Your Personal Sleep Coach: A 10-Year Brown University Research Study on Sleep

Download for Android Download for iPhone
example sleep sensing example sleep sensing example sleep sensing

Can you optimize your sleep?

SleepCoacher is an automated system to help you achieve that by monitoring your sleep behaviors, guiding you towards better sleep quality through self-experiments that happen while you sleep. It's based on research conducted by Brown University.

Some people need more sleep than others, some are night owls while others are early birds, and some are more sensitive to noise. To know how to sleep better, you need to know more about yourself.

SleepCoacher was designed to be your own personal sleep coach: it shows you a list of sleep expert-approved suggestions that you can incorporate into your life and see if they help you sleep better.

When you put your phone on the bed, the app monitors movement and noise while you sleep. When you wake up, it sends your sleep data to a system that reviews your sleep history, and learns how your behavior and sleep quality are related.

Since everyone responds to changes differently, SleepCoacher observes the outcomes of behavioral changes, and tells you what works best for you specifically. After a few nights of tracking your sleep and following the instructions of what to do, SleepCoacher lets you know which condition is more likely to help you sleep better (e.g. there is an 83% likelihood that wearing roomier PJs is helping you fall asleep faster).

The 10-Year Study on Sleep

To learn what behaviors affect your sleep quality, a week is not enough. Even a month can only tell you one or two things about your habits.

SleepCoacher will run for 10 years, so you as a user can optimize your sleep behaviors over a long series of mini-experiments. Start and stop each self-experiment whenever you please. SleepCoacher cycle

Articles and Videos

pdf icon

SleepBandits: Guided Flexible Self-Experiments for Sleep
Daskalova, N., Yoon, J., Wang, L., Beltran, G., Araujo, C., Nugent, N., McGeary, J., Williams, J., & Huang, J. SleepBandits: Guided Flexible Self-Experiments for Sleep. CHI 2020.

Video below summarizes our paper and its findings, but the paper contains a lot more interesting details.

pdf icon

SleepCoacher: A Personalized Automated Self-Experimentation System for Sleep Recommendations   [Video]
Daskalova, N., Metaxa-Kakavouli, D., Tran, A., Nugent, N., Boergers, J., McGeary, J., & Huang, J. (2016, October). SleepCoacher: A Personalized Automated Self-Experimentation System for Sleep Recommendations. In Proceedings of the 29th Annual Symposium on User Interface Software and Technology (pp. 347-358). ACM.

pillow icon

Smart Pillow Talks to Users, Improves Sleep (2018), Brown Daily Herald.

pillow icon

HeyPillow: Computationally Guided Sleep Behavior Study through Sensing (Video)
Nediyana Daskalova, Jiaju Ma, Tiffany Chen, Valerie Nguon, Jing Qian, Chonghui Chen, Jeff Huang. 2019.

Source Code and Documentation

The source code for the system from the SleepCoacher 2016 paper at UIST is available, along with documentation about how to set it up. The software for the apps and new statistical engine will be released upon publication of the upcoming paper.

Source Code on Github

Development Team

Cintia Araujo

Guillermo Beltran

Nediyana Daskalova

Niharika Jhingan

Lisa Wang

Jina Yoon

This research is in collaboration with clinicians and researchers at Rhode Island Hospital and the Providence VA Medical Center
Funded by the Brown University Seed Award, National Science Foundation IIS-1656763, and Brown University Data Science Institute