The Evolution of Machine Learning Algorithms and Their Contribution to Physical Activity Management.
Gespeichert in:
| Titel: | The Evolution of Machine Learning Algorithms and Their Contribution to Physical Activity Management. |
|---|---|
| Autoren: | Messas K; Bioinformatics and Human Electrophysiology Laboratory, Department of Informatics, Ionian University, Kerkira, Greece. messas.k@ionio.gr., Exarchos T; Bioinformatics and Human Electrophysiology Laboratory, Department of Informatics, Ionian University, Kerkira, Greece. |
| Quelle: | Advances in experimental medicine and biology [Adv Exp Med Biol] 2026; Vol. 1489, pp. 275-281. |
| Publikationsart: | Journal Article; Review |
| Sprache: | English |
| Info zur Zeitschrift: | Publisher: Kluwer Academic/Plenum Publishers Country of Publication: United States NLM ID: 0121103 Publication Model: Print Cited Medium: Print ISSN: 0065-2598 (Print) Linking ISSN: 00652598 NLM ISO Abbreviation: Adv Exp Med Biol Subsets: MEDLINE |
| Imprint Name(s): | Publication: 1998- : New York : Kluwer Academic/Plenum Publishers Original Publication: New York, Plenum Press. |
| MeSH-Schlagworte: | Exercise*/physiology , Machine Learning* , Algorithms*, Humans |
| Abstract: | The evolution of society has redefined people's needs and expanded the possibilities available through technology to manage daily activities, including physical activity. The purpose of this research was to study the extent to which machine learning algorithms can contribute to the personalized suggestion of physical activity programs and the prediction of specific fitness goals. It is recognized that people's daily lives are characterized by complex situations, such as the high prevalence of sedentary lifestyles, the methods of transport used in daily activities, attitudes toward physical activity, and more. Gaps in the literature focus on the lack of individualized recommendations for physical activity. It is further concluded that machine learning algorithms can model data governed by dynamic relationships, such as human behavior. The literature review shows that some machine learning algorithm models demonstrate high prediction accuracy, and that the choice of the appropriate algorithm is guided by the features given to the model. (© 2026. The Author(s), under exclusive license to Springer Nature Switzerland AG.) |
| References: | Ai D et al (2023) Machine learning model for predicting physical activity related bleeding risk in Chinese boys with haemophilia a. Thromb Res 232:43–53. (PMID: 10.1016/j.thromres.2023.10.01237931538) Alsareii SA et al (2022) Physical activity monitoring and classification using machine learning techniques. Life 12(8):1103. https://doi.org/10.3390/life12081103. (PMID: 10.3390/life12081103358929059332439) Aranki D et al (2018) The feasibility and usability of RunningCoach: a remote coaching system for long-distance runners. Sensors 18(1):175. https://doi.org/10.3390/s18010175. (PMID: 10.3390/s18010175293204365795494) Awais M et al (2019) Physical activity classification for elderly people in free-living conditions. IEEE J Biomed Health Inform 23(1):197–207. (PMID: 10.1109/JBHI.2018.282017929994291) Bai Z, Bai X (2021) Sports big data: management, analysis, applications, and challenges. Complexity 2021(1). https://doi.org/10.1155/2021/6676297. Banos O et al (2018) Smart sensing technologies for personalised e-coaching. Sensors 18(6):1751. https://doi.org/10.3390/s18061751. (PMID: 10.3390/s18061751298442926021907) Cheng X et al (2021) Does physical activity predict obesity—a machine learning and statistical method-based analysis. Int J Environ Res Public Health 18(8):3966. https://doi.org/10.3390/ijerph18083966. (PMID: 10.3390/ijerph18083966339187608069304) Cui H, Peng Z (2021) Application of artificial intelligence wearable technology in the big data analysis of physical activity in China. Mob Inf Syst 2021:1–8. https://doi.org/10.1155/2021/1537389. (PMID: 10.1155/2021/1537389) Dancs H (2019) Cooperation between performance analysts and sport data analysts. In: Hughes M, Franks IM, Dancs H (eds) Essentials of performance analysis in sport. Routledge, New York, pp 407–410. https://doi.org/10.4324/9780429340130. (PMID: 10.4324/9780429340130) Dijkhuis TB et al (2018) Personalized physical activity coaching: a machine learning approach. Sensors 18(2):623. https://doi.org/10.3390/s18020623. (PMID: 10.3390/s18020623294630525856112) Galasso S et al (2023) Predicting physical activity levels from kinematic gait data using machine learning techniques. Eng Appl Artif Intell 123:106487. https://doi.org/10.1016/j.engappai.2023.106487. (PMID: 10.1016/j.engappai.2023.106487) Klein M, Manzoor A, Mollee J (2017) Active2Gether: a personalized M-health intervention to encourage physical activity. Sensors 17(6):1436. (PMID: 10.3390/s17061436286291785492389) Lu Y (2023) Using machine learning algorithms to design personalized exercise programs for health and wellness. Scalable Comput: Pract Exp 24(3):463–474. Ma X (2022) Analysis of human exercise health monitoring data of smart bracelet based on machine learning. Comput Intell Neurosci 2022:1–11. McKay FH et al (2019) Using health and Well-being apps for behavior change: a systematic search and rating of apps. JMIR Mhealth Uhealth 7(7):e11926. (PMID: 10.2196/11926312741126637726) Papadakis N et al (2020) Employing body-fixed sensors and machine learning to predict physical activity in military personnel. BMJ Military Health 169(2):152–156. https://doi.org/10.1136/bmjmilitary-2020-001585. (PMID: 10.1136/bmjmilitary-2020-00158533127870) Pickett KL et al (2021) Random survival forests for dynamic predictions of a time-to-event outcome using a longitudinal biomarker. BMC Med Res Methodol 21(1). https://doi.org/10.1186/s12874-021-01375-x. Rabbi M et al (2015) Automated personalized feedback for physical activity and dietary behavior change with mobile phones: a randomized controlled trial on adults. JMIR Mhealth Uhealth 3(2). https://doi.org/10.2196/mhealth.4160. Silacci A et al (2019) Designing an e-coach to tailor training plans for road cyclists. Adv Intell Systems Comput:671–677. Silacci A, Taiar R, Caon M (2020) Towards an AI-based tailored training planning for road cyclists: a case study. Appl Sci 11(1):313. https://doi.org/10.3390/app11010313. (PMID: 10.3390/app11010313) Vanstrum EB et al (2023) Machine learning analysis of physical activity data to classify postural dysfunction. Laryngoscope 133(12):3529–3533. https://doi.org/10.1002/lary.30698. (PMID: 10.1002/lary.306983708311210589386) WHO (n.d.) Physical activity. Available at: http://www.who.int/topics/physical_activity/en/. |
| Contributed Indexing: | Keywords: Dynamic data analysis; Personalized training; Physical activity management; Time-series analysis; Wearable sensors |
| Entry Date(s): | Date Created: 20251118 Date Completed: 20251118 Latest Revision: 20260214 |
| Update Code: | 20260215 |
| DOI: | 10.1007/978-3-032-03394-9_27 |
| PMID: | 41252014 |
| Datenbank: | MEDLINE |
Nájsť tento článok vo Web of Science | Abstract: | The evolution of society has redefined people's needs and expanded the possibilities available through technology to manage daily activities, including physical activity. The purpose of this research was to study the extent to which machine learning algorithms can contribute to the personalized suggestion of physical activity programs and the prediction of specific fitness goals. It is recognized that people's daily lives are characterized by complex situations, such as the high prevalence of sedentary lifestyles, the methods of transport used in daily activities, attitudes toward physical activity, and more. Gaps in the literature focus on the lack of individualized recommendations for physical activity. It is further concluded that machine learning algorithms can model data governed by dynamic relationships, such as human behavior. The literature review shows that some machine learning algorithm models demonstrate high prediction accuracy, and that the choice of the appropriate algorithm is guided by the features given to the model.<br /> (© 2026. The Author(s), under exclusive license to Springer Nature Switzerland AG.) |
|---|---|
| ISSN: | 0065-2598 |
| DOI: | 10.1007/978-3-032-03394-9_27 |