SVM based dynamic classifier for sleep disorder monitoring wearable device

Jaihyun Park, Daehun Kim, Cheoljong Yang, Hanseok Ko

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

1 Citation (Scopus)

Abstract

An accelerometer embedded wrist-worn device is widely used for sleep assessment. However, conventional methods determine a state of user to «sleep» or «wakefulness» according to whether the accelerometer value of individual epoch exceeds a certain threshold or not. As a result, high miss-classification rate is observed due to user's small intermittent movements while sleeping and short term movements while awake. In this paper, a novel approach is proposed that mitigates such problems by employing a dynamic classifier which analyzes similarity between the neighboring data scores obtained from support vector machine classifier. Performance of the proposed method is evaluated using 50 real data sets and its superiority is verified.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Consumer Electronics, ICCE 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages309-310
Number of pages2
ISBN (Print)9781467383646
DOIs
Publication statusPublished - 2016 Mar 10
EventIEEE International Conference on Consumer Electronics, ICCE 2016 - Las Vegas, United States
Duration: 2016 Jan 72016 Jan 11

Other

OtherIEEE International Conference on Consumer Electronics, ICCE 2016
CountryUnited States
CityLas Vegas
Period16/1/716/1/11

Fingerprint

Accelerometers
Classifiers
Monitoring
Support vector machines
Sleep

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Park, J., Kim, D., Yang, C., & Ko, H. (2016). SVM based dynamic classifier for sleep disorder monitoring wearable device. In 2016 IEEE International Conference on Consumer Electronics, ICCE 2016 (pp. 309-310). [7430624] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE.2016.7430624

SVM based dynamic classifier for sleep disorder monitoring wearable device. / Park, Jaihyun; Kim, Daehun; Yang, Cheoljong; Ko, Hanseok.

2016 IEEE International Conference on Consumer Electronics, ICCE 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 309-310 7430624.

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

Park, J, Kim, D, Yang, C & Ko, H 2016, SVM based dynamic classifier for sleep disorder monitoring wearable device. in 2016 IEEE International Conference on Consumer Electronics, ICCE 2016., 7430624, Institute of Electrical and Electronics Engineers Inc., pp. 309-310, IEEE International Conference on Consumer Electronics, ICCE 2016, Las Vegas, United States, 16/1/7. https://doi.org/10.1109/ICCE.2016.7430624
Park J, Kim D, Yang C, Ko H. SVM based dynamic classifier for sleep disorder monitoring wearable device. In 2016 IEEE International Conference on Consumer Electronics, ICCE 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 309-310. 7430624 https://doi.org/10.1109/ICCE.2016.7430624
Park, Jaihyun ; Kim, Daehun ; Yang, Cheoljong ; Ko, Hanseok. / SVM based dynamic classifier for sleep disorder monitoring wearable device. 2016 IEEE International Conference on Consumer Electronics, ICCE 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 309-310
@inproceedings{0dd03c1752ff4aa0b415b03cabf97b33,
title = "SVM based dynamic classifier for sleep disorder monitoring wearable device",
abstract = "An accelerometer embedded wrist-worn device is widely used for sleep assessment. However, conventional methods determine a state of user to «sleep» or «wakefulness» according to whether the accelerometer value of individual epoch exceeds a certain threshold or not. As a result, high miss-classification rate is observed due to user's small intermittent movements while sleeping and short term movements while awake. In this paper, a novel approach is proposed that mitigates such problems by employing a dynamic classifier which analyzes similarity between the neighboring data scores obtained from support vector machine classifier. Performance of the proposed method is evaluated using 50 real data sets and its superiority is verified.",
author = "Jaihyun Park and Daehun Kim and Cheoljong Yang and Hanseok Ko",
year = "2016",
month = "3",
day = "10",
doi = "10.1109/ICCE.2016.7430624",
language = "English",
isbn = "9781467383646",
pages = "309--310",
booktitle = "2016 IEEE International Conference on Consumer Electronics, ICCE 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - SVM based dynamic classifier for sleep disorder monitoring wearable device

AU - Park, Jaihyun

AU - Kim, Daehun

AU - Yang, Cheoljong

AU - Ko, Hanseok

PY - 2016/3/10

Y1 - 2016/3/10

N2 - An accelerometer embedded wrist-worn device is widely used for sleep assessment. However, conventional methods determine a state of user to «sleep» or «wakefulness» according to whether the accelerometer value of individual epoch exceeds a certain threshold or not. As a result, high miss-classification rate is observed due to user's small intermittent movements while sleeping and short term movements while awake. In this paper, a novel approach is proposed that mitigates such problems by employing a dynamic classifier which analyzes similarity between the neighboring data scores obtained from support vector machine classifier. Performance of the proposed method is evaluated using 50 real data sets and its superiority is verified.

AB - An accelerometer embedded wrist-worn device is widely used for sleep assessment. However, conventional methods determine a state of user to «sleep» or «wakefulness» according to whether the accelerometer value of individual epoch exceeds a certain threshold or not. As a result, high miss-classification rate is observed due to user's small intermittent movements while sleeping and short term movements while awake. In this paper, a novel approach is proposed that mitigates such problems by employing a dynamic classifier which analyzes similarity between the neighboring data scores obtained from support vector machine classifier. Performance of the proposed method is evaluated using 50 real data sets and its superiority is verified.

UR - http://www.scopus.com/inward/record.url?scp=84965168933&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84965168933&partnerID=8YFLogxK

U2 - 10.1109/ICCE.2016.7430624

DO - 10.1109/ICCE.2016.7430624

M3 - Conference contribution

SN - 9781467383646

SP - 309

EP - 310

BT - 2016 IEEE International Conference on Consumer Electronics, ICCE 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -