Machine learning in physical activity, sedentary, and sleep behavior research

Aug 5, 2026

Upload by Liam

Human movement and non-movement behaviors are multidimensional and difficult to study, but wearable activity monitors enable continuous measurement across physical activity, sedentary behavior, and sleep. The growing volume and complexity of resulting data require advanced analysis methods tailored to these patterns. Machine learning offers models that handle complicated data and can support tasks such as activity recognition, posture detection, profile analysis, and correlate research. This review introduces ML basics, supervised and unsupervised learning, key algorithms, and research areas where ML has already been applied, outlining successes and challenges.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Abstract

Introduction

Wearable monitoring and data complexity

Machine learning modeling pipeline (overview)

Types of machine learning

Supervised learning

Unsupervised learning

Machine learning algorithms (examples)

Research areas and applications

Activity recognition and posture detection

Profile analysis and correlates

Farrahi and Rostami Journal of Activity, Sedentary and Sleep Behaviors [https://doi.org/10.1186/s44167-024-00045-9](https://doi.org/10.1186/s44167-024-00045-9) Journal of Activity, Sedentary (2024) 3:5 and Sleep Behaviors REVIEW Open Access Machine learning in physical activity, sedentary, and sleep behavior research Vahid Farrahi 1* and Mehrdad Rostami2 Abstract The nature of human movement and non-movement behaviors is complex and multifaceted, making their study complicated and challenging. Thanks to the availability of wearable activity monitors, we can now monitor the full spectrum of physical activity, sedentary, and sleep behaviors better than ever before—whether the subjects are elite athletes, children, adults, or individuals with pre-existing medical conditions. The increasing volume of generated data, combined with the inherent complexities of human movement and non-movement behaviors, necessitates the development of new data analysis methods for the research of physical activity, sedentary, and sleep behaviors. The characteristics of machine learning (ML) methods, including their ability to deal with complicated data, make them suitable for such analysis and thus can be an alternative tool to deal with data of this nature. ML can potentially be an excellent tool for solving many traditional problems related to the research of physical activity, sedentary, and sleep behaviors such as activity recognition, posture detection, profile analysis, and correlates research. However, despite this potential, ML has not yet been widely utilized for analyzing and studying these behaviors. In this review, we aim to introduce experts in physical activity, sedentary behavior, and sleep research—individuals who may possess limited familiarity with ML—to the potential applications of these techniques for analyzing their data. We begin by explaining the underlying principles of the ML modeling pipeline, highlighting the challenges and issues that need to be considered when applying ML. We then present the types of ML: supervised and unsupervised learning, and introduce a few ML algorithms frequently used in supervised and unsupervised learning. Finally, we highlight three research areas where ML methodologies have already been used in physical activity, sedentary behavior, and sleep behavior research, emphasizing their successes and challenges. This paper serves as a resource for ML in physical activity, sedentary, and sleep behavior research, offering guidance and resources to facilitate its utilization. Keywords Wearables, Supervised learning, Unsupervised learning, Classification, Clustering, Machine learning modelling, Predictive modelling Introduction Our daily lives constitute three main components—physical activity, sedentary, and sleep behaviors—that are interconnected with each other [1] and codependently *Correspondence: Vahid Farrahi [Vahid.farrahi@tu-dortmund.de](Vahid.farrahi@tu-dortmund.de) 1 Institute for Sport and Sport Science, TU Dortmund University, Dortmund, Germany 2 Centre of Machine Vision and Signal Analysis, Faculty of Information Technology, University of Oulu, Oulu, Finland related to various aspects of our health [2, 3]. In recent years, there has been a growing use of wearable devices to measure these behaviors, adding to the complexity of studying and understanding them. Nowadays, wearable activity monitors have the capacity to continuously capture the entire spectrum of movement and non-movement behaviors over extended periods [2], lasting even up to several weeks [4]. However, making sense of such data is challenging and often requires the use of advanced analytical tools tailored to handle their complex nature [2, 3]. © The Author(s) 2024. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credi

FAQs

Why is studying physical activity, sedentary, and sleep behavior challenging?

Human movement and non-movement behaviors are complex and multifaceted, and the 24-hour interdependence makes it hard to choose appropriate mathematical relationships. Wearable data also introduces large-scale complexity that classical methods often cannot capture well.

How can machine learning help in this research area?

Machine learning can manage complicated data and support problems such as activity recognition, posture detection, profile analysis, and correlate research. It can serve as an alternative tool where traditional approaches struggle.

What does the review cover regarding machine learning methods?

It explains the ML modeling pipeline principles, discusses challenges in applying ML, and presents supervised and unsupervised learning along with commonly used algorithms. It also highlights three research areas where ML has already been used, including successes and challenges.

Aug 5, 2026

Upload by Liam