{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:15:15Z","timestamp":1792790115163,"version":"4.5.0"},"reference-count":39,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Mirella & Lino Saputo Foundation","id":[{"id":"https:\/\/ror.org\/02gqq6w73","id-type":"ROR","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/02gqq6w73","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Step-counting remains difficult in irregular walking, where step timing and signal patterns are less consistent than in controlled walking. We propose a step-counting model that uses step timing annotations as temporal supervision during training. Each step timestamp is expanded into a short temporal label interval, and a U-Net is used to localize step events because its dense prediction structure is well suited to temporal localization. The model is trained to estimate both where steps occur in the window and how many steps the window contains. The final count is obtained by summing the predicted values over time and dividing by the label width. On the Clemson wrist-worn dataset, the model achieves MAPE values of 4.61%, 9.90%, and 15.78% under regular, semi-regular, and irregular walking, respectively. Compared with classical step-detection algorithms and reproduced CNN, WaveNet, and LSTM baselines, the proposed model shows substantially lower error under irregular walking. On OxWalk, the model achieves 13.06% MAPE using only OxWalk training data, reaching performance comparable to fine-tuned Stepcount SSL, which relies on large-scale self-supervised pretraining. These results suggest that temporal step supervision improves robustness under irregular walking and can reduce dependence on large-scale external pretraining.<\/jats:p>","DOI":"10.3390\/s26196235","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T09:38:16Z","timestamp":1790847496000},"page":"6235","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Temporal Step Supervision for Robust Step Counting from Wearable Accelerometers"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8605-5932","authenticated-orcid":false,"given":"Yan","family":"Zhang","sequence":"first","affiliation":[{"name":"Centre de Recherche du CHUM, Montr\u00e9al, QC H2X 0A9, Canada"},{"name":"D\u00e9partement d\u2019Informatique et de Recherche Op\u00e9rationnelle, Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, QC H3C 3J7, Canada"},{"name":"Mila\u2013Quebec AI Institute, Montr\u00e9al, QC H2S 3H1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5290-6486","authenticated-orcid":false,"given":"Paula","family":"Lago","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Concordia University, Montr\u00e9al, QC H3G 1M8, Canada"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5412-2597","authenticated-orcid":false,"given":"Quoc Dinh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Centre de Recherche du CHUM, Montr\u00e9al, QC H2X 0A9, Canada"},{"name":"D\u00e9partement de M\u00e9decine, Facult\u00e9 de M\u00e9decine, Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, QC H3C 3J7, Canada"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"key":"ref_1","unstructured":"World Health Organization (2020). WHO Guidelines on Physical Activity and Sedentary Behaviour, World Health Organization."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1270","DOI":"10.1249\/MSS.0000000000001939","article-title":"Physical Activity, All-Cause and Cardiovascular Mortality, and Cardiovascular Disease","volume":"51","author":"Kraus","year":"2019","journal-title":"Med. Sci. Sport. Exerc."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.1007\/s40279-016-0663-1","article-title":"Step Counting: A Review of Measurement Considerations and Health-Related Applications","volume":"47","author":"Bassett","year":"2017","journal-title":"Sport. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1206","DOI":"10.1249\/MSS.0000000000001932","article-title":"Daily Step Counts for Measuring Physical Activity Exposure and Its Relation to Health","volume":"51","author":"Kraus","year":"2019","journal-title":"Med. Sci. Sport. Exerc."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1186\/s12966-020-00978-9","article-title":"Systematic Review of the Prospective Association of Daily Step Counts with Risk of Mortality, Cardiovascular Disease, and Dysglycemia","volume":"17","author":"Hall","year":"2020","journal-title":"Int. J. Behav. Nutr. Phys. Act."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1151","DOI":"10.1001\/jama.2020.1382","article-title":"Association of Daily Step Count and Step Intensity With Mortality Among US Adults","volume":"323","author":"Troiano","year":"2020","journal-title":"JAMA"},{"key":"ref_7","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_8","doi-asserted-by":"crossref","first-page":"e5191","DOI":"10.2196\/jmir.5191","article-title":"Cardiac Patients\u2019 Walking Activity Determined by a Step Counter in Cardiac Telerehabilitation: Data from the Intervention Arm of a Randomized Controlled Trial","volume":"18","author":"Thorup","year":"2016","journal-title":"J. Med. Internet Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1249\/MSS.0b013e3182351913","article-title":"Evaluation of Activity Monitors in Controlled and Free-Living Environments","volume":"44","author":"Feito","year":"2012","journal-title":"Med. Sci. Sport. Exerc."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1186\/s12966-022-01350-9","article-title":"A Catalog of Validity Indices for Step Counting Wearable Technologies during Treadmill Walking: The CADENCE-Adults Study","volume":"19","author":"Gould","year":"2022","journal-title":"Int. J. Behav. Nutr. Phys. Act."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1249\/MSS.0000000000001569","article-title":"Video-Recorded Validation of Wearable Step Counters under Free-Living Conditions","volume":"50","author":"Toth","year":"2018","journal-title":"Med. Sci. Sport. Exerc."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Mattfeld, R., Jesch, E., and Hoover, A. (2021). Evaluating Pedometer Algorithms on Semi-Regular and Unstructured Gaits. Sensors, 21.","DOI":"10.3390\/s21134260"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.gaitpost.2016.12.014","article-title":"Comparison of Tri-Axial Accelerometers Step-Count Accuracy in Slow Walking Condition","volume":"53","author":"Feng","year":"2017","journal-title":"Gait Posture"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"830","DOI":"10.2340\/16501977-1993","article-title":"Capturing Step Counts at Slow Walking Speeds in Older Adults: Comparison of Ankle and Waist Placement of Measuring Device","volume":"47","author":"Simpson","year":"2015","journal-title":"J. Rehabil. Med."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2333721418781126","DOI":"10.1177\/2333721418781126","article-title":"Accuracy of Objective Physical Activity Monitors in Measuring Steps in Older Adults","volume":"4","author":"Hergenroeder","year":"2018","journal-title":"Gerontol. Geriatr. Med."},{"key":"ref_16","first-page":"7720","article-title":"Design and Implementation of Practical Step Detection Algorithm for Wrist-Worn Devices","volume":"16","author":"Cho","year":"2016","journal-title":"IEEE Sens. J."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Huang, B., Qi, G., Yang, X., Zhao, L., and Zou, H. (2016, January 12\u201316). Exploiting Cyclic Features of Walking for Pedestrian Dead Reckoning with Unconstrained Smartphones. Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Heidelberg, Germany.","DOI":"10.1145\/2971648.2971742"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Kang, X., Huang, B., and Qi, G. (2018). A Novel Walking Detection and Step Counting Algorithm Using Unconstrained Smartphones. Sensors, 18.","DOI":"10.3390\/s18010297"},{"key":"ref_19","unstructured":"Chen, Z. (2018). An LSTM Recurrent Network for Step Counting. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Shao, W., Luo, H., Zhao, F., Wang, C., Crivello, A., and Tunio, M.Z. (2018, January 20\u201324). DePedo: Anti Periodic Negative-Step Movement Pedometer with Deep Convolutional Neural Networks. Proceedings of the 2018 IEEE International Conference on Communications, Kansas City, MO, USA.","DOI":"10.1109\/ICC.2018.8422308"},{"key":"ref_21","unstructured":"Pillai, A., Lea, H., Khan, F., and Dennis, G. (2020). Personalized Step Counting Using Wearable Sensors: A Domain Adapted LSTM Network Approach. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Khan, S.S., and Abedi, A. (2022). Step Counting with Attention-Based LSTM. arXiv.","DOI":"10.1109\/SSCI51031.2022.10022210"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Luu, L., Pillai, A., Lea, H., Buendia, R., Khan, F.M., and Dennis, G. (2022). Accurate Step Count with Generalized and Personalized Deep Learning on Accelerometer Data. Sensors, 22.","DOI":"10.3390\/s22113989"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1038\/s41746-024-01062-3","article-title":"Self-Supervised Learning for Human Activity Recognition Using 700,000 Person-Days of Wearable Data","volume":"7","author":"Yuan","year":"2024","journal-title":"npj Digit. Med."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1945","DOI":"10.1249\/MSS.0000000000003478","article-title":"Self-Supervised Machine Learning to Characterize Step Counts from Wrist-Worn Accelerometers in the UK Biobank","volume":"56","author":"Small","year":"2024","journal-title":"Med. Sci. Sport. Exerc."},{"key":"ref_26","first-page":"1","article-title":"Full-Featured Pedometer Design Realized with 3-Axis Digital Accelerometer","volume":"44","author":"Zhao","year":"2010","journal-title":"Analog Dialogue"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3453","DOI":"10.1109\/JSEN.2017.2685999","article-title":"Fast and Accurate Smartphone-Based Step Counting for Indoor Localization","volume":"17","author":"Gu","year":"2017","journal-title":"IEEE Sens. J."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Rai, A., Chintalapudi, K.K., Padmanabhan, V.N., and Sen, R. (2012, January 22\u201326). Zee: Zero-Effort Crowdsourcing for Indoor Localization. Proceedings of the 18th Annual International Conference on Mobile Computing and Networking (MobiCom \u201912), Istanbul, Turkey.","DOI":"10.1145\/2348543.2348580"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1136\/bjsports-2020-103147","article-title":"Recommendations for Determining the Validity of Consumer Wearable and Smartphone Step Count: Expert Statement and Checklist of the INTERLIVE Network","volume":"55","author":"Johnston","year":"2021","journal-title":"Br. J. Sport. Med."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1093\/biostatistics\/kxz033","article-title":"Adaptive Empirical Pattern Transformation (ADEPT) with Application to Walking Stride Segmentation","volume":"22","author":"Karas","year":"2021","journal-title":"Biostatistics"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1038\/s41746-022-00745-z","article-title":"A \u201cOne-Size-Fits-Most\u201d Walking Recognition Method for Smartphones, Smartwatches, and Wearable Accelerometers","volume":"6","author":"Straczkiewicz","year":"2023","journal-title":"npj Digit. Med."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2182","DOI":"10.1080\/02640414.2022.2147134","article-title":"Stepping up with GGIR: Validity of step cadence derived from wrist-worn research-grade accelerometers using the Verisense step count algorithm","volume":"40","author":"Rowlands","year":"2022","journal-title":"J. Sport. Sci."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"115532","DOI":"10.1016\/j.asoc.2026.115532","article-title":"Entropy-Informed Deep Residual Network for Nonlinear EEG Dynamics in Fine-Grained Driver State Recognition","volume":"201","author":"Chen","year":"2026","journal-title":"Appl. Soft Comput."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhang, B., Li, Z., Ma, Q., Zhang, J., Xiang, Z., and Jiang, D. (2026). Silhouette-Based Cross-View Motion Gait Recognition via a Multi-Scale Temporal Difference Unit. Electronics, 15.","DOI":"10.3390\/electronics15122512"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Sudlow, C., Gallacher, J., Allen, N., Beral, V., Burton, P., Danesh, J., Downey, P., Elliott, P., Green, J., and Landray, M. (2015). UK Biobank: An Open Access Resource for Identifying the Causes of a Wide Range of Complex Diseases of Middle and Old Age. PLoS Med., 12.","DOI":"10.1371\/journal.pmed.1001779"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention, Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_37","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019, January 8\u201314). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_38","unstructured":"Kingma, D.P., and Ba, J. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6235\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T04:21:36Z","timestamp":1791951696000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6235"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":39,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196235"],"URL":"https:\/\/doi.org\/10.3390\/s26196235","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]}}}