages of sleep, which is important for diagnosing and treating related sleep disorders. To address these issues, this paper surveys the progress and challenges in existing electroencephalogram, e.g., based methods for sleep stage identification. These methods typically use multiple EEG channels, and are based on either 32nd or 22nd epochs, which limits their applicability for real-time applications. Additionally, the Physionet Sleep European Data Format, EDF, database was used. The proposed methodology achieved an average classification sensitivity, specificity, and accuracy of 89.06%, 98.61%, and 93.13%, respectively, when a decision tree classifier was employed. Furthermore, the proposed method was compared to other recent studies, which confirmed its high classification accuracy. This article was authored by Caldali Iyabualayn, Mayad Faisapur, Wafa Esalmehamedi, and others. We are article.tv, links in the description below.