{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T20:58:23Z","timestamp":1760821103422,"version":"build-2065373602"},"reference-count":35,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2019,10,17]],"date-time":"2019-10-17T00:00:00Z","timestamp":1571270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Few methods for classifying physical activity from accelerometer data have been tested using an independent dataset for cross-validation, and even fewer using multiple independent datasets. The aim of this study was to evaluate whether unsupervised machine learning was a viable approach for the development of a reusable clustering model that was generalisable to independent datasets. We used two labelled adult laboratory datasets to generate a k-means clustering model. To assess its generalised application, we applied the stored clustering model to three independent labelled datasets: two laboratory and one free-living. Based on the development labelled data, the ten clusters were collapsed into four activity categories: sedentary, standing\/mixed\/slow ambulatory, brisk ambulatory, and running. The percentages of each activity type contained in these categories were 89%, 83%, 78%, and 96%, respectively. In the laboratory independent datasets, the consistency of activity types within the clusters dropped, but remained above 70% for the sedentary clusters, and 85% for the running and ambulatory clusters. Acceleration features were similar within each cluster across samples. The clusters created reflected activity types known to be associated with health and were reasonably robust when applied to diverse independent datasets. This suggests that an unsupervised approach is potentially useful for analysing free-living accelerometer data.<\/jats:p>","DOI":"10.3390\/s19204504","type":"journal-article","created":{"date-parts":[[2019,10,17]],"date-time":"2019-10-17T11:07:59Z","timestamp":1571310479000},"page":"4504","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Towards a Portable Model to Discriminate Activity Clusters from Accelerometer Data"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9340-9168","authenticated-orcid":false,"given":"Petra","family":"Jones","sequence":"first","affiliation":[{"name":"Leicester Diabetes Centre, University Hospitals of Leicester, Leicester LE5 4PW, UK"},{"name":"Diabetes Research Centre, University of Leicester, Leicester General Hospital, Gwendolen Road, Leicester LE5 4PW, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1474-1734","authenticated-orcid":false,"given":"Evgeny M.","family":"Mirkes","sequence":"additional","affiliation":[{"name":"Department of Mathematics, ATT 912, Attenborough Building, University of Leicester, University Road, Leicester LE5 4PW, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Yates","sequence":"additional","affiliation":[{"name":"Diabetes Research Centre, University of Leicester, Leicester General Hospital, Gwendolen Road, Leicester LE5 4PW, UK"},{"name":"NIHR Leicester Biomedical Research Centre, Leicester General Hospital, Gwendolen Road, Leicester LE5 4PW, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charlotte L.","family":"Edwardson","sequence":"additional","affiliation":[{"name":"Diabetes Research Centre, University of Leicester, Leicester General Hospital, Gwendolen Road, Leicester LE5 4PW, UK"},{"name":"NIHR Leicester Biomedical Research Centre, Leicester General Hospital, Gwendolen Road, Leicester LE5 4PW, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mike","family":"Catt","sequence":"additional","affiliation":[{"name":"Institute of Neuroscience, Henry Wellcome Building, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne NE2 4HH, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Melanie J.","family":"Davies","sequence":"additional","affiliation":[{"name":"Leicester Diabetes Centre, University Hospitals of Leicester, Leicester LE5 4PW, UK"},{"name":"Diabetes Research Centre, University of Leicester, Leicester General Hospital, Gwendolen Road, Leicester LE5 4PW, UK"},{"name":"NIHR Leicester Biomedical Research Centre, Leicester General Hospital, Gwendolen Road, Leicester LE5 4PW, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2343-7099","authenticated-orcid":false,"given":"Kamlesh","family":"Khunti","sequence":"additional","affiliation":[{"name":"Leicester Diabetes Centre, University Hospitals of Leicester, Leicester LE5 4PW, UK"},{"name":"NIHR Leicester Biomedical Research Centre, Leicester General Hospital, Gwendolen Road, Leicester LE5 4PW, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1463-697X","authenticated-orcid":false,"given":"Alex V.","family":"Rowlands","sequence":"additional","affiliation":[{"name":"Diabetes Research Centre, University of Leicester, Leicester General Hospital, Gwendolen Road, Leicester LE5 4PW, UK"},{"name":"NIHR Leicester Biomedical Research Centre, Leicester General Hospital, Gwendolen Road, Leicester LE5 4PW, UK"},{"name":"Alliance for research in Exercise, Nutrition and Activity (ARENA), Sansom Institute for Health Research, Division of Health Sciences, University of South Australia, Adelaide SA 5001, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2019,10,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/S0140-6736(12)61031-9","article-title":"Impact of physical inactivity on the world\u2019s major non-communicable diseases","volume":"380","author":"Lee","year":"2012","journal-title":"Lancet"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Doherty, A., Jackson, D., Hammerla, N., Pl\u00f6tz, T., Olivier, P., Granat, M.H., White, T., Van Hees, V.T., Trenell, M.I., and Owen, C.G. (2017). Large scale population assessment of physical activity using wrist worn accelerometers: The UK Biobank study. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0169649"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1161\/01.HYP.0000184225.05629.51","article-title":"Effects of endurance training on blood pressure, blood pressure-regulating mechanisms and cardiovascular risk factors","volume":"46","author":"Cornelissen","year":"2005","journal-title":"Hypertension"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e004473","DOI":"10.1161\/JAHA.112.004473","article-title":"Pharmacological and lifestyle interventions to prevent or delay type 2 diabetes in people with impaired glucose tolerance: Systematic review and meta-analysis","volume":"2","author":"Cornelissen","year":"2013","journal-title":"J. Am. Heart Assoc."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1136\/bmj.39063.689375.55","article-title":"Impact of physical inactivity on the world\u2019s major non-communicable diseases","volume":"334","author":"Gillies","year":"2007","journal-title":"BMJ"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e002014","DOI":"10.1161\/JAHA.115.002014","article-title":"Effects of exercise training on cardiorespiratory fitness and biomarkers of cardiometabolic health: A systematic review and meta-analysis of randomized controlled trials","volume":"4","author":"Lin","year":"2015","journal-title":"J. Am. Heart Assoc."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1152\/japplphysiol.00760.2017","article-title":"Cross-validation and out-of-sample testing of physical activity intensity predictions using a wrist-worn accelerometer","volume":"124","author":"Montoye","year":"2018","journal-title":"J. Appl. Physiol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1249\/MSS.0000000000000841","article-title":"Objective assessment of physical activity: Classifiers for public health","volume":"48","author":"Kerr","year":"2016","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Van Kuppevelt, D., Heywood, J., Hamer, M., Sabia, S., Fitzsimons, E., and van Hees, V. (2018). Segmenting accelerometer data from daily life with unsupervised machine learning. PLoS ONE, 14.","DOI":"10.1101\/263046"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1502","DOI":"10.1111\/biom.12892","article-title":"Physical activity classification with dynamic discriminative methods","volume":"74","author":"Ray","year":"2018","journal-title":"Biometrics"},{"key":"ref_11","first-page":"1042","article-title":"Impact of study design on development and evaluation of an activity type classifier","volume":"114","author":"Golubic","year":"2012","journal-title":"J. Appl. Physiol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Rowlands, A., Plekhanova, T., Yates, T., Mirkes, E., Davies, M., Khunti, K., and Edwardson, C. (2019). Providing a basis for harmonisation of accelerometer physical activity outcomes across epidemiological datasets. J. Meas. Phys. Behav., in press.","DOI":"10.1123\/jmpb.2018-0073"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Van Hees, V.T., Renstr\u00f6m, F., Wright, A., Gradmark, A., Catt, M., Chen, K.Y., L\u00f6f, M., Bluck, L., Pomeroy, J., and Wareham, N.J. (2011). Estimation of daily energy expenditure in pregnant and non-pregnant women using a wrist-worn tri-axial accelerometer. PLoS ONE, 6.","DOI":"10.1371\/journal.pone.0022922"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Bakrania, K., Yates, T., Rowlands, A.V., Esliger, D.W., Bunnewell, S., Sanders, J., Davies, M., Khunti, K., and Edwardson, C.L. (2016). Intensity thresholds on raw acceleration data: Euclidean norm minus one (ENMO) and mean amplitude deviation (MAD) approaches. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0164045"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1249\/MSS.0b013e31820513be","article-title":"Validation of the GENEA accelerometer","volume":"43","author":"Esliger","year":"2011","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1016\/j.jsams.2012.05.013","article-title":"Calibration of the GENEA accelerometer for assessment of physical activity intensity in children","volume":"16","author":"Phillips","year":"2013","journal-title":"J. Sci. Med. Sport"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1249\/MSS.0000000000001435","article-title":"Accelerometer assessed physical activity in epidemiology: Are monitors equivalent?","volume":"50","author":"Rowlands","year":"2018","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_18","unstructured":"(2019, October 17). Python Software Foundation. Available online: https:\/\/www.python.org\/."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least squares quantization in PCM","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/BF02289263","article-title":"Who belongs in the family?","volume":"18","author":"Thorndike","year":"1953","journal-title":"Psychometrika"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"A graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"Comput. Appl. Math."},{"key":"ref_22","first-page":"1","article-title":"A dendrite method for cluster analysis","volume":"3","author":"Calinsky","year":"1972","journal-title":"Commun. Stat."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s00357-010-9049-5","article-title":"Intelligent choice of the number of clusters in k-means clustering: An experimental study with different cluster spreads","volume":"27","author":"Mirkin","year":"2010","journal-title":"J. Classif."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Moore, D., and McCowan, I. (2007, January 22\u201326). Unsupervised clustering of free-living human activities using ambulatory accelerometry. Proceedings of the 29th Annual International Conference of the IEEE EMBS Cit\u00e9 Internationale, Lyon, France.","DOI":"10.1109\/IEMBS.2007.4353437"},{"key":"ref_25","unstructured":"Arthur, D., and Vassilvitskii, S. (2007, January 7\u20139). K-means++: The advantages of careful seeding. Proceedings of the eighteenth annual ACM-SIAM symposium on discrete algorithms, New Orleans, LA, USA."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"31314","DOI":"10.3390\/s151229858","article-title":"Physical human activity recognition using wearable sensors","volume":"15","author":"Attal","year":"2015","journal-title":"Sensors"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Billingsley, J., and Brett, P. (2008). Unsupervised habitual activity detection in accelerometer data. Mechatronics and Machine Vision in Practice 3, Springer.","DOI":"10.1007\/978-3-540-74027-8"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1249\/MSS.0000000000000224","article-title":"Assessing sedentary behaviour with the GENEActiv: Introducing the sedentary sphere","volume":"46","author":"Rowlands","year":"2014","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1816","DOI":"10.1249\/MSS.0000000000000289","article-title":"Age-group comparability of raw accelerometer output from wrist- and hip-worn monitors","volume":"46","author":"Hildebrand","year":"2014","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1132","DOI":"10.1016\/j.jsams.2019.06.016","article-title":"A data-driven, meaningful, easy to interpret, standardised accelerometer outcome variable for global surveillance","volume":"22","author":"Rowlands","year":"2019","journal-title":"J. Sci. Med. Sport"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Aggarwal, C., and Reddy, C. (2014). Data Clustering: Algorithms and Applications, CRC Press.","DOI":"10.1201\/b15410"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"14754","DOI":"10.3390\/s131114754","article-title":"Comparison of raw acceleration from the GENEA and ActiGraph GT3X+ activity monitors","volume":"13","author":"John","year":"2013","journal-title":"Sensors"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1249\/MSS.0000000000000394","article-title":"Comparison of measured acceleration output from accelerometery-based activity monitors","volume":"47","author":"Rowlands","year":"2015","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1249\/MSS.0000000000000813","article-title":"Sedentary Sphere: Wrist-worn accelerometer-brand independent posture classification","volume":"48","author":"Rowlands","year":"2016","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1186\/s12966-017-0514-y","article-title":"Low physical activity, high television viewing and poor sleep duration cluster in overweight and obese adults: A cross-sectional study of 398,984 participants from the UK Biobank","volume":"14","author":"Cassidy","year":"2017","journal-title":"Int. J. Behav. Nutr. Phys. Act."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/20\/4504\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:27:07Z","timestamp":1760189227000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/20\/4504"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,17]]},"references-count":35,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2019,10]]}},"alternative-id":["s19204504"],"URL":"https:\/\/doi.org\/10.3390\/s19204504","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2019,10,17]]}}}