{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T23:01:16Z","timestamp":1790982076968,"version":"4.1.0"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001030","name":"National Heart Foundation of Australia","doi-asserted-by":"publisher","award":["APP 107158"],"award-info":[{"award-number":["APP 107158"]}],"id":[{"id":"10.13039\/501100001030","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Behav Nutr Phys Act"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Wearable accelerometers are widely used in health research, but differing placements (e.g. wrist vs. thigh) hinder harmonising activity classification across studies. Prior studies report 1.5- to 2.0-fold differences in physical activity level by wear location, hampering data comparability, and compromising the potential for pooling data to develop consortia and carrying out Meta- and Individual Participant Data analysis. Although supervised machine learning is increasingly used in wearables research, its reliance on extensive labelled data limits its use in free-living datasets. Semi-supervised learning offers an efficient alternative by using laboratory collected labelled data to iteratively self-train models on unlabelled free-living data. Using a self-training approach, the aim of this study was to train and evaluate algorithms for wrist- and thigh-worn devices to facilitate harmonisation of posture and activity type classification between placements.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A total of 146 participants aged 30\u201375 years completed either structured laboratory-based activity trials or one of two independent free-living assessments while wearing Axivity AX3 accelerometers on the wrist and thigh. For each placement, a supervised Random Forest classifier was initially trained using a labelled laboratory dataset (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200940) to classify sitting, standing, walking, running, stair climbing, and cycling - and then re-trained using self-training on free-living data (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200953, independent to the laboratory study sample). The final models were validated using another hold-out free-living independent dataset (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200953) with ground-truth activity labels obtained via direct video observation. Overall model comparison and performance was assessed using accuracy, kappa statistic, and F1 scores. Individual activity class comparison and performance was evaluated using equivalence testing, confusion matrices, and coefficient of variation between the wrist and thigh estimates.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>During a total of 43,800\u00a0min, of which 19,080\u00a0min were in the hold-out dataset, both self-trained models achieved high overall classification accuracy: 91.8% (SD\u2009=\u20096.8%) for the wrist and 95.1% (SD\u2009=\u20095.4%) for the thigh. The overall F1 score was 88.2 (SD\u2009=\u20099.6%) for the wrist classifier and 90.1 (SD\u2009=\u20099.3%) for the thigh classifier. Equivalence testing demonstrated that both classifiers produced activity duration estimates statistically equivalent to ground-truth for all activity types except stair climbing. Confusion matrices for the wrist demonstrated very good to excellent (88% \u2212\u200997%) classification accuracy for sitting, walking, running, and cycling, and good accuracy for standing and stair climbing (71%\u201378%). For the thigh, classification performance was very good to excellent (83% \u2212\u200998%) across sitting, standing, walking, running, and cycling, with good accuracy for stair climbing (75%). The coefficient of variation values ranged from 0.022 for running to 0.140 for standing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>These findings highlight the potential of self-training models to support harmonisation of wearable accelerometer data collected using different wear placements. Self-training models reduce reliance on extensive labelled data and demonstrated high activity type classification accuracy for both wrist- and thigh-worn accelerometers, with a high degree of agreement and equivalence with ground-truth data across almost all activity types.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12966-026-01930-z","type":"journal-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T03:21:11Z","timestamp":1782962471000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Development and evaluation of wrist- and thigh-worn accelerometer algorithms using self-training machine learning models for classification of activity type and posture: towards device placement-agnostic methods in the ProPASS consortium"],"prefix":"10.1186","volume":"23","author":[{"given":"Matthew N.","family":"Ahmadi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas","family":"Koemel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raaj","family":"Biswas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Holtermann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annemarie","family":"Koster","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Atkins","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Pulsford","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Borja","family":"del Pozo Cruz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vegar","family":"Rangul","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Mitchell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joanna","family":"Blodgett","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pasan","family":"Hettiarachchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Magnus","family":"Svartengren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Malcolm","family":"Granat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bronwyn","family":"Clark","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Hamer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel","family":"Stamatakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"1930_CR1","doi-asserted-by":"publisher","unstructured":"LeeI-M, Powell KE, Sarmiento OL, Hallal PC. Even a small dose of physical activity can be good medicine. Nat Med. 2025:1\u20133. https:\/\/doi.org\/10.1038\/s41591-024-03396-7.","DOI":"10.1038\/s41591-024-03396-7"},{"key":"1930_CR2","doi-asserted-by":"publisher","unstructured":"LeeI-M, Keadle SK, Matthews CE. Fitness Trackers to Guide Advice on Activity Prescription. JAMA. 2023. https:\/\/doi.org\/10.1001\/jama.2023.19332.","DOI":"10.1001\/jama.2023.19332"},{"issue":"6","key":"1930_CR3","doi-asserted-by":"publisher","first-page":"dyae136","DOI":"10.1093\/ije\/dyae136","volume":"53","author":"MN Ahmadi","year":"2024","unstructured":"Ahmadi MN, Coenen P, Straker L, Stamatakis E. Device-measured stationary behaviour and cardiovascular and orthostatic circulatory disease incidence. Int J Epidemiol. 2024;53(6):dyae136.","journal-title":"Int J Epidemiol"},{"issue":"5","key":"1930_CR4","doi-asserted-by":"publisher","first-page":"e023433","DOI":"10.1161\/JAHA.121.023433","volume":"11","author":"S Nguyen","year":"2022","unstructured":"Nguyen S, Bellettiere J, Wang G, et al. Accelerometer-derived daily life movement classified by machine learning and incidence of cardiovascular disease in older women: the OPACH study. J Am Heart Association. 2022;11(5):e023433.","journal-title":"J Am Heart Association"},{"issue":"1","key":"1930_CR5","first-page":"77","volume":"76","author":"P Jain","year":"2021","unstructured":"Jain P, Bellettiere J, Glass N, et al. The relationship of accelerometer-assessed standing time with and without ambulation and mortality: the WHI OPACH study. Journals Gerontology: Ser A. 2021;76(1):77\u201384.","journal-title":"Journals Gerontology: Ser A"},{"issue":"2","key":"1930_CR6","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1161\/CIRCULATIONAHA.124.069820","volume":"151","author":"JM Blodgett","year":"2025","unstructured":"Blodgett JM, Ahmadi MN, Atkin AJ, et al. Device-measured 24-hour movement behaviors and blood pressure: a 6-part compositional individual participant data analysis in the ProPASS Consortium. Circulation. 2025;151(2):159\u201370.","journal-title":"Circulation"},{"key":"1930_CR7","doi-asserted-by":"publisher","unstructured":"Edwardson CL, Biddle SJ, Clemes SA et al. Effectiveness of an intervention for reducing sitting time and improving health in office workers: three arm cluster randomised controlled trial. BMJ. 2022;378. https:\/\/doi.org\/10.1136\/bmj-2021-069288.","DOI":"10.1136\/bmj-2021-069288"},{"issue":"10","key":"1930_CR8","doi-asserted-by":"publisher","first-page":"2129","DOI":"10.1249\/MSS.0000000000000661","volume":"47","author":"K Wijndaele","year":"2015","unstructured":"Wijndaele K, Westgate K, Stephens SK, et al. Utilization and harmonization of adult accelerometry data: review and expert consensus. Med Sci Sports Exerc. 2015;47(10):2129.","journal-title":"Med Sci Sports Exerc"},{"issue":"1","key":"1930_CR9","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1123\/jmpb.2021-0046","volume":"5","author":"T Strain","year":"2022","unstructured":"Strain T, Wijndaele K, Pearce M, Brage S. Considerations for the use of consumer-grade wearables and smartphones in population surveillance of physical activity. J Meas Phys Behav. 2022;5(1):8\u201314.","journal-title":"J Meas Phys Behav"},{"issue":"1","key":"1930_CR10","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1186\/s12966-022-01388-9","volume":"20","author":"RM Pulsford","year":"2023","unstructured":"Pulsford RM, Brocklebank L, Fenton SA, et al. The impact of selected methodological factors on data collection outcomes in observational studies of device-measured physical behaviour in adults: A systematic review. Int J Behav Nutr Phys Activity. 2023;20(1):26.","journal-title":"Int J Behav Nutr Phys Activity"},{"key":"1930_CR11","doi-asserted-by":"publisher","unstructured":"IoannidisJ. Next-generation systematic reviews: prospective meta-analysis, individual-level data, networks and umbrella reviews. Br J Sports Med. 2017:1456\u20138. https:\/\/doi.org\/10.1136\/bjsports-2017-097621.","DOI":"10.1136\/bjsports-2017-097621"},{"issue":"8","key":"1930_CR12","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1136\/bjsports-2019-100786","volume":"54","author":"E Stamatakis","year":"2020","unstructured":"Stamatakis E, Koster A, Hamer M, et al. Emerging collaborative research platforms for the next generation of physical activity, sleep and exercise medicine guidelines: the Prospective Physical Activity, Sitting, and Sleep consortium (ProPASS). Br J Sports Med. 2020;54(8):435\u20137. https:\/\/doi.org\/10.1136\/bjsports-2019-100786.","journal-title":"Br J Sports Med"},{"key":"1930_CR13","doi-asserted-by":"publisher","unstructured":"Ahmadi MN, Blodgett JM, Atkin AJ et al. Relationship of device measured physical activity type and posture with cardiometabolic health markers: pooled dose\u2013response associations from the Prospective Physical Activity, Sitting and Sleep Consortium. Diabetologia. 2024:1\u201315. https:\/\/doi.org\/10.1007\/s00125-024-06090-y.","DOI":"10.1007\/s00125-024-06090-y"},{"key":"1930_CR14","doi-asserted-by":"publisher","unstructured":"Blodgett JM, Ahmadi MN, Atkin AJ et al. Device-measured physical activity and cardiometabolic health: the Prospective Physical Activity, Sitting, and Sleep (ProPASS) consortium. Eur Heart J. 2023:ehad717. https:\/\/doi.org\/10.1093\/eurheartj\/ehad717.","DOI":"10.1093\/eurheartj\/ehad717"},{"key":"1930_CR15","doi-asserted-by":"publisher","unstructured":"Chong KH, Suesse T, Cross PL et al. Pooled Analysis of Physical Activity, Sedentary Behavior, and Sleep Among Children From 33 Countries. JAMA Pediatr. 2024. https:\/\/doi.org\/10.1001\/jamapediatrics.2024.3330.","DOI":"10.1001\/jamapediatrics.2024.3330"},{"issue":"22","key":"1930_CR16","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.1136\/bjsports-2020-102345","volume":"55","author":"S Chastin","year":"2021","unstructured":"Chastin S, McGregor D, Palarea-Albaladejo J, et al. Joint association between accelerometry-measured daily combination of time spent in physical activity, sedentary behaviour and sleep and all-cause mortality: a pooled analysis of six prospective cohorts using compositional analysis. Br J Sports Med. 2021;55(22):1277\u201385. https:\/\/doi.org\/10.1136\/bjsports-2020-102345.","journal-title":"Br J Sports Med"},{"key":"1930_CR17","doi-asserted-by":"crossref","unstructured":"Wang Q, Lohit S, Toledo MJ, Buman MP, Turaga P. A statistical estimation framework for energy expenditure of physical activities from a wrist-worn accelerometer. IEEE. 2016:2631\u20135.","DOI":"10.1109\/EMBC.2016.7591270"},{"key":"1930_CR18","unstructured":"World Health O. Physical activity measurement and surveillance in adults: report of a scoping and planning meeting, 27\u201328 November 2023. World Health Organization; 2024. https:\/\/www.who.int\/publications\/i\/item\/9789240095557."},{"issue":"24","key":"1930_CR19","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1136\/bjsports-2020-102955","volume":"54","author":"FC Bull","year":"2020","unstructured":"Bull FC, Al-Ansari SS, Biddle S, et al. World Health Organization 2020 guidelines on physical activity and sedentary behaviour. Br J Sports Med. 2020;54(24):1451\u201362. https:\/\/doi.org\/10.1136\/bjsports-2020-102955.","journal-title":"Br J Sports Med"},{"key":"1930_CR20","unstructured":"International Society of Physical Activity and Health. Satellite Event: Towards the 1st device-based guidelines of physical activity, sedentary behaviour & sleep. https:\/\/ispah.org\/satellite-event-towards-the-1st-device-based-guidelines-of-physical-activity-sedentary-behaviour-sleep\/."},{"issue":"5","key":"1930_CR21","doi-asserted-by":"publisher","first-page":"941","DOI":"10.1249\/MSS.0000000000000844","volume":"48","author":"JE Sasaki","year":"2016","unstructured":"Sasaki JE, Hickey A, Staudenmayer J, John D, Kent JA, Freedson PS. Performance of activity classification algorithms in free-living older adults. Med Sci Sports Exerc. 2016;48(5):941.","journal-title":"Med Sci Sports Exerc"},{"key":"1930_CR22","doi-asserted-by":"publisher","unstructured":"Bastian T, Maire A, Dugas J et al. Automatic identification of physical activity types and sedentary behaviors from triaxial accelerometer: laboratory-based calibrations are not enough. J Appl Physiol. 2015. https:\/\/doi.org\/10.1152\/japplphysiol.01189.2013.","DOI":"10.1152\/japplphysiol.01189.2013"},{"issue":"1","key":"1930_CR23","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1093\/nsr\/nwx106","volume":"5","author":"Z-H Zhou","year":"2018","unstructured":"Zhou Z-H. A brief introduction to weakly supervised learning. Natl Sci Rev. 2018;5(1):44\u201353.","journal-title":"Natl Sci Rev"},{"key":"1930_CR24","first-page":"22243","volume":"33","author":"T Chen","year":"2020","unstructured":"Chen T, Kornblith S, Swersky K, Norouzi M, Hinton GE. Big self-supervised models are strong semi-supervised learners. Adv Neural Inf Process Syst. 2020;33:22243\u201355.","journal-title":"Adv Neural Inf Process Syst"},{"key":"1930_CR25","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s10115-013-0706-y","volume":"42","author":"I Triguero","year":"2015","unstructured":"Triguero I, Garc\u00eda S, Herrera F. Self-labeled techniques for semi-supervised learning: taxonomy, software and empirical study. Knowl Inf Syst. 2015;42:245\u201384.","journal-title":"Knowl Inf Syst"},{"key":"1930_CR26","doi-asserted-by":"crossref","unstructured":"Leistner C, Saffari A, Santner J, Bischof H. Semi-supervised random forests. IEEE. 2009:506\u201313.","DOI":"10.1109\/ICCV.2009.5459198"},{"issue":"21","key":"1930_CR27","doi-asserted-by":"publisher","first-page":"3017","DOI":"10.1093\/bioinformatics\/btr502","volume":"27","author":"M Shi","year":"2011","unstructured":"Shi M, Zhang B. Semi-supervised learning improves gene expression-based prediction of cancer recurrence. Bioinformatics. 2011;27(21):3017\u201323.","journal-title":"Bioinformatics"},{"key":"1930_CR28","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.amsu.2020.12.043","volume":"62","author":"N Al-Azzam","year":"2021","unstructured":"Al-Azzam N, Shatnawi I. Comparing supervised and semi-supervised machine learning models on diagnosing breast cancer. Annals Med Surg. 2021;62:53\u201364.","journal-title":"Annals Med Surg"},{"key":"1930_CR29","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/s13042-015-0328-7","volume":"8","author":"J Tanha","year":"2017","unstructured":"Tanha J, Van Someren M, Afsarmanesh H. Semi-supervised self-training for decision tree classifiers. Int J Mach Learn Cybernet. 2017;8:355\u201370.","journal-title":"Int J Mach Learn Cybernet"},{"key":"1930_CR30","first-page":"8887","volume":"975","author":"A Ennaji","year":"2012","unstructured":"Ennaji A, Mammass D, El Yassa M. Self-training using a k-nearest neighbor as a base classifier reinforced by support vector machines. Int J Comput Appl. 2012;975:8887.","journal-title":"Int J Comput Appl"},{"issue":"1","key":"1930_CR31","doi-asserted-by":"publisher","first-page":"67","DOI":"10.3233\/IDA-150794","volume":"20","author":"M Chen","year":"2016","unstructured":"Chen M, Tan X, Zhang L. An iterative self-training support vector machine algorithm in brain-computer interfaces. Intell Data Anal. 2016;20(1):67\u201382.","journal-title":"Intell Data Anal"},{"key":"1930_CR32","doi-asserted-by":"crossref","unstructured":"Lu W, Zhang X, Han L et al. Research on self-training enhanced semi-supervised support vector machine framework. SPIE; 2024. 334\u2013340. https:\/\/www.spiedigitallibrary.org\/conference-proceedings-of-spie\/13222\/132221C\/Research-on-self-training-enhanced-semi-supervised-support-vector-machine\/10.1117\/12.3038653.short.","DOI":"10.1117\/12.3038653"},{"key":"1930_CR33","doi-asserted-by":"crossref","unstructured":"Chau VTN, Phung NH. A random forest-based self-training algorithm for study status prediction at the program level: Minsemi-RF. Springer; 2016. 219\u201330. https:\/\/link.springer.com\/chapter\/10.1007\/978-3-319-49397-8_19.","DOI":"10.1007\/978-3-319-49397-8_19"},{"issue":"2","key":"1930_CR34","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1111\/mice.12601","volume":"36","author":"M Zhu","year":"2021","unstructured":"Zhu M, Zhu H, Guo F, Chen X, Ju JW. Tunnel condition assessment via cloud model-based random forests and self\u2010training approach. Computer\u2010Aided Civil Infrastructure Eng. 2021;36(2):164\u201379.","journal-title":"Computer\u2010Aided Civil Infrastructure Eng"},{"key":"1930_CR35","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1007\/s11053-018-9416-1","volume":"28","author":"MI Sameen","year":"2019","unstructured":"Sameen MI, Pradhan B, Lee S. Self-learning random forests model for mapping groundwater yield in data-scarce areas. Nat Resour Res. 2019;28:757\u201375.","journal-title":"Nat Resour Res"},{"issue":"4","key":"1930_CR36","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1249\/JES.0000000000000206","volume":"47","author":"SK Keadle","year":"2019","unstructured":"Keadle SK, Lyden KA, Strath SJ, Staudenmayer JW, Freedson PS. A framework to evaluate devices that assess physical behavior. Exerc Sport Sci Rev. 2019;47(4):206\u201314.","journal-title":"Exerc Sport Sci Rev"},{"issue":"2","key":"1930_CR37","first-page":"3","volume":"4","author":"DE Warburton","year":"2011","unstructured":"Warburton DE, Jamnik VK, Bredin SS, Gledhill N. The physical activity readiness questionnaire for everyone (PAR-Q+) and electronic physical activity readiness medical examination (ePARmed-X+). Health Fit J Can. 2011;4(2):3\u201317.","journal-title":"Health Fit J Can"},{"issue":"24","key":"1930_CR38","doi-asserted-by":"publisher","first-page":"9323","DOI":"10.3390\/ijerph17249323","volume":"17","author":"A Davies","year":"2020","unstructured":"Davies A, Allman-Farinelli M, Owen K, et al. Feasibility study comparing physical activity classifications from accelerometers with wearable camera data. Int J Environ Res Public Health. 2020;17(24):9323.","journal-title":"Int J Environ Res Public Health"},{"issue":"4","key":"1930_CR39","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1080\/02640414.2019.1703301","volume":"38","author":"MN Ahmadi","year":"2020","unstructured":"Ahmadi MN, Nathan N, Sutherland R, Wolfenden L, Trost SG. Non-wear or sleep? Evaluation of five non-wear detection algorithms for raw accelerometer data. J Sports Sci. 2020;38(4):399\u2013404. https:\/\/doi.org\/10.1080\/02640414.2019.1703301.","journal-title":"J Sports Sci"},{"issue":"5","key":"1930_CR40","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1109\/jsen.2011.2167319","volume":"12","author":"M Sipos","year":"2012","unstructured":"Sipos M, Paces P, Rohac J, Novacek P. Analyses of Triaxial Accelerometer Calibration Algorithms. IEEE Sens J. 2012;12(5):1157\u201365. https:\/\/doi.org\/10.1109\/jsen.2011.2167319.","journal-title":"IEEE Sens J"},{"key":"1930_CR41","doi-asserted-by":"publisher","unstructured":"Ellis K, Kerr J, Godbole S, Staudenmayer J, Lanckriet G. Hip and Wrist Accelerometer Algorithms for Free-Living Behavior Classification. Med Sci Sports Exerc. May 2016;48(5):933\u201340. https:\/\/doi.org\/10.1249\/MSS.0000000000000840.","DOI":"10.1249\/MSS.0000000000000840"},{"issue":"1","key":"1930_CR42","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.jsams.2016.06.003","volume":"20","author":"TG Pavey","year":"2017","unstructured":"Pavey TG, Gilson ND, Gomersall SR, Clark B, Trost SG. Field evaluation of a random forest activity classifier for wrist-worn accelerometer data. J Sci Med Sport Jan. 2017;20(1):75\u201380. https:\/\/doi.org\/10.1016\/j.jsams.2016.06.003.","journal-title":"J Sci Med Sport Jan"},{"issue":"5","key":"1930_CR43","doi-asserted-by":"publisher","first-page":"e0233229","DOI":"10.1371\/journal.pone.0233229","volume":"15","author":"MN Ahmadi","year":"2020","unstructured":"Ahmadi MN, Chowdhury A, Pavey T, Trost SG. Laboratory-based and free-living algorithms for energy expenditure estimation in preschool children: a free-living evaluation. PLoS ONE. 2020;15(5):e0233229.","journal-title":"PLoS ONE"},{"issue":"11","key":"1930_CR44","doi-asserted-by":"publisher","first-page":"2183","DOI":"10.1088\/0967-3334\/35\/11\/2183","volume":"35","author":"SG Trost","year":"2014","unstructured":"Trost SG, Zheng Y, Wong W-K. Machine learning for activity recognition: hip versus wrist data. Physiol Meas. 2014;35(11):2183.","journal-title":"Physiol Meas"},{"key":"1930_CR45","first-page":"2","volume":"5","author":"S-S Learning","year":"2006","unstructured":"Learning S-S. Semi-supervised learning. CSZ2006 html. 2006;5:2.","journal-title":"CSZ2006 html"},{"issue":"4","key":"1930_CR46","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1177\/1948550617697177","volume":"8","author":"D Lakens","year":"2017","unstructured":"Lakens D. Equivalence tests: A practical primer for t tests, correlations, and meta-analyses. Social Psychol personality Sci. 2017;8(4):355\u201362.","journal-title":"Social Psychol personality Sci"},{"issue":"4","key":"1930_CR47","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1249\/MSS.0000000000001481","volume":"50","author":"PM Dixon","year":"2018","unstructured":"Dixon PM, Saint-Maurice PF, Kim Y, Hibbing P, Bai Y, Welk GJ. A primer on the use of equivalence testing for evaluating measurement agreement. Med Sci Sports Exerc. 2018;50(4):837.","journal-title":"Med Sci Sports Exerc"},{"issue":"4","key":"1930_CR48","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1123\/jmpb.2021-0021","volume":"4","author":"MW O\u2019Brien","year":"2021","unstructured":"O\u2019Brien MW. Implications and recommendations for equivalence testing in measures of movement behaviors: A scoping review. J Meas Phys Behav. 2021;4(4):353\u201362.","journal-title":"J Meas Phys Behav"},{"key":"1930_CR49","doi-asserted-by":"crossref","unstructured":"Cohen J. Statistical power analysis for the behavioral sciences. Routledge; 2013. https:\/\/www.taylorfrancis.com\/books\/mono\/10.4324\/9780203771587\/statistical-power-analysis-behavioral-sciences-jacob-cohen.","DOI":"10.4324\/9780203771587"},{"issue":"1","key":"1930_CR50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12966-019-0835-0","volume":"16","author":"P Crowley","year":"2019","unstructured":"Crowley P, Skotte J, Stamatakis E, et al. Comparison of physical behavior estimates from three different thigh-worn accelerometers brands: A proof-of-concept for the Prospective Physical Activity, Sitting, and Sleep consortium (ProPASS). Int J Behav Nutr Phys Activity. 2019;16(1):1\u20137.","journal-title":"Int J Behav Nutr Phys Activity"},{"key":"1930_CR51","unstructured":"World Health Oranization. Measuring physical activity in adults using wearable technologies: report of a scientific meeting. Geneva: World Health Organization; 2025."},{"issue":"1","key":"1930_CR52","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s12966-019-0835-0","volume":"16","author":"P Crowley","year":"2019","unstructured":"Crowley P, Skotte J, Stamatakis E, et al. Comparison of physical behavior estimates from three different thigh-worn accelerometers brands: a proof-of-concept for the Prospective Physical Activity, Sitting, and Sleep consortium (ProPASS). Int J Behav Nutr Phys Activity. 2019;16(1):65.","journal-title":"Int J Behav Nutr Phys Activity"},{"key":"1930_CR53","doi-asserted-by":"crossref","unstructured":"Franzese F, Hettiarachchi P, Holtermann A, Ahmadi M, Johansson PJ. Comparing Physical Activity Metrics From Different Placements of Thigh-Worn Accelerometers. J Meas Phys Behav. 2025;8(1).","DOI":"10.1123\/jmpb.2024-0043"},{"key":"1930_CR54","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1016\/j.pmcj.2014.05.006","volume":"15","author":"S Bhattacharya","year":"2014","unstructured":"Bhattacharya S, Nurmi P, Hammerla N, Pl\u00f6tz T. Using unlabeled data in a sparse-coding framework for human activity recognition. Pervasive Mob Comput. 2014;15:242\u201362.","journal-title":"Pervasive Mob Comput"},{"key":"1930_CR55","doi-asserted-by":"crossref","unstructured":"Guan D, Yuan W, Lee Y-K, Gavrilov A, Lee S. Activity recognition based on semi-supervised learning. IEEE. 2007:469\u201375.","DOI":"10.1109\/RTCSA.2007.17"},{"key":"1930_CR56","doi-asserted-by":"publisher","unstructured":"Strath SJ, Pfeiffer KA, Whitt-Glover MC. Accelerometer use with children, older adults, and adults with functional limitations. Med Sci Sports Exerc. Jan 2012;44(1 Suppl 1):S77\u201385. https:\/\/doi.org\/10.1249\/MSS.0b013e3182399eb1.","DOI":"10.1249\/MSS.0b013e3182399eb1"},{"key":"1930_CR57","doi-asserted-by":"publisher","first-page":"128337","DOI":"10.1109\/ACCESS.2020.3008951","volume":"8","author":"Z Liu","year":"2020","unstructured":"Liu Z, Wen T, Sun W, Zhang Q. Semi-supervised self-training feature weighted clustering decision tree and random forest. IEEE Access. 2020;8:128337\u201348.","journal-title":"IEEE Access"},{"issue":"1","key":"1930_CR58","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1038\/s41597-024-02956-3","volume":"11","author":"C Cheng","year":"2024","unstructured":"Cheng C, Messerschmidt L, Bravo I, et al. A general primer for data harmonization. Sci data. 2024;11(1):152.","journal-title":"Sci data"},{"key":"1930_CR59","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.inffus.2022.01.001","volume":"82","author":"Y Nan","year":"2022","unstructured":"Nan Y, Del Ser J, Walsh S, et al. Data harmonisation for information fusion in digital healthcare: A state-of-the-art systematic review, meta-analysis and future research directions. Inform Fusion. 2022;82:99\u2013122.","journal-title":"Inform Fusion"},{"issue":"3","key":"1930_CR60","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1093\/aje\/kwr194","volume":"174","author":"I Fortier","year":"2011","unstructured":"Fortier I, Doiron D, Burton P, Raina P. Invited commentary: consolidating data harmonization\u2014how to obtain quality and applicability? Am J Epidemiol. 2011;174(3):261\u20134.","journal-title":"Am J Epidemiol"},{"issue":"1","key":"1930_CR61","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1123\/jmpb.2019-0001","volume":"3","author":"M Pearce","year":"2020","unstructured":"Pearce M, Bishop TR, Sharp S, et al. Network harmonization of physical activity variables through indirect validation. J Meas Phys Behav. 2020;3(1):8\u201318.","journal-title":"J Meas Phys Behav"},{"key":"1930_CR62","doi-asserted-by":"publisher","unstructured":"El-Gazzar A, Thomas RM, van Wingen G. Harmonization techniques for machine learning studies using multi-site functional MRI data. bioRxiv. 2023:2023.06.14.544758. https:\/\/doi.org\/10.1101\/2023.06.14.544758.","DOI":"10.1101\/2023.06.14.544758"},{"key":"1930_CR63","doi-asserted-by":"publisher","first-page":"111956","DOI":"10.1016\/j.ejrad.2025.111956","volume":"184","author":"C Zhou","year":"2025","unstructured":"Zhou C, Zhou J, Lv Y, et al. The impact of the novel CovBat harmonization method on enhancing radiomics feature stability and machine learning model performance: A multi-center, multi-device study. Eur J Radiol Mar. 2025;184:111956. https:\/\/doi.org\/10.1016\/j.ejrad.2025.111956.","journal-title":"Eur J Radiol Mar"},{"issue":"1","key":"1930_CR64","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1038\/s41746-024-01062-3","volume":"7","author":"H Yuan","year":"2024","unstructured":"Yuan H, Chan S, Creagh AP, et al. Self-supervised learning for human activity recognition using 700,000 person-days of wearable data. NPJ Digit Med. 2024;7(1):91.","journal-title":"NPJ Digit Med"},{"key":"1930_CR65","doi-asserted-by":"publisher","first-page":"107478","DOI":"10.1016\/j.engappai.2023.107478","volume":"128","author":"A Logacjov","year":"2024","unstructured":"Logacjov A, Bach K. Self-supervised learning with randomized cross-sensor masked reconstruction for human activity recognition. Eng Appl Artif Intell. 2024;128:107478.","journal-title":"Eng Appl Artif Intell"},{"key":"1930_CR66","doi-asserted-by":"publisher","first-page":"106854","DOI":"10.1016\/j.cie.2020.106854","volume":"149","author":"L Li","year":"2020","unstructured":"Li L, Fan Y, Tse M, Lin K-Y. A review of applications in federated learning. Comput Ind Eng. 2020;149:106854.","journal-title":"Comput Ind Eng"},{"issue":"2","key":"1930_CR67","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3298981","volume":"10","author":"Q Yang","year":"2019","unstructured":"Yang Q, Liu Y, Chen T, Tong Y. Federated machine learning: Concept and applications. ACM Trans Intell Syst Technol (TIST). 2019;10(2):1\u201319.","journal-title":"ACM Trans Intell Syst Technol (TIST)"}],"container-title":["International Journal of Behavioral Nutrition and Physical Activity"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12966-026-01930-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12966-026-01930-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12966-026-01930-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T03:21:41Z","timestamp":1782962501000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12966-026-01930-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"references-count":67,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1930"],"URL":"https:\/\/doi.org\/10.1186\/s12966-026-01930-z","relation":{},"ISSN":["1479-5868"],"issn-type":[{"value":"1479-5868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]},"assertion":[{"value":"26 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was approved by the Sydney Local Health District (ETH02815, ETH00138). Before participation, written consent was obtained from each participant.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"ES is a paid consultant and holds equity in Complement 1, a US-based company whose products and services relate to promotion of physical activity and other lifestyle behaviours. All other authors disclose no conflict of interest for this work.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"68"}}