Activity Recognition for Diabetic Patients Using a Smartphone. / Kvetkovic, Bozidara; Janko, Vito; Romero Lopez, Alfonso; Kafali, Remzi; Stathis, Konstantinos; Lustrek, Mitja.

In: Journal of Medical Systems, Vol. 40, 256, 12.2016, p. 1-8.

Research output: Contribution to journalArticlepeer-review

Published

Standard

Activity Recognition for Diabetic Patients Using a Smartphone. / Kvetkovic, Bozidara; Janko, Vito; Romero Lopez, Alfonso; Kafali, Remzi; Stathis, Konstantinos; Lustrek, Mitja.

In: Journal of Medical Systems, Vol. 40, 256, 12.2016, p. 1-8.

Research output: Contribution to journalArticlepeer-review

Harvard

Kvetkovic, B, Janko, V, Romero Lopez, A, Kafali, R, Stathis, K & Lustrek, M 2016, 'Activity Recognition for Diabetic Patients Using a Smartphone', Journal of Medical Systems, vol. 40, 256, pp. 1-8. https://doi.org/10.1007/s10916-016-0598-y

APA

Vancouver

Author

Kvetkovic, Bozidara ; Janko, Vito ; Romero Lopez, Alfonso ; Kafali, Remzi ; Stathis, Konstantinos ; Lustrek, Mitja. / Activity Recognition for Diabetic Patients Using a Smartphone. In: Journal of Medical Systems. 2016 ; Vol. 40. pp. 1-8.

BibTeX

@article{59dcbac666b4466dbf57e7ed155cd97f,
title = "Activity Recognition for Diabetic Patients Using a Smartphone",
abstract = "Diabetes is a disease that has to be managed through appropriate lifestyle. Technology can help with this, particularly when it is designed so that it does not impose an additional burden on the patient. This paper presents an approach that combines machine-learning and symbolic reasoning to recognise high-level lifestyle activities using sensor data obtained primarily from the patient{\textquoteright}s smartphone. We compare five methods for machine-learning which differ in the amount of manually labelled data by the user, to investigate the trade-off between the labelling effort and recognition accuracy. In an evaluation on real-life data, the highest accuracy of 83.4 % was achieved by the MCAT method, which is capable of gradually adapting to each user. ",
author = "Bozidara Kvetkovic and Vito Janko and {Romero Lopez}, Alfonso and Remzi Kafali and Konstantinos Stathis and Mitja Lustrek",
year = "2016",
month = dec,
doi = "10.1007/s10916-016-0598-y",
language = "English",
volume = "40",
pages = "1--8",
journal = "Journal of Medical Systems",
issn = "1573-689X",
publisher = "Springer",

}

RIS

TY - JOUR

T1 - Activity Recognition for Diabetic Patients Using a Smartphone

AU - Kvetkovic, Bozidara

AU - Janko, Vito

AU - Romero Lopez, Alfonso

AU - Kafali, Remzi

AU - Stathis, Konstantinos

AU - Lustrek, Mitja

PY - 2016/12

Y1 - 2016/12

N2 - Diabetes is a disease that has to be managed through appropriate lifestyle. Technology can help with this, particularly when it is designed so that it does not impose an additional burden on the patient. This paper presents an approach that combines machine-learning and symbolic reasoning to recognise high-level lifestyle activities using sensor data obtained primarily from the patient’s smartphone. We compare five methods for machine-learning which differ in the amount of manually labelled data by the user, to investigate the trade-off between the labelling effort and recognition accuracy. In an evaluation on real-life data, the highest accuracy of 83.4 % was achieved by the MCAT method, which is capable of gradually adapting to each user.

AB - Diabetes is a disease that has to be managed through appropriate lifestyle. Technology can help with this, particularly when it is designed so that it does not impose an additional burden on the patient. This paper presents an approach that combines machine-learning and symbolic reasoning to recognise high-level lifestyle activities using sensor data obtained primarily from the patient’s smartphone. We compare five methods for machine-learning which differ in the amount of manually labelled data by the user, to investigate the trade-off between the labelling effort and recognition accuracy. In an evaluation on real-life data, the highest accuracy of 83.4 % was achieved by the MCAT method, which is capable of gradually adapting to each user.

U2 - 10.1007/s10916-016-0598-y

DO - 10.1007/s10916-016-0598-y

M3 - Article

VL - 40

SP - 1

EP - 8

JO - Journal of Medical Systems

JF - Journal of Medical Systems

SN - 1573-689X

M1 - 256

ER -