CoChat
Sign Up
PreprintCited by 8Context-Aware Activity Recognition SystemsPhysical Activity and HealthTime Series Analysis and Forecasting

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

A Novel ViT-BILSTM Model for Physical Activity Intensity classification in Adults using Gravity-based Acceleration

Open access
Wang, Lin, Luo, Zizhang, Zhang, Tianle·2024·BMC Biomedical Engineering
DOI 10.21203/rs.3.rs-4696057/v1PMC PMC11786420

Preprint — published as 10.1186/s42490-025-00088-2 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Aim The aim of this study is to apply a novel hybrid framework incorporating a Vision Transformer (ViT) and bidirectional long short-term memory (Bi-LSTM) model for classifying physical activity intensity (PAI) in adults using gravity-based acceleration. Additionally, it further investigates how PAI and temporal window (TW) impacts the model’ s accuracy. Method This research used the Capture-24 dataset, consisting of raw accelerometer data from 151 participants aged 18 to 91. Gravity-based acceleration was utilised to generate images encoding various PAIs. These images were subsequently analysed using the ViT-BiLSTM model, with results presented in confusion matrices and compared with baseline models. The model's robustness was evaluated through temporal stability testing and examination of accuracy and loss curves. Result The ViT-BiLSTM model excelled in PAI classification task, achieving an overall accuracy of 98.5% ±1.48% across five TWs-98.7% for 1s, 98.1% for 5s, 98.2% for 10s, 99% for 15s, and 98.65% for 30s of TW. The model consistently exhibited superior accuracy in predicting sedentary (98.9%±1%) compared to light physical activity (98.2%±2%) and moderate-to-vigorous physical activity (98.2%± 3%). ANOVA showed no significant accuracy variation across PAIs (F = 2.18, p = 0.13) and TW (F = 0.52, p = 0.72). Accuracy and loss curves show the model consistently improves its performance across epochs, demonstrating its excellent robustness. Conclusion This study demonstrates the ViT-BiLSTM model’s efficacy in classifying PAI using gravity-based acceleration, with performance remaining consistent across diverse TWs and intensities. However, PAI and TW could result in slight variations in the model’s performance. Future research should concern and investigate the impact of gravity-based acceleration on PAI thresholds, which may influence model's robustness and reliability.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.21203/rs.3.rs-4696057/v1

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 32

  1. Ahmadi, M. N., Hamer, M., Gill, J. M. R., Murphy, M., Sanders, J. P., Doherty, A., & Stamatakis, E. (2023). Brief bouts of device-measured intermittent lifestyle physical activity and its association with major adverse cardiovascular events and mortality in people who do not exercise: a prospective cohort study. Lancet Public Health, 8(10), e800-e810. https://doi.org/10.1016/S2468-2667(23)00183-4 · DOI · Paper page
  2. Boyer, W. R. (2016). Accelerometer-derived total activity counts, bouted minutes of moderate to vigorous activity, and insulin resistance: NHANES 2003–2006. Preventing chronic disease, 13. · DOI
  3. Chen, H., Cui, J., Zhang, Y., & Zhang, Y. (2022). VIT and Bi-LSTM for Micro-Expressions Recognition. 2022 IEEE 5th International Conference on Information Systems and Computer Aided Education (ICISCAE), · DOI
  4. Chong, J., Tjurin, P., Niemela, M., Jamsa, T., & Farrahi, V. (2021). Machine-learning models for activity class prediction: A comparative study of feature selection and classification algorithms. Gait Posture, 89, 45–53. https://doi.org/10.1016/j.gaitpost.2021.06.017 · DOI
  5. Crouter, S. E., Clowers, K. G., & Bassett, D. R., Jr. (2006). A novel method for using accelerometer data to predict energy expenditure. J Appl Physiol (1985), 100(4), 1324–1331. https://doi.org/10.1152/japplphysiol.00818.2005 · DOI · Paper page
  6. Fairclough, Taylor, S., Rowlands, A. V., Boddy, L. M., & Noonan, R. J. (2019). Average acceleration and intensity gradient of primary school children and associations with indicators of health and well-being [Journal Article; Randomized Controlled Trial]. Journal of sports sciences, 37(18), 2159-2167. https://doi.org/10.1080/02640414.2019.1624313 · DOI
  7. Farrahi, V., Muhammad, U., Rostami, M., & Oussalah, M. (2023). AccNet24: A deep learning framework for classifying 24-hour activity behaviours from wrist-worn accelerometer data under free-living environments. Int J Med Inform, 172, 105004. https://doi.org/10.1016/j.ijmedinf.2023.105004 · DOI
  8. Freedson, P. S., Melanson, E., & Sirard, J. (1998). Calibration of the computer science and applications, inc. accelerometer. Medicine and science in sports and exercise, 30(5), 777–781. · DOI · Paper page
  9. Gershuny, J., Harms, T., Doherty, A., Thomas, E., Milton, K., Kelly, P., & Foster, C. (2020). Testing self-report time-use diaries against objective instruments in real time. Sociological Methodology, 50(1), 318–349. · DOI · Paper page
  10. Hildebrand, M., VT, V. H., Hansen, B. H., & Ekelund, U. (2014). Age group comparability of raw accelerometer output from wrist-and hip-worn monitors. Medicine and science in sports and exercise, 46(9), 1816–1824. · DOI · Paper page
  11. Marshall, Z., Mackintosh, K., Gregory, J., & McNarry, M. (2022). Using compositional analysis to explore the relationship between physical activity and cardiovascular health in children and adolescents with and without type 1 diabetes. Pediatric Diabetes, 23(1), 115–125. https://doi.org/doi:10.1111/pedi.13288 · DOI
  12. Miatke, A., Olds, T., Maher, C., Fraysse, F., Mellow, M. L., Smith, A. E., Pedisic, Z., Grgic, J., & Dumuid, D. (2023). The association between reallocations of time and health using compositional data analysis: a systematic scoping review with an interactive data exploration interface. International Journal of Behavioral Nutrition and Physical Activity, 20(1), 127. · DOI
  13. Migueles, J. H., Aadland, E., Andersen, L. B., Brond, J. C., Chastin, S. F., Hansen, B. H., Konstabel, K., Kvalheim, O. M., McGregor, D. E., Rowlands, A. V., Sabia, S., van Hees, V. T., Walmsley, R., Ortega, F. B., & External review, g. (2022). GRANADA consensus on analytical approaches to assess associations with accelerometer-determined physical behaviours (physical activity, sedentary behaviour and sleep) in epidemiological studies. Br J Sports Med, 56(7), 376–384. https://doi.org/10.1136/bjsports-2020-103604 · DOI
  14. Muazu Musa, R., Abdul Majeed, A. P. P., Taha, Z., Abdullah, M. R., Husin Musawi Maliki, A. B., & Azura Kosni, N. (2019). The application of Artificial Neural Network and k-Nearest Neighbour classification models in the scouting of high-performance archers from a selected fitness and motor skill performance parameters. SCIENCE & SPORTS, 34(4), e241-e249. https://doi.org/10.1016/j.scispo.2019.02.006 · DOI
  15. Nagayoshi, S., Oshima, Y., Ando, T., Aoyama, T., Nakae, S., Usui, C., Kumagai, S., & Tanaka, S. (2019). Validity of estimating physical activity intensity using a triaxial accelerometer in healthy adults and older adults. BMJ Open Sport Exerc Med, 5(1), e000592. https://doi.org/10.1136/bmjsem-2019-000592 · DOI
  16. Nawaratne, R., Alahakoon, D., De Silva, D., O'Halloran, P. D., Montoye, A. H., Staley, K., Nicholson, M., & Kingsley, M. I. (2021). Deep Learning to Predict Energy Expenditure and Activity Intensity in Free Living Conditions using Wrist-specific Accelerometry. J Sports Sci, 39(6), 683–690. https://doi.org/10.1080/02640414.2020.1841394 · DOI
  17. Ng, J. Y. Y., Zhang, J. H., Hui, S. S., Jiang, G., Yau, F., Cheng, J., & Ha, A. S. (2024). Development of a multi-wear-site, deep learning-based physical activity intensity classification algorithm using raw acceleration data. PLoS One, 19(3), e0299295. https://doi.org/10.1371/journal.pone.0299295 · DOI
  18. Pate, R. R. (1993). Physical activity assessment in children and adolescents. Crit Rev Food Sci Nutr, 33(4–5), 321–326. https://doi.org/10.1080/10408399309527627 · DOI
  19. Rowlands. (2018). Moving Forward With Accelerometer-Assessed Physical Activity: Two Strategies to Ensure Meaningful, Interpretable, and Comparable Measures. Pediatr Exerc Sci, 30(4), 450–456. https://doi.org/10.1123/pes.2018-0201 · DOI · Paper page
  20. Rowlands, Dawkins, Maylor, B., Edwardson, C. L., Fairclough, S. J., Davies, M. J., Harrington, D. M., Khunti, K., & Yates, T. (2019). Enhancing the value of accelerometer-assessed physical activity: meaningful visual comparisons of data-driven translational accelerometer metrics. Sports Medicine - Open, 5(1), 47. https://doi.org/http://dx.doi.org/10.1186/s40798-019-0225-9 · DOI
  21. Rowlands, Edwardson, C. L., Davies, M. J., Khunti, K., Harrington, D. M., & Yates, T. (2018). Beyond Cut Points: Accelerometer Metrics that Capture the Physical Activity Profile. Med Sci Sports Exerc, 50(6), 1323–1332. https://doi.org/10.1249/MSS.0000000000001561 · DOI
  22. Rowlands, Sherar, L. B., Fairclough, S. J., Yates, T., Edwardson, C. L., Harrington, D. M., & Stiles, V. H. (2019). A data-driven, meaningful, easy to interpret, standardised accelerometer outcome variable for global surveillance. J Sci Med Sport, 22(10), 1132–1138. https://doi.org/10.1016/j.jsams.2019.06.016 · DOI
  23. Rowlands, A. V. (2007). Accelerometer assessment of physical activity in children: an update. Pediatric exercise science, 19(3), 252–266. · DOI
  24. Tan, K. S., Lim, K. M., Lee, C. P., & Kwek, L. C. (2022). Bidirectional long short-term memory with temporal dense sampling for human action recognition. Expert Systems with Applications, 210, 118484. · DOI
  25. Thornton, C. B., Kolehmainen, N., & Nazarpour, K. (2023). Using unsupervised machine learning to quantify physical activity from accelerometry in a diverse and rapidly changing population. PLOS Digit Health, 2(4), e0000220. https://doi.org/10.1371/journal.pdig.0000220 · DOI
  26. van Kuppevelt, D., Heywood, J., Hamer, M., Sabia, S., Fitzsimons, E., & van Hees, V. (2019). Segmenting accelerometer data from daily life with unsupervised machine learning. PLoS One, 14(1), e0208692. https://doi.org/10.1371/journal.pone.0208692 · DOI · Paper page
  27. Vela, D., Sharp, A., Zhang, R., Nguyen, T., Hoang, A., & Pianykh, O. S. (2022). Temporal quality degradation in AI models. Scientific reports, 12(1), 11654. · DOI
  28. Verswijveren, S., Lamb, K. E., Martin-Fernandez, J. A., Winkler, E., Leech, R. M., Timperio, A., Salmon, J., Daly, R. M., Cerin, E., Dunstan, D. W., Telford, R. M., Telford, R. D., Olive, L. S., & Ridgers, N. D. (2022). Using compositional data analysis to explore accumulation of sedentary behavior, physical activity and youth health. J Sport Health Sci, 11(2), 234–243. https://doi.org/10.1016/j.jshs.2021.03.004 · DOI
  29. Walmsley, R., Chan, S., Smith-Byrne, K., Ramakrishnan, R., Woodward, M., Rahimi, K., Dwyer, T., Bennett, D., & Doherty, A. (2022). Reallocation of time between device-measured movement behaviours and risk of incident cardiovascular disease. BRITISH JOURNAL OF SPORTS MEDICINE, 56(18), 1008–1017. · DOI · Paper page
  30. Willetts, M., Hollowell, S., Aslett, L., Holmes, C., & Doherty, A. (2018). Statistical machine learning of sleep and physical activity phenotypes from sensor data in 96,220 UK Biobank participants. Scientific reports, 8(1), 7961. · DOI · Paper page
  31. Yuan, H., Plekhanova, T., Walmsley, R., Reynolds, A. C., Maddison, K. J., Bucan, M., Gehrman, P., Rowlands, A., Ray, D. W., Bennett, D., McVeigh, J., Straker, L., Eastwood, P., Kyle, S. D., & Doherty, A. (2024). Self-supervised learning of accelerometer data provides new insights for sleep and its association with mortality. NPJ Digit Med, 7(1), 86. https://doi.org/10.1038/s41746-024-01065-0 · DOI
  32. Zhao, Y., Dong, F., Sun, T., Ju, Z., Yang, L., Shan, P., Li, L., Lv, X., & Lian, C. (2024). Image expression of time series data of wearable IMU sensor and fusion classification of gymnastics action. Expert Systems with Applications, 238. https://doi.org/10.1016/j.eswa.2023.121978 · DOI

Metadata

Authors
Wang, L., Luo, Z., & Zhang, T.
Affiliations
  • University of Exeter (GB)
  • Yangtze University (CN)
  • University of Liverpool (GB)
Corresponding author
Wang, Lin
ORCID
Venue
BMC Biomedical Engineering
Publisher
Springer Science and Business Media LLC
Published
2024-08-06
Volume
7
Issue
1
Pages
2-2
ISSN
2524-4426 (ISSN-L)
DOI
10.21203/rs.3.rs-4696057/v1
PMC
PMC11786420
OpenAlex
W4407024896
Cited by
8
References
1
Citations by year
2026: 5 · 2025: 3
FWCI
2.79
Type
journal article
Language
en
Open access
Licence
Locations
  • BMC Biomedical Engineering (publishedVersion, cc-by)
  • Research Square (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
China Scholarship Council
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Physical Activity and Health
  • Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
Keywords
physical activity intensity classification, vision transformer, bidirectional LSTM, hybrid deep learning model, accelerometer data, sedentary behavior, moderate-to-vigorous physical activity, light physical activity

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review