{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:36:56Z","timestamp":1775230616420,"version":"3.50.1"},"reference-count":37,"publisher":"MDPI AG","issue":"24","license":[{"start":{"date-parts":[[2020,12,15]],"date-time":"2020-12-15T00:00:00Z","timestamp":1607990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"publisher","award":["1193766"],"award-info":[{"award-number":["1193766"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004412","name":"Human Frontier Science Program","doi-asserted-by":"publisher","award":["LT001080\/2017"],"award-info":[{"award-number":["LT001080\/2017"]}],"id":[{"id":"10.13039\/100004412","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Activity recognition can provide useful information about an older individual\u2019s activity level and encourage older people to become more active to live longer in good health. This study aimed to develop an activity recognition algorithm for smartphone accelerometry data of older people. Deep learning algorithms, including convolutional neural network (CNN) and long short-term memory (LSTM), were evaluated in this study. Smartphone accelerometry data of free-living activities, performed by 53 older people (83.8 \u00b1 3.8 years; 38 male) under standardized circumstances, were classified into lying, sitting, standing, transition, walking, walking upstairs, and walking downstairs. A 1D CNN, a multichannel CNN, a CNN-LSTM, and a multichannel CNN-LSTM model were tested. The models were compared on accuracy and computational efficiency. Results show that the multichannel CNN-LSTM model achieved the best classification results, with an 81.1% accuracy and an acceptable model and time complexity. Specifically, the accuracy was 67.0% for lying, 70.7% for sitting, 88.4% for standing, 78.2% for transitions, 88.7% for walking, 65.7% for walking downstairs, and 68.7% for walking upstairs. The findings indicated that the multichannel CNN-LSTM model was feasible for smartphone-based activity recognition in older people.<\/jats:p>","DOI":"10.3390\/s20247195","type":"journal-article","created":{"date-parts":[[2020,12,15]],"date-time":"2020-12-15T21:11:02Z","timestamp":1608066662000},"page":"7195","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Deep Learning for Activity Recognition in Older People Using a Pocket-Worn Smartphone"],"prefix":"10.3390","volume":"20","author":[{"given":"Yashi","family":"Nan","sequence":"first","affiliation":[{"name":"Graduate School of Biomedical Engineering, University of New South Wales, Sydney 2033, Australia"},{"name":"Neuroscience Research Australia, University of New South Wales, Sydney 2031, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1637-1079","authenticated-orcid":false,"given":"Nigel H.","family":"Lovell","sequence":"additional","affiliation":[{"name":"Graduate School of Biomedical Engineering, University of New South Wales, Sydney 2033, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2630-5449","authenticated-orcid":false,"given":"Stephen J.","family":"Redmond","sequence":"additional","affiliation":[{"name":"Graduate School of Biomedical Engineering, University of New South Wales, Sydney 2033, Australia"},{"name":"School of Electrical and Electronic Engineering, University College Dublin, Dublin, Ireland"}]},{"given":"Kejia","family":"Wang","sequence":"additional","affiliation":[{"name":"Graduate School of Biomedical Engineering, University of New South Wales, Sydney 2033, Australia"}]},{"given":"Kim","family":"Delbaere","sequence":"additional","affiliation":[{"name":"Neuroscience Research Australia, University of New South Wales, Sydney 2031, Australia"},{"name":"School of Public Health and Community Medicine, University of New South Wales, Sydney 2052, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0902-8440","authenticated-orcid":false,"given":"Kimberley S.","family":"van Schooten","sequence":"additional","affiliation":[{"name":"Neuroscience Research Australia, University of New South Wales, Sydney 2031, Australia"},{"name":"School of Public Health and Community Medicine, University of New South Wales, Sydney 2052, Australia"}]}],"member":"1968","published-online":{"date-parts":[[2020,12,15]]},"reference":[{"key":"ref_1","first-page":"26","article-title":"Physical activity is medicine for older adults Postgrad","volume":"90","author":"Taylor","year":"2014","journal-title":"Med. J."},{"key":"ref_2","unstructured":"Australian Government Department of Health Population Health (2020, July 29). Australia\u2019s Physical Activity and Sedentary Behaviour Guidelines and the Australian 24-Hour Movement Guidelines, Available online: https:\/\/www1.health.gov.au\/internet\/main\/publishing.nsf\/Content\/health-pubhlth-strateg-phys-act-guidelines."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Australian Institute of Health Welfare (2018). Insufficient Physical Activity, Australia\u2019s Health 2018.","DOI":"10.21820\/23987073.2018.2.80"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Sozen, H. (2016). Activity Tracking and Improved Health Outcomes. Fitness Medicine, IntechOpen.","DOI":"10.5772\/62558"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2269","DOI":"10.1088\/0967-3334\/35\/11\/2269","article-title":"A comparison of activity classification in younger and older cohorts using a smartphone","volume":"35","author":"Wang","year":"2014","journal-title":"Physiol. Meas."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1109\/JBHI.2018.2820179","article-title":"Physical Activity Classification for Elderly People in Free-Living Conditions","volume":"23","author":"Awais","year":"2018","journal-title":"IEEE J. Biomed. Heal. Inform."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Papagiannaki, A., Zacharaki, E., Kalouris, G., Kalogiannis, S., Deltouzos, K., Ellul, J., and Megalooikonomou, V. (2019). Recognizing Physical Activity of Older People from Wearable Sensors and Inconsistent Data. Sensors, 19.","DOI":"10.3390\/s19040880"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Sansrimahachai, W., and Toahchoodee, M. (2016, January 22\u201325). Mobile-phone based immobility tracking system for elderly care. Proceedings of the 2016 IEEE Region 10 Conference (TENCON), Singapore.","DOI":"10.1109\/TENCON.2016.7848718"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Tahavori, F., Stack, E., Agarwal, V., Burnett, M., Ashburn, A., Hoseinitabatabaei, S.A., and Harwin, W. (2017, January 14\u201317). Physical activity recognition of elderly people and people with parkinson\u2019s (PwP) during standard mobility tests using wearable sensors. Proceedings of the 2017 International Smart Cities Conference (ISC2), Wuxi, China.","DOI":"10.1109\/ISC2.2017.8090858"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.patrec.2018.02.010","article-title":"Deep learning for sensor-based activity recognition: A survey","volume":"119","author":"Wang","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Rueda, F.M., Grzeszick, R., Fink, G.A., Feldhorst, S., and Hompel, M.T. (2018). Convolutional Neural Networks for Human Activity Recognition Using Body-Worn Sensors. Informatics, 5.","DOI":"10.3390\/informatics5020026"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1123\/JAPA.2013-0103","article-title":"Assessing Physical Activity in Older Adults: Required Days of Trunk Accelerometer Measurements for Reliable Estimation","volume":"23","author":"Rispens","year":"2015","journal-title":"J. Aging Phys. Act."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1016\/j.asoc.2017.09.027","article-title":"Real-time human activity recognition from accelerometer data using Convolutional Neural Networks","volume":"62","author":"Ignatov","year":"2018","journal-title":"Appl. Soft Comput."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Ord\u00f3\u00f1ez, F.J., and Roggen, D. (2016). Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition. Sensors, 16.","DOI":"10.3390\/s16010115"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.1109\/JSEN.2017.2782492","article-title":"Human Activity Classification in Smartphones Using Accelerometer and Gyroscope Sensors","volume":"18","author":"Jain","year":"2018","journal-title":"IEEE Sensors J."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/978-981-10-1536-6_5","article-title":"Elderly People and Their Attitude Towards Mobile Phones and Their Applications\u2014A Review Study","volume":"Volume 393","author":"Park","year":"2016","journal-title":"Advanced Multimedia and Ubiquitous Engineering"},{"key":"ref_17","unstructured":"Brownlee, J. (2020, July 21). A gentle Introduction to Imbalanced Classification, Machine Learning Mastery, 22 December 2019. Available online: https:\/\/machinelearningmastery.com\/what-is-imbalanced-classification\/."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"6585","DOI":"10.1016\/j.eswa.2011.12.043","article-title":"Analysis of preprocessing vs. cost-sensitive learning for imbalanced classification. Open problems on intrinsic data characteristics","volume":"39","author":"Herrera","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_19","unstructured":"(2020, June 02). JetBrains, Pycharm. Available online: https:\/\/www.jetbrains.com\/pycharm\/."},{"key":"ref_20","unstructured":"Anaconda, Inc. (2020, June 02). Anaconda Software Distribution. Available online: https:\/\/anaconda.com."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Gholamrezaii, M., and Almodarresi, S.M.T. (May, January 30). Human Activity Recognition Using 2D Convolutional Neural Networks. Proceedings of the 2019 27th Iranian Conference on Electrical Engineering (ICEE), Yazd, Iran.","DOI":"10.1109\/IranianCEE.2019.8786578"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1602","DOI":"10.1109\/TBME.2016.2614230","article-title":"Wavelet-Based Sit-To-Stand Detection and Assessment of Fall Risk in Older People Using a Wearable Pendant Device","volume":"64","author":"Ejupi","year":"2017","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_23","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv, Available online: http:\/\/arxiv.org\/abs\/1704.04861."},{"key":"ref_24","unstructured":"Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., and Garnett, R. (2018). Constructing fast network through deconstruction of convolution. Advances in Neural Information Processing Systems 31, Curran Associates, Inc."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ignatov, A., Timofte, R., Chou, W., Wang, K., Wu, M., Hartley, T., and Van Gool, L. (2018). AI Benchmark: Running Deep Neural Networks on Android Smartphones. arXiv, Available online: http:\/\/arxiv.org\/abs\/1810.01109.","DOI":"10.1007\/978-3-030-11021-5_19"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"12777","DOI":"10.1007\/s11042-019-08453-9","article-title":"Dropout vs. batch normalization: An empirical study of their impact to deep learning","volume":"79","author":"Garbin","year":"2020","journal-title":"Tools Appl."},{"key":"ref_27","unstructured":"Brownlee, J. (2020, July 27). How to Avoid Overfitting in Deep Learning Neural Eetworks, Machine Learning Mastery. Available online: https:\/\/machinelearningmastery.com\/introduction-to-regularization-to-reduce-overfitting-and-improve-generalization-error\/."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1007\/978-3-642-16355-5_42","article-title":"Activity recognition on an accelerometer embedded mobile phone with varying positions and orientations","volume":"Volume 6406","author":"Yu","year":"2010","journal-title":"Ubiquitous Intelligence and Computing"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"6008","DOI":"10.1109\/JSEN.2016.2574124","article-title":"Quaternion-Based Complementary Filter for Attitude Determination of a Smartphone","volume":"16","author":"Lovell","year":"2016","journal-title":"IEEE Sens. J."},{"key":"ref_30","unstructured":"Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., and Liu, Y. (2020). Deep learning for sensor-based human activity recognition: Overview, challenges and opportunities. arXiv, Available online: http:\/\/arxiv.org\/abs\/2001.07416."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"26783","DOI":"10.3390\/s151026783","article-title":"Can Smartwatches Replace Smartphones for Posture Tracking?","volume":"15","author":"Mortazavi","year":"2015","journal-title":"Sensors"},{"key":"ref_32","first-page":"26","article-title":"Hyperparameter optimization for machine learning models based on Bayesian optimization","volume":"17","author":"Wu","year":"2019","journal-title":"J. Electron. Sci. Technol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1271","DOI":"10.1007\/s11517-010-0701-3","article-title":"Accelerometer\u2019s position independent physical activity recognition system for long-term activity monitoring in the elderly","volume":"48","author":"Khan","year":"2010","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Voicu, R.-A., Dobre, C., B\u0103jenaru, L., and Ciobanu, R.-I. (2019). Human Physical Activity Recognition Using Smartphone Sensors. Sensors, 19.","DOI":"10.3390\/s19030458"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/s11556-009-0051-z","article-title":"Effect of age and physical activity level on functional fitness in older adults","volume":"6","author":"Tuna","year":"2009","journal-title":"Eur. Rev. Aging Phys. Act."},{"key":"ref_36","unstructured":"(2020, July 27). Gait and Balance Disorders in Older Adults\u2014American Family Physician. Available online: https:\/\/www.aafp.org\/afp\/2010\/0701\/p61.html."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Rokni, S.A., Nourollahi, M., and Ghasemzadeh, H. (2018). Personalized human activity recognition using convolutional neural networks. arXiv, Available online: http:\/\/arxiv.org\/abs\/1801.08252.","DOI":"10.1609\/aaai.v32i1.12185"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/24\/7195\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:45:30Z","timestamp":1760179530000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/24\/7195"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,15]]},"references-count":37,"journal-issue":{"issue":"24","published-online":{"date-parts":[[2020,12]]}},"alternative-id":["s20247195"],"URL":"https:\/\/doi.org\/10.3390\/s20247195","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,15]]}}}