Sleep Monitoring Data Validation using a Linear Discriminant Classifier

Jose Perez-Macias Martin; Michael Pavel; Ilkka Korhonen; Holly Jimison

Sleep Monitoring Data Validation using a Linear Discriminant Classifier

Jose Perez-Macias Martin, Michael Pavel, Ilkka Korhonen, Holly Jimison

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

Sleep quality has an important impact in
overall health. There are several new commercially
available devices for sleep tracking. Although they have
been tested in sleep laboratories, for some users,
estimates are reliable whereas for others are very
different. In this paper we present a framework to
predict the error range of the total sleep time. We
studied 23 subjects’ sleep patterns using Fitbit One and
Beddit Pro devices. We used Beddit Pro as our
reference devices to verify Fitbit’s reliability. Previous
analyses found that for some users the agreement
between systems was high, whereas for others was low.
We used a linear discriminant to predict this behavior
in in the Fitbit data. 72.7% accuracy was achieved. Our
results suggest that reliability of sleep estimates could
be estimated without the use of a second device.

Original language	English
Title of host publication	7th annual Canadian Student Conference on Biomedical Computing and Engineering and IEEE EMBS International Student Conference (ISC)
Number of pages	2
Publication status	Published - 25 Jun 2014
Publication type	A4 Article in conference proceedings
Event	IEEE EMBS International Student Conference (ISC'14 Oshawa) - University of Ontario Institute of Technology (UOIT.ca), Oshawa, Canada Duration: 24 Jun 2014 → 26 Jun 2014 http://sites.ieee.org/cscbce/

Conference

Conference	IEEE EMBS International Student Conference (ISC'14 Oshawa)
Abbreviated title	CSCBCE / ISC
Country/Territory	Canada
City	Oshawa
Period	24/06/14 → 26/06/14
Internet address	http://sites.ieee.org/cscbce/

Cite this

@inproceedings{f0aaef25dea14989a27e5fdb910cf230,

title = "Sleep Monitoring Data Validation using a Linear Discriminant Classifier",

abstract = "Sleep quality has an important impact inoverall health. There are several new commerciallyavailable devices for sleep tracking. Although they havebeen tested in sleep laboratories, for some users,estimates are reliable whereas for others are verydifferent. In this paper we present a framework topredict the error range of the total sleep time. Westudied 23 subjects{\textquoteright} sleep patterns using Fitbit One andBeddit Pro devices. We used Beddit Pro as ourreference devices to verify Fitbit{\textquoteright}s reliability. Previousanalyses found that for some users the agreementbetween systems was high, whereas for others was low.We used a linear discriminant to predict this behaviorin in the Fitbit data. 72.7\% accuracy was achieved. Ourresults suggest that reliability of sleep estimates couldbe estimated without the use of a second device.",

author = "\{Perez-Macias Martin\}, Jose and Michael Pavel and Ilkka Korhonen and Holly Jimison",

year = "2014",

month = jun,

day = "25",

language = "English",

booktitle = "7th annual Canadian Student Conference on Biomedical Computing and Engineering and IEEE EMBS International Student Conference (ISC)",

note = "IEEE EMBS International Student Conference (ISC'14 Oshawa), CSCBCE / ISC ; Conference date: 24-06-2014 Through 26-06-2014",

url = "http://sites.ieee.org/cscbce/",

}

Sleep Monitoring Data Validation using a Linear Discriminant Classifier. / Perez-Macias Martin, Jose; Pavel, Michael; Korhonen, Ilkka et al.
7th annual Canadian Student Conference on Biomedical Computing and Engineering and IEEE EMBS International Student Conference (ISC). 2014.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Sleep Monitoring Data Validation using a Linear Discriminant Classifier

AU - Perez-Macias Martin, Jose

AU - Pavel, Michael

AU - Korhonen, Ilkka

AU - Jimison, Holly

PY - 2014/6/25

Y1 - 2014/6/25

N2 - Sleep quality has an important impact inoverall health. There are several new commerciallyavailable devices for sleep tracking. Although they havebeen tested in sleep laboratories, for some users,estimates are reliable whereas for others are verydifferent. In this paper we present a framework topredict the error range of the total sleep time. Westudied 23 subjects’ sleep patterns using Fitbit One andBeddit Pro devices. We used Beddit Pro as ourreference devices to verify Fitbit’s reliability. Previousanalyses found that for some users the agreementbetween systems was high, whereas for others was low.We used a linear discriminant to predict this behaviorin in the Fitbit data. 72.7% accuracy was achieved. Ourresults suggest that reliability of sleep estimates couldbe estimated without the use of a second device.

AB - Sleep quality has an important impact inoverall health. There are several new commerciallyavailable devices for sleep tracking. Although they havebeen tested in sleep laboratories, for some users,estimates are reliable whereas for others are verydifferent. In this paper we present a framework topredict the error range of the total sleep time. Westudied 23 subjects’ sleep patterns using Fitbit One andBeddit Pro devices. We used Beddit Pro as ourreference devices to verify Fitbit’s reliability. Previousanalyses found that for some users the agreementbetween systems was high, whereas for others was low.We used a linear discriminant to predict this behaviorin in the Fitbit data. 72.7% accuracy was achieved. Ourresults suggest that reliability of sleep estimates couldbe estimated without the use of a second device.

UR - http://sites.ieee.org/cscbce/files/2014/06/cscbceisc2014_submission_3.pdf

M3 - Conference contribution

BT - 7th annual Canadian Student Conference on Biomedical Computing and Engineering and IEEE EMBS International Student Conference (ISC)

T2 - IEEE EMBS International Student Conference (ISC'14 Oshawa)

Y2 - 24 June 2014 through 26 June 2014

ER -

Sleep Monitoring Data Validation using a Linear Discriminant Classifier

Abstract

Conference

Other files and links

Fingerprint

Cite this