We developed a machine learning methodology for automatic sleep stage scoring. Our time-frequency analysis-based feature extraction is fine-tuned to capture sleep stage-specific signal features as described in the American Academy of Sleep Medicine manual that the human experts follow. We used ensemble learning with an ensemble of stacked sparse autoencoders for classifying the sleep stages. We used class-balanced random sampling across sleep stages for each model in the ensemble to avoid skewed performance in favor of the most represented sleep stages, and addressed the problem of misclassification errors due to class imbalance while significantly improving worst-stage classification. We used an openly available dataset from 20 healthy young adults for evaluation. We used a single channel of EEG from this dataset, which makes our method a suitable candidate for longitudinal monitoring using wearable EEG in real-world settings. Our method has both high overall accuracy (78%, range 75–80%), and high mean \(F_1\)-score (84%, range 82–86%) and mean accuracy across individual sleep stages (86%, range 84–88%) over all subjects. The performance of our method appears to be uncorrelated with the sleep efficiency and percentage of transitional epochs in each recording.