{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,21]],"date-time":"2026-11-21T17:39:26Z","timestamp":1795282766346,"version":"4.10.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,1,21]],"date-time":"2023-01-21T00:00:00Z","timestamp":1674259200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,1,21]],"date-time":"2023-01-21T00:00:00Z","timestamp":1674259200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Nowadays, work-related musculoskeletal disorders have a drastic impact on a large part of the world population. In particular, low-back pain counts as the leading cause of absence from work in the industrial sector. Robotic exoskeletons have great potential to improve industrial workers\u2019 health and life quality. Nonetheless, current solutions are often limited by sub-optimal control systems. Due to the dynamic environment in which they are used, failure to adapt to the wearer and the task may be limiting exoskeleton adoption in occupational scenarios. In this scope, we present a deep-learning-based approach exploiting inertial sensors to provide industrial exoskeletons with human activity recognition and adaptive payload compensation. Inertial measurement units are easily wearable or embeddable in any industrial exoskeleton. We exploited Long-Short Term Memory networks both to perform human activity recognition and to classify the weight of lifted objects up to 15 kg. We found a median F1 score of\n                    <jats:inline-formula>\n                      <jats:alternatives>\n                        <jats:tex-math>$$90.80\\%$$<\/jats:tex-math>\n                        <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                          <mml:mrow>\n                            <mml:mn>90.80<\/mml:mn>\n                            <mml:mo>%<\/mml:mo>\n                          <\/mml:mrow>\n                        <\/mml:math>\n                      <\/jats:alternatives>\n                    <\/jats:inline-formula>\n                    (activity recognition) and\n                    <jats:inline-formula>\n                      <jats:alternatives>\n                        <jats:tex-math>$$87.14\\%$$<\/jats:tex-math>\n                        <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                          <mml:mrow>\n                            <mml:mn>87.14<\/mml:mn>\n                            <mml:mo>%<\/mml:mo>\n                          <\/mml:mrow>\n                        <\/mml:math>\n                      <\/jats:alternatives>\n                    <\/jats:inline-formula>\n                    (payload estimation) with subject-specific models trained and tested on 12 (6M-6F) young healthy volunteers. We also succeeded in evaluating the applicability of this approach with an in-lab real-time test in a simulated target scenario. These high-level algorithms may be useful to fully exploit the potential of powered exoskeletons to achieve symbiotic human\u2013robot interaction.\n                  <\/jats:p>","DOI":"10.1038\/s41598-023-28195-x","type":"journal-article","created":{"date-parts":[[2023,1,21]],"date-time":"2023-01-21T06:02:49Z","timestamp":1674280969000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":72,"title":["IMU-based human activity recognition and payload classification for low-back exoskeletons"],"prefix":"10.1038","volume":"13","author":[{"given":"Mattia","family":"Pesenti","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giovanni","family":"Invernizzi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julie","family":"Mazzella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Bocciolone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandra","family":"Pedrocchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marta","family":"Gandolla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,1,21]]},"reference":[{"key":"28195_CR1","unstructured":"Eurofound. Sixth European Working Conditions Survey. Overview Report (2017 Update) (2017)."},{"key":"28195_CR2","doi-asserted-by":"publisher","first-page":"1545","DOI":"10.1016\/S0140-6736(16)31678-6","volume":"388","author":"T Vos","year":"2016","unstructured":"Vos, T. et al. Global, regional, and national incidence, prevalence, and years lived with disability for 310 diseases and injuries, 1990\u20132015: a systematic analysis for the global burden of disease study 2015. Lancet 388, 1545\u20131602 (2016).","journal-title":"Lancet"},{"key":"28195_CR3","first-page":"593","volume":"7","author":"A Garg","year":"1992","unstructured":"Garg, A. & Moore, J. Epidemiology of low-back pain in industry. Occup. Med. (Philadelphia, PA) 7, 593\u2013608 (1992).","journal-title":"Occup. Med. (Philadelphia, PA)"},{"key":"28195_CR4","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/s10926-012-9375-z","volume":"23","author":"P Coenen","year":"2013","unstructured":"Coenen, P. et al. Cumulative low back load at work as a risk factor of low back pain: A prospective cohort study. J. Occup. Rehabil. 23, 11\u201318 (2013).","journal-title":"J. Occup. Rehabil."},{"key":"28195_CR5","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1080\/00140139.2015.1081988","volume":"59","author":"MP De Looze","year":"2016","unstructured":"De Looze, M. P., Bosch, T., Krause, F., Stadler, K. S. & O\u2019sullivan, L. W. Exoskeletons for industrial application and their potential effects on physical work load. Ergonomics 59, 671\u2013681 (2016).","journal-title":"Ergonomics"},{"key":"28195_CR6","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1080\/00140139.2020.1870162","volume":"64","author":"T Kermavnar","year":"2021","unstructured":"Kermavnar, T., de Vries, A. W., de Looze, M. P. & O\u2019Sullivan, L. W. Effects of industrial back-support exoskeletons on body loading and user experience: An updated systematic review. Ergonomics 64, 685\u2013711 (2021).","journal-title":"Ergonomics"},{"key":"28195_CR7","doi-asserted-by":"publisher","first-page":"808","DOI":"10.3390\/s21030808","volume":"21","author":"M Pesenti","year":"2021","unstructured":"Pesenti, M., Antonietti, A., Gandolla, M. & Pedrocchi, A. Towards a functional performance validation standard for industrial low-back exoskeletons: State of the art review. Sensors 21, 808 (2021).","journal-title":"Sensors"},{"key":"28195_CR8","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1017\/S0266462317000460","volume":"33","author":"D Hill","year":"2017","unstructured":"Hill, D., Holloway, C. S., Ramirez, D. Z. M., Smitham, P. & Pappas, Y. What are user perspectives of exoskeleton technology? A literature review. Int. J. Technol. Assess. Health Care 33, 160\u2013167 (2017).","journal-title":"Int. J. Technol. Assess. Health Care"},{"key":"28195_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12984-021-00963-8","volume":"18","author":"JT Meyer","year":"2021","unstructured":"Meyer, J. T., Gassert, R. & Lambercy, O. An analysis of usability evaluation practices and contexts of use in wearable robotics. J. NeuroEng. Rehabil. 18, 1\u201315 (2021).","journal-title":"J. NeuroEng. Rehabil."},{"key":"28195_CR10","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1080\/24725838.2019.1684399","volume":"7","author":"T McFarland","year":"2019","unstructured":"McFarland, T. & Fischer, S. Considerations for industrial use: A systematic review of the impact of active and passive upper limb exoskeletons on physical exposures. IISE Trans. Occup. Ergon. Hum. Factors 7, 322\u2013347 (2019).","journal-title":"IISE Trans. Occup. Ergon. Hum. Factors"},{"key":"28195_CR11","first-page":"933","volume":"3","author":"RM Singh","year":"2012","unstructured":"Singh, R. M., Chatterji, S. & Kumar, A. Trends and challenges in EMG based control scheme of exoskeleton robots\u2014A review. Int. J. Sci. Eng. Res 3, 933\u2013940 (2012).","journal-title":"Int. J. Sci. Eng. Res"},{"key":"28195_CR12","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.robot.2014.08.015","volume":"73","author":"F Giovacchini","year":"2015","unstructured":"Giovacchini, F. et al. A light-weight active orthosis for hip movement assistance. Robot. Auton. Syst. 73, 123\u2013134 (2015).","journal-title":"Robot. Auton. Syst."},{"key":"28195_CR13","doi-asserted-by":"publisher","first-page":"17","DOI":"10.3389\/fnbot.2018.00017","volume":"12","author":"B Chen","year":"2018","unstructured":"Chen, B., Grazi, L., Lanotte, F., Vitiello, N. & Crea, S. A real-time lift detection strategy for a hip exoskeleton. Front. Neurorobot. 12, 17 (2018).","journal-title":"Front. Neurorobot."},{"key":"28195_CR14","doi-asserted-by":"crossref","unstructured":"Poliero, T., Mancini, L., Caldwell, D.\u00a0G. & Ortiz, J. Enhancing back-support exoskeleton versatility based on human activity recognition. in 2019 Wearable Robotics Association Conference (WearRAcon). 86\u201391 (IEEE, 2019).","DOI":"10.1109\/WEARRACON.2019.8719625"},{"key":"28195_CR15","doi-asserted-by":"publisher","first-page":"28","DOI":"10.3389\/frobt.2015.00028","volume":"2","author":"M Vrigkas","year":"2015","unstructured":"Vrigkas, M., Nikou, C. & Kakadiaris, I. A. A review of human activity recognition methods. Front. Robot. AI 2, 28 (2015).","journal-title":"Front. Robot. AI"},{"key":"28195_CR16","doi-asserted-by":"publisher","first-page":"172988141986318","DOI":"10.1177\/1729881419863186","volume":"16","author":"X Wang","year":"2019","unstructured":"Wang, X. et al. Multi-connection load compensation and load information calculation for an upper-limb exoskeleton based on a six-axis force\/torque sensor. Int. J. Adv. Robot. Syst. 16, 1729881419863186 (2019).","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"28195_CR17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0192938","volume":"13","author":"D Totah","year":"2018","unstructured":"Totah, D. et al. Low-back electromyography (EMG) data-driven load classification for dynamic lifting tasks. PloS One 13, e0192938 (2018).","journal-title":"PloS One"},{"key":"28195_CR18","doi-asserted-by":"publisher","first-page":"53","DOI":"10.3389\/frobt.2018.00053","volume":"5","author":"S Toxiri","year":"2018","unstructured":"Toxiri, S. et al. Rationale, implementation and evaluation of assistive strategies for an active back-support exoskeleton. Front. Robot. AI 5, 53 (2018).","journal-title":"Front. Robot. AI"},{"key":"28195_CR19","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1080\/24725838.2019.1573770","volume":"7","author":"R Hensel","year":"2019","unstructured":"Hensel, R. & Keil, M. Subjective evaluation of a passive industrial exoskeleton for lower-back support: A field study in the automotive sector. IISE Trans. Occup. Ergon. Hum. Factors 7, 213\u2013221 (2019).","journal-title":"IISE Trans. Occup. Ergon. Hum. Factors"},{"key":"28195_CR20","doi-asserted-by":"crossref","unstructured":"Siedl, S.\u00a0M., Wolf, M. & Mara, M. Exoskeletons in the supermarket: Influences of comfort, strain relief and task-technology fit on retail workers\u2019 post-trial intention to use. in Companion of the 2021 ACM\/IEEE International Conference on Human-Robot Interaction. 397\u2013401 (2021).","DOI":"10.1145\/3434074.3447200"},{"key":"28195_CR21","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1177\/0018720819889534","volume":"62","author":"SA Elprama","year":"2020","unstructured":"Elprama, S. A. et al. Social processes: What determines industrial workers\u2019 intention to use exoskeletons?. Hum. Factors 62, 337\u2013350 (2020).","journal-title":"Hum. Factors"},{"key":"28195_CR22","doi-asserted-by":"publisher","first-page":"123260","DOI":"10.1109\/ACCESS.2021.3109238","volume":"9","author":"Y Tirupachuri","year":"2021","unstructured":"Tirupachuri, Y. et al. Online non-collocated estimation of payload and articular stress for real-time human ergonomy assessment. IEEE Access 9, 123260\u2013123279 (2021).","journal-title":"IEEE Access"},{"key":"28195_CR23","doi-asserted-by":"crossref","unstructured":"Aziz, S., Khan, M.\u00a0U., Aamir, F. & Javid, M.\u00a0A. Electromyography (EMG) data-driven load classification using empirical mode decomposition and feature analysis. in 2019 International Conference on Frontiers of Information Technology (FIT). 272\u20132725 (IEEE, 2019).","DOI":"10.1109\/FIT47737.2019.00058"},{"key":"28195_CR24","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TITB.2005.856864","volume":"10","author":"DM Karantonis","year":"2006","unstructured":"Karantonis, D. M., Narayanan, M. R., Mathie, M., Lovell, N. H. & Celler, B. G. Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring. IEEE Trans. Inf. Technol. Biomed. 10, 156\u2013167 (2006).","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"28195_CR25","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F. et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"28195_CR26","unstructured":"Abadi, M. et\u00a0al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Software available from tensorflow.org (2015)."},{"key":"28195_CR27","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997).","journal-title":"Neural Comput."},{"key":"28195_CR28","unstructured":"Lipton, Z.\u00a0C., Berkowitz, J. & Elkan, C. A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019 (2015)."},{"key":"28195_CR29","unstructured":"TensorFlow. Tensorflow Lite | ml for Mobile and Edge Devices. https:\/\/www.tensorflow.org\/lite\/ (2022)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-28195-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-28195-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-28195-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,21]],"date-time":"2023-01-21T06:07:51Z","timestamp":1674281271000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-28195-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,21]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["28195"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-28195-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,21]]},"assertion":[{"value":"18 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"M.G. and A.P. hold shares of Agade srl, a start-up company active in the field of industrial exoskeletons. The other authors do not have anything to disclose.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1184"}}