Personalized physical activity coaching: a machine learning approach

Onderzoeksoutput: ArticleAcademicpeer review

63 Downloads (Pure)

Uittreksel

Living a sedentary lifestyle is one of the major causes of numerous health problems. To encourage employees to lead a less sedentary life, the Hanze University started a health promotion program. One of the interventions in the program was the use of an activity tracker to record participants' daily step count. The daily step count served as input for a fortnightly coaching session. In this paper, we investigate the possibility of automating part of the coaching procedure on physical activity by providing personalized feedback throughout the day on a participant's progress in achieving a personal step goal. The gathered step count data was used to train eight different machine learning algorithms to make hourly estimations of the probability of achieving a personalized, daily steps threshold. In 80% of the individual cases, the Random Forest algorithm was the best performing algorithm (mean accuracy = 0.93, range = 0.88–0.99, and mean F1-score = 0.90, range = 0.87–0.94). To demonstrate the practical usefulness of these models, we developed a proof-of-concept Web application that provides personalized feedback about whether a participant is expected to reach his or her daily threshold. We argue that the use of machine learning could become an invaluable asset in the process of automated personalized coaching. The individualized algorithms allow for predicting physical activity during the day and provides the possibility to intervene in time.
Originele taal-2English
Aantal pagina's16
TijdschriftSensors
Volume18
Nummer van het tijdschrift2
StatusPublished - 19 feb 2018

Keywords

  • bewegen (activiteit)
  • coaching
  • gezondheid

Citeer dit

@article{ddec2ec48e064fdb9cafc078224da225,
title = "Personalized physical activity coaching: a machine learning approach",
abstract = "Living a sedentary lifestyle is one of the major causes of numerous health problems. To encourage employees to lead a less sedentary life, the Hanze University started a health promotion program. One of the interventions in the program was the use of an activity tracker to record participants' daily step count. The daily step count served as input for a fortnightly coaching session. In this paper, we investigate the possibility of automating part of the coaching procedure on physical activity by providing personalized feedback throughout the day on a participant's progress in achieving a personal step goal. The gathered step count data was used to train eight different machine learning algorithms to make hourly estimations of the probability of achieving a personalized, daily steps threshold. In 80{\%} of the individual cases, the Random Forest algorithm was the best performing algorithm (mean accuracy = 0.93, range = 0.88–0.99, and mean F1-score = 0.90, range = 0.87–0.94). To demonstrate the practical usefulness of these models, we developed a proof-of-concept Web application that provides personalized feedback about whether a participant is expected to reach his or her daily threshold. We argue that the use of machine learning could become an invaluable asset in the process of automated personalized coaching. The individualized algorithms allow for predicting physical activity during the day and provides the possibility to intervene in time.",
keywords = "bewegen (activiteit), coaching, gezondheid, physical activity, machine learning, coaching, sedentary lifestyle",
author = "Talko Dijkhuis and Frank Blaauw and {van Ittersum}, Miriam and Hugo Velthuijsen and Marco Aiello",
year = "2018",
month = "2",
day = "19",
language = "English",
volume = "18",
journal = "Sensors",
issn = "1424-8220",
publisher = "MDPI",
number = "2",

}

Personalized physical activity coaching: a machine learning approach. / Dijkhuis, Talko; Blaauw, Frank; van Ittersum, Miriam; Velthuijsen, Hugo; Aiello, Marco.

In: Sensors, Vol. 18, Nr. 2, 19.02.2018.

Onderzoeksoutput: ArticleAcademicpeer review

TY - JOUR

T1 - Personalized physical activity coaching: a machine learning approach

AU - Dijkhuis, Talko

AU - Blaauw, Frank

AU - van Ittersum, Miriam

AU - Velthuijsen, Hugo

AU - Aiello, Marco

PY - 2018/2/19

Y1 - 2018/2/19

N2 - Living a sedentary lifestyle is one of the major causes of numerous health problems. To encourage employees to lead a less sedentary life, the Hanze University started a health promotion program. One of the interventions in the program was the use of an activity tracker to record participants' daily step count. The daily step count served as input for a fortnightly coaching session. In this paper, we investigate the possibility of automating part of the coaching procedure on physical activity by providing personalized feedback throughout the day on a participant's progress in achieving a personal step goal. The gathered step count data was used to train eight different machine learning algorithms to make hourly estimations of the probability of achieving a personalized, daily steps threshold. In 80% of the individual cases, the Random Forest algorithm was the best performing algorithm (mean accuracy = 0.93, range = 0.88–0.99, and mean F1-score = 0.90, range = 0.87–0.94). To demonstrate the practical usefulness of these models, we developed a proof-of-concept Web application that provides personalized feedback about whether a participant is expected to reach his or her daily threshold. We argue that the use of machine learning could become an invaluable asset in the process of automated personalized coaching. The individualized algorithms allow for predicting physical activity during the day and provides the possibility to intervene in time.

AB - Living a sedentary lifestyle is one of the major causes of numerous health problems. To encourage employees to lead a less sedentary life, the Hanze University started a health promotion program. One of the interventions in the program was the use of an activity tracker to record participants' daily step count. The daily step count served as input for a fortnightly coaching session. In this paper, we investigate the possibility of automating part of the coaching procedure on physical activity by providing personalized feedback throughout the day on a participant's progress in achieving a personal step goal. The gathered step count data was used to train eight different machine learning algorithms to make hourly estimations of the probability of achieving a personalized, daily steps threshold. In 80% of the individual cases, the Random Forest algorithm was the best performing algorithm (mean accuracy = 0.93, range = 0.88–0.99, and mean F1-score = 0.90, range = 0.87–0.94). To demonstrate the practical usefulness of these models, we developed a proof-of-concept Web application that provides personalized feedback about whether a participant is expected to reach his or her daily threshold. We argue that the use of machine learning could become an invaluable asset in the process of automated personalized coaching. The individualized algorithms allow for predicting physical activity during the day and provides the possibility to intervene in time.

KW - bewegen (activiteit)

KW - coaching

KW - gezondheid

KW - physical activity

KW - machine learning

KW - coaching

KW - sedentary lifestyle

M3 - Article

VL - 18

JO - Sensors

JF - Sensors

SN - 1424-8220

IS - 2

ER -