InTheMoodForLife: Analyzing Sleep to Better Manage Mood Disorders

on YouTube ↗19m

" summary

An app that decodes a consumer sleep tracker over Bluetooth, streams 140 samples/sec into a Raspberry Pi running Raspberry Pi + Eclipse Vert.x + Warp 10, and runs Warpscript analytics to decompose sleep and flag REM fragmentation markers. Prototype processes one person (the uploader's son), compares 30-day windows and reports a drop starting ~10 days before mixed manic/depressive episodes. Won the Eclipse Open IoT Challenge; still needs larger clinical data and a medical-grade device.

AI-written summary · about

" chapters (10)

1. 0:00Start
2. 0:054 years ago in Brittany
3. 5:06USER EXPERIENCE...
4. 5:48Consumer sleep trackers
5. 6:31HARDWARE
6. 9:48Analyze strategy
7. 12:29Filtering & standardization
8. 12:48DATA VALUE STREAM iot
9. 12:59Mood monitoring
10. 18:12Privacy by design - end to end encryption

" related talks

• 01h 13mHealth Monitoring with Wireless Sensors and Machine LearningBruce M. Maggs · Algorithmic Foundations for Emerging Computing Technologies Boot Camp 2025
• 47mReactive Brain WavesUri Shaked · DevFest Nantes 2017
• 49mWearables Gone WildSonny Vu, Kamil Adamczyk, Amol Sarva, Yonatan Wexler, Arik Hesseldahl · DLD 2014
• 46mControlling apps with your mindVladimir Novick · Agent Conf 2020
• 06mBodyCompass: Monitoring Sleep Posture with Wireless SignalsHao Wang, Dina Katabi, Shichao Yue, Yuzhe Yang, Hariharan Rahul · UbiComp / ISWC 2020
• 22mUsing data to improve physical therapy for people with neurological diseasesGernot Greimler · DSC DACH 2023
• 02mHighlights - Wearables Gone WildSonny Vu, Kamil Adamczyk, A.Sarva, Y.Wexler, A.Hesseldahl · DLD 2014
• 34mA machine learning hub for IoT data using Apache MadlibNitin Borwankar · ApacheCon@Home 2021