"Come Sleep! O Sleep, the certain knot of peace,
The baiting place of wit, the balm of woe, 
The poor man's wealth, the prisoner's release."    
        —Sir Philip Sidney

  #### t h e m o t i v a t i o n : Because lack of sleep leads to a multitude of negative conditions, it is important to research topic.

Sleep disorders include, but are not limited to hypersomnolence disorder, obstructive sleep apnea, hypopnea, central sleep apnea, sleep related hypoventilation, circadian rhythm sleep-wake disorders, non-rapid eye movement sleep arousal disorders, nightmare disorder, rapid eye movement sleep behavior disorder, and restless legs syndrome. Some of these disorders are commonly associated with time, for example, night terror disorder appears at Stage 4 Non-REM sleep while nightmare disorder appears at REM Stage 5.

To date, the most studied sleep disorder is Obstructive Sleep Apnea Hypopnea Syndrome (apnea) where the airway collapses during sleep. This leads to disturbances while sleeping. There are other conditions aside from apneas which also impact the quality of sleep. These conditions are known as sleep arousals. Some examples which can lead to these arousals are teeth grinding (bruxisms), vocalizations, partial airway obstructions, and snoring. The goal of the PhysioNet challenge is to identify non-apnea related arousals from data collected during polysomnographic sleep studies. Polysomnography consists of EMG (muscles), EOG (eyes), EEG (brain), and airflow in 20 minute nap session with sleep onset, REM onset, Maintenance of Wakefulness, and Sedentary test.

● Evaluate different machine learning techniques for classifying sleep stages on single-channel EEG
● Mixed Neural Network Approach for Temporal Sleep Stage Classification
● Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline
● A Machine Learning Approach to Classify Sleep Stages of Rats

The final model is for a course in Deep Learning, this model still requires fine tuning to improve the performance.