Wearable accelerometer based extended sleep position recognition

Sarah Fallmann, Rick Van Veen, Liming Chen, David Walker, Feng Chen, Chengsheng Pan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Sleep positions have an impact on sleep quality and therefore need to be further analyzed. Current research on position tracking includes only the four basic positions. In the context of wearable devices, energy efficiency is still an open issue. This research presents a way to detect eight positions with higher granularity under energy efficient constraints. Generalized Matrix Learning Vector Quantization is used, as it is a fast and appropriate method for environments with limited computation resources, and has not been seen for this kind of application before. The overall model trained on individuals performs with an averaged accuracy of 99.8%, in contrast to an averaged accuracy of 83.62% for grouped datasets. Real world application gives an accuracy of around 98%. The results show that energy efficiency will be feasible, as performance stays similar for lower sampling rate. This is a step towards a mobile solution which gives more insight in person's sleep behaviour.
Original languageEnglish
Title of host publication2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom)
Place of PublicationDalian, China
PublisherIEEE Xplore
Pages1-6
Number of pages6
ISBN (Electronic)978-1-5090-6704-6
ISBN (Print)978-1-5090-6705-3
DOIs
Publication statusPublished - 17 Oct 2017
Event2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom) - Dalian
Duration: 12 Oct 201715 Oct 2017

Conference

Conference2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom)
Period12/10/1715/10/17

Keywords

  • sleep apnea
  • sensors
  • legged locomotion
  • accelerometers
  • biomedical monitoring
  • monitoring
  • imaging

Fingerprint Dive into the research topics of 'Wearable accelerometer based extended sleep position recognition'. Together they form a unique fingerprint.

Cite this