I developed an end-to-end sleep staging smartphone application that uses Deep Learning model trained on the OpenSleepEDF dataset to infer on the EEG from Muse: A wearable BCI. I also programmed power-spectral analysis to gain insights on the EEG power bands namely: Alpha, Beta, Gamma, Delta and Theta during different sleep stages. I built the data pipelines of EEG and IMU along with a raw EEG visualizer with Muse sensors. With this model application, I designed a connector module that can integrate this project with the BioEssence Project developed by my mentor Judith Amores, towards a sleep-olfactory interface aimed at automatic real-time intervention of scent during sleep. Further, we presented a statistically-proven independent and intuitive measure from the power spectral densities of EEG to classify deep sleep.