Tampere University of Technology

TUTCRIS Research Portal

Data Correction for Seven Activity Trackers based on Regression Models

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Standard

Data Correction for Seven Activity Trackers based on Regression Models. / Andalibi, Vafa; Honko, Harri ; Christophe, Francois ; Viik, Jari .

Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2015. p. 1592 - 1595.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Andalibi, V, Honko, H, Christophe, F & Viik, J 2015, Data Correction for Seven Activity Trackers based on Regression Models. in Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. pp. 1592 - 1595, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 1/01/00.

APA

Andalibi, V., Honko, H., Christophe, F., & Viik, J. (2015). Data Correction for Seven Activity Trackers based on Regression Models. In Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 1592 - 1595)

Vancouver

Andalibi V, Honko H, Christophe F, Viik J. Data Correction for Seven Activity Trackers based on Regression Models. In Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2015. p. 1592 - 1595

Author

Andalibi, Vafa ; Honko, Harri ; Christophe, Francois ; Viik, Jari . / Data Correction for Seven Activity Trackers based on Regression Models. Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2015. pp. 1592 - 1595

Bibtex - Download

@inproceedings{28930128dc194bcbbacbb71453693043,
title = "Data Correction for Seven Activity Trackers based on Regression Models",
abstract = "Using an activity tracker for measuring activity-related parameters, e.g. steps and energy expenditure (EE), can be very helpful in assisting a person’s fitness improvement. Unlike the measuring of number of steps, an accurate EE estimation requires additional personal information as well as accurate velocity of movement which is hard to achieve due to inaccuracy of sensors. In this paper, we have evaluated regression-based models to improve the precision for both steps and EE estimation. For this purpose, data of seven activity trackers and two reference devices was collected from 20 young adult volunteers wearing all devices at once in three different tests, namely 60-minute office work, 6-hour overall activity and 60-minute walking. Reference data is used to create regression models for each device and relative percentage errors of adjusted values are then statistically compared to that of original values. The effectiveness of regression models are determined based on the result of a statistical test. During a walking period, EE measurement was improved in all devices. The step measurement was also improved in five of them. The results show that improvement of EE estimation is possible only with low-cost implementation of fitting model over the collected data e.g. in the app or in corresponding service back-end.",
author = "Vafa Andalibi and Harri Honko and Francois Christophe and Jari Viik",
note = "ORG=tie,0.3 ORG=sgn,0.35 ORG=elt,0.35",
year = "2015",
language = "English",
isbn = "978-1-4244-9270-1",
pages = "1592 -- 1595",
booktitle = "Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - Data Correction for Seven Activity Trackers based on Regression Models

AU - Andalibi, Vafa

AU - Honko, Harri

AU - Christophe, Francois

AU - Viik, Jari

N1 - ORG=tie,0.3 ORG=sgn,0.35 ORG=elt,0.35

PY - 2015

Y1 - 2015

N2 - Using an activity tracker for measuring activity-related parameters, e.g. steps and energy expenditure (EE), can be very helpful in assisting a person’s fitness improvement. Unlike the measuring of number of steps, an accurate EE estimation requires additional personal information as well as accurate velocity of movement which is hard to achieve due to inaccuracy of sensors. In this paper, we have evaluated regression-based models to improve the precision for both steps and EE estimation. For this purpose, data of seven activity trackers and two reference devices was collected from 20 young adult volunteers wearing all devices at once in three different tests, namely 60-minute office work, 6-hour overall activity and 60-minute walking. Reference data is used to create regression models for each device and relative percentage errors of adjusted values are then statistically compared to that of original values. The effectiveness of regression models are determined based on the result of a statistical test. During a walking period, EE measurement was improved in all devices. The step measurement was also improved in five of them. The results show that improvement of EE estimation is possible only with low-cost implementation of fitting model over the collected data e.g. in the app or in corresponding service back-end.

AB - Using an activity tracker for measuring activity-related parameters, e.g. steps and energy expenditure (EE), can be very helpful in assisting a person’s fitness improvement. Unlike the measuring of number of steps, an accurate EE estimation requires additional personal information as well as accurate velocity of movement which is hard to achieve due to inaccuracy of sensors. In this paper, we have evaluated regression-based models to improve the precision for both steps and EE estimation. For this purpose, data of seven activity trackers and two reference devices was collected from 20 young adult volunteers wearing all devices at once in three different tests, namely 60-minute office work, 6-hour overall activity and 60-minute walking. Reference data is used to create regression models for each device and relative percentage errors of adjusted values are then statistically compared to that of original values. The effectiveness of regression models are determined based on the result of a statistical test. During a walking period, EE measurement was improved in all devices. The step measurement was also improved in five of them. The results show that improvement of EE estimation is possible only with low-cost implementation of fitting model over the collected data e.g. in the app or in corresponding service back-end.

M3 - Conference contribution

SN - 978-1-4244-9270-1

SP - 1592

EP - 1595

BT - Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

ER -