A Clustering Approach for Personalized Coaching Applications

Anika van Buren; Audrey Kwan; Harald Rietdijk; Talko  Dijkhuis; Patricia Conde-Cespedes; Hilbrand Oldenhuis; Maria Trocan

doi:10.1007/978-3-031-70259-4_27

A Clustering Approach for Personalized Coaching Applications

Anika van Buren, Audrey Kwan, Harald Rietdijk, Talko Dijkhuis, Patricia Conde-Cespedes, Hilbrand Oldenhuis, Maria Trocan

Research output: Chapter in Book/Report/Conference proceeding › Contribution to conference proceeding › Academic › peer-review

Abstract

Insufficient physical activity presents a significant hazard to overall health, with sedentary lifestyles linked to a variety of health issues. Monitoring physical activity levels allows the recognition of patterns of sedentary behavior and the provision of coaching to meet the recommended physical activity standards. In this paper, we aim to address the problem of reducing the time consuming process of fitting classifiers when generating personalized models for a coaching application. The proposed approach consists of evaluating the effects of clustering participants based on their walking patterns and then recommending a unique model for each group. Each model consists of a random forest classifier with a different number of estimators each. The resulting approach reduces the fitting time considerably while keeping nearly the same classification performance as personalized models.

Translated title of the contribution	Een clustering benadering voor gepersonaliseerde coaching applicaties
Original language	English
Title of host publication	Advances in Computational Collective Intelligence
Subtitle of host publication	16th International Conference, ICCCI 2024 Leipzig, Germany, September 9–11, 2024 Proceedings, Part II
Place of Publication	Cham
Publisher	Springer International Publishing
Pages	351-362
Number of pages	12
Volume	2166
ISBN (Electronic)	978-3-031-70259-4
ISBN (Print)	978-3-031-70258-7
DOIs	https://doi.org/10.1007/978-3-031-70259-4_27
Publication status	Published - 9 Sept 2024
Event	Advances in Computational Collective Intelligence - Leipzig University, Leipzig, Germany Duration: 9 Sept 2024 → 11 Sept 2024 Conference number: 16

Conference

Conference	Advances in Computational Collective Intelligence
Country/Territory	Germany
City	Leipzig
Period	9/09/24 → 11/09/24

Keywords

clustering
estimators
fitting time optimization
gersonalized coaching
random forests
sedentary lifestyle
variability

Research Focus Areas Hanze University of Applied Sciences * (mandatory by Hanze)

Entrepreneurship
Energy
Healthy Ageing

Publinova themes

Language, Culture and Arts
Economics and Management
Law
ICT and Media
Health
People and Society
Technology

Access to Document

10.1007/978-3-031-70259-4_27

Best Student Paper Award
Rietdijk, H. (Recipient), 11 Sept 2024
Prize: Prize (including medals and awards)

Cite this

van Buren, A., Kwan, A., Rietdijk, H., Dijkhuis, T., Conde-Cespedes, P., Oldenhuis, H., & Trocan, M. (2024). A Clustering Approach for Personalized Coaching Applications. In Advances in Computational Collective Intelligence: 16th International Conference, ICCCI 2024 Leipzig, Germany, September 9–11, 2024 Proceedings, Part II (Vol. 2166, pp. 351-362). Springer International Publishing. https://doi.org/10.1007/978-3-031-70259-4_27

@inproceedings{f8f17ca382b24ccdbaa2f1a9f18d1b1b,

title = "A Clustering Approach for Personalized Coaching Applications",

abstract = "Insufficient physical activity presents a significant hazard to overall health, with sedentary lifestyles linked to a variety of health issues. Monitoring physical activity levels allows the recognition of patterns of sedentary behavior and the provision of coaching to meet the recommended physical activity standards. In this paper, we aim to address the problem of reducing the time consuming process of fitting classifiers when generating personalized models for a coaching application. The proposed approach consists of evaluating the effects of clustering participants based on their walking patterns and then recommending a unique model for each group. Each model consists of a random forest classifier with a different number of estimators each. The resulting approach reduces the fitting time considerably while keeping nearly the same classification performance as personalized models.",

keywords = "clustering, gepersonaliseerde coaching, optimalisatie van de montagetijd, schattingen, sedentaire levensstijl, variabiliteit, willekeurige bossen, clustering, estimators, fitting time optimization, gersonalized coaching, random forests, sedentary lifestyle, variability",

author = "{van Buren}, Anika and Audrey Kwan and Harald Rietdijk and Talko Dijkhuis and Patricia Conde-Cespedes and Hilbrand Oldenhuis and Maria Trocan",

year = "2024",

month = sep,

day = "9",

doi = "10.1007/978-3-031-70259-4_27",

language = "English",

isbn = "978-3-031-70258-7",

volume = "2166",

pages = "351--362",

booktitle = "Advances in Computational Collective Intelligence",

publisher = "Springer International Publishing",

address = "Switzerland",

note = "Advances in Computational Collective Intelligence ; Conference date: 09-09-2024 Through 11-09-2024",

}

van Buren, A, Kwan, A, Rietdijk, H , Dijkhuis, T, Conde-Cespedes, P, Oldenhuis, H & Trocan, M 2024, A Clustering Approach for Personalized Coaching Applications. in Advances in Computational Collective Intelligence: 16th International Conference, ICCCI 2024 Leipzig, Germany, September 9–11, 2024 Proceedings, Part II. vol. 2166, Springer International Publishing, Cham, pp. 351-362, Advances in Computational Collective Intelligence, Leipzig, Saxony, Germany, 9/09/24. https://doi.org/10.1007/978-3-031-70259-4_27

A Clustering Approach for Personalized Coaching Applications. / van Buren, Anika; Kwan, Audrey; Rietdijk, Harald et al.
Advances in Computational Collective Intelligence: 16th International Conference, ICCCI 2024 Leipzig, Germany, September 9–11, 2024 Proceedings, Part II. Vol. 2166 Cham: Springer International Publishing, 2024. p. 351-362.

Research output: Chapter in Book/Report/Conference proceeding › Contribution to conference proceeding › Academic › peer-review

TY - GEN

T1 - A Clustering Approach for Personalized Coaching Applications

AU - van Buren, Anika

AU - Kwan, Audrey

AU - Rietdijk, Harald

AU - Dijkhuis, Talko

AU - Conde-Cespedes, Patricia

AU - Oldenhuis, Hilbrand

AU - Trocan, Maria

N1 - Conference code: 16

PY - 2024/9/9

Y1 - 2024/9/9

N2 - Insufficient physical activity presents a significant hazard to overall health, with sedentary lifestyles linked to a variety of health issues. Monitoring physical activity levels allows the recognition of patterns of sedentary behavior and the provision of coaching to meet the recommended physical activity standards. In this paper, we aim to address the problem of reducing the time consuming process of fitting classifiers when generating personalized models for a coaching application. The proposed approach consists of evaluating the effects of clustering participants based on their walking patterns and then recommending a unique model for each group. Each model consists of a random forest classifier with a different number of estimators each. The resulting approach reduces the fitting time considerably while keeping nearly the same classification performance as personalized models.

AB - Insufficient physical activity presents a significant hazard to overall health, with sedentary lifestyles linked to a variety of health issues. Monitoring physical activity levels allows the recognition of patterns of sedentary behavior and the provision of coaching to meet the recommended physical activity standards. In this paper, we aim to address the problem of reducing the time consuming process of fitting classifiers when generating personalized models for a coaching application. The proposed approach consists of evaluating the effects of clustering participants based on their walking patterns and then recommending a unique model for each group. Each model consists of a random forest classifier with a different number of estimators each. The resulting approach reduces the fitting time considerably while keeping nearly the same classification performance as personalized models.

KW - clustering

KW - gepersonaliseerde coaching

KW - optimalisatie van de montagetijd

KW - schattingen

KW - sedentaire levensstijl

KW - variabiliteit

KW - willekeurige bossen

KW - clustering

KW - estimators

KW - fitting time optimization

KW - gersonalized coaching

KW - random forests

KW - sedentary lifestyle

KW - variability

U2 - 10.1007/978-3-031-70259-4_27

DO - 10.1007/978-3-031-70259-4_27

M3 - Contribution to conference proceeding

SN - 978-3-031-70258-7

VL - 2166

SP - 351

EP - 362

BT - Advances in Computational Collective Intelligence

PB - Springer International Publishing

CY - Cham

T2 - Advances in Computational Collective Intelligence

Y2 - 9 September 2024 through 11 September 2024

ER -

van Buren A, Kwan A, Rietdijk H , Dijkhuis T, Conde-Cespedes P, Oldenhuis H et al. A Clustering Approach for Personalized Coaching Applications. In Advances in Computational Collective Intelligence: 16th International Conference, ICCCI 2024 Leipzig, Germany, September 9–11, 2024 Proceedings, Part II. Vol. 2166. Cham: Springer International Publishing. 2024. p. 351-362 doi: 10.1007/978-3-031-70259-4_27

A Clustering Approach for Personalized Coaching Applications

Abstract

Conference

Keywords

Research Focus Areas Hanze University of Applied Sciences * (mandatory by Hanze)

Publinova themes

Access to Document

Fingerprint

Prizes

Best Student Paper Award

Cite this