Understanding sleep graphs

Raw data from the sensors are aggregated into larger time frames and then used to plot the sleep graph and compute statistics.

Sleep graph screen

The graph screen shows up to three graphs: actigraph, hypnogram and noise graph. It also gives some numbers about your night, along with an option to rate and tag the record.

The sleep graph screen

Actigraph

Actigraph is a visualization of your nightly movements. The higher the peak, the more you’ve been moving.

Hypnogram

The hypnogram shows your sleep phases progress during the night.
  • Awake is shown in light green – the highest column
  • REM phase and light sleep are shown in medium green
  • Deep sleep is shown in dark green

Noise graph

The grey noise graph shows how much noise (sleep talk, snoring, environmental) was there throughout the night

Further data on sleep graph (colored lines)

screen11-36-44_framed
  • Red line = heart rate through the night. Red dots with numbers inside are the maximum and minimum heart rate.
  • Blue line = breath rate if you are using sonar, blood oxygen level if you are using oximeter. Blue dots with numbers indicate maximum and minimum.

A healthy sleep (if you are a monophasic sleeper) is 7-8 hours long and consists of 5 sleep cycles where the first lasts for 70-100 minutes and the consequent cycles get longer but lighter. Each cycle consists of 5 stages lasting usually 5-15 minutes. Stage 1 and 2 are considered light sleep and this is the best time to be woken up in the morning.
So a healthy sleep cycle looks like a 10-30 minutes of light sleep (high peaks) followed by an area of deep sleep (low peaks or no peaks) lasting 40-100 minutes.
Different resources on sleep may provide different figures though.

So deep sleep % may actually range between 30%-70%. Figures out of this range may indicate either incorrect sleep tracking setup (see Setup sleep tracking) or some sleep issues. For example very low deep sleep % may indicate either sleep deprivation or issues in your life style such as higher alcohol or caffeine intake, not enough sport etc. See an example of such sleep graphs in the figure below.

graphtags

Graph with markers (icons)

Beside deep sleep marked with a green dashed line and light sleep marked in blue, there are several other events depicted in the sleep graphs. 

graphtags
Smart wake up period is depicted by a red dashed line. More in Smart wake up
  •   snoring events, as described in Snoring detection
  •   periods when sleep tracking has been paused, as described in Sleep tracking
  •   noise recordings, as described in Noise recording
  •   alarms and snoozed within the sleep graph
  •  surise and sunset times

For more details on the tracked sleep measured, please consult Statistics.

Sleep advice

With the modern hectic lifestyle it is more and more difficult to get enough deep sleep. There is stress, noise from the street and many more factors which lower your deep sleep %. From that perspective we can see the aim of maximizing deep sleep % as an interesting goal in improving your sleep. We have implemented a simple polynomial regression analysis of your deep sleep % in relation to sleep length and fall asleep hours to advice you on better sleep habits to maximize deep sleep percentage. This analysis is available when opening Charts as you can see on the images below. In this example highest deep sleep percentages are achieved with fall asleep hour around 2:43 and sleep length 9:26.

Of course such advice needs to be taken only as a slight guidance in which direction you may adjust your sleep habits. But we don’t recommend to do any dramatic changes. Rather gradual iterative adjustments with feedback from the sleep tracking are recommended. Also the performed analysis always needs some correction and interpretation from the user.

screen15-07-19_framed

More on sleep data analysis in Statistics and Advice.

Snoring detection

Over a long period of time we have been gathering snoring samples in order to use machine learning algorithms and to teach Sleep as Android to detect snoring. Currently our algorithm is already performing very well. It is based on a training set of 600 snoring recordings and we are constantly gathering new and adding to the set in order to improve snoring detection accuracy. For more on snoring please refer to Snoring detection.

Heart rate detection

If you are using a smartwatch with HR sensor or a dedicated HR strap, you can use those to gather heart rate data. HR data make the whole sleep tracking much more accurate, especially distinguishing between sleeping and being awake, which actigraphy alone does not do well.

More on heart rate detection