Classification of human walking context using a single-point accelerometer.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
06 Feb 2024
06 Feb 2024
Historique:
received:
22
09
2023
accepted:
29
01
2024
medline:
7
2
2024
pubmed:
7
2
2024
entrez:
6
2
2024
Statut:
epublish
Résumé
Real-world walking data offers rich insights into a person's mobility. Yet, daily life variations can alter these patterns, making the data challenging to interpret. As such, it is essential to integrate context for the extraction of meaningful information from real-world movement data. In this work, we leveraged the relationship between the characteristics of a walking bout and context to build a classification algorithm to distinguish between indoor and outdoor walks. We used data from 20 participants wearing an accelerometer on the thigh over a week. Their walking bouts were isolated and labeled using GPS and self-reporting data. We trained and validated two machine learning models, random forest and ensemble Support Vector Machine, using a leave-one-participant-out validation scheme on 15 subjects. The 5 remaining subjects were used as a testing set to choose a final model. The chosen model achieved an accuracy of 0.941, an F1-score of 0.963, and an AUROC of 0.931. This validated model was then used to label the walks from a different dataset with 15 participants wearing the same accelerometer. Finally, we characterized the differences between indoor and outdoor walks using the ensemble of the data. We found that participants walked significantly faster, longer, and more continuously when walking outdoors compared to indoors. These results demonstrate how movement data alone can be used to obtain accurate information on important contextual factors. These factors can then be leveraged to enhance our understanding and interpretation of real-world movement data, providing deeper insights into a person's health.
Identifiants
pubmed: 38321039
doi: 10.1038/s41598-024-53143-8
pii: 10.1038/s41598-024-53143-8
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
3039Informations de copyright
© 2024. The Author(s).
Références
Morris, J. N. & Hardman, A. E. Walking to health. Sports Med. 23, 306–332. https://doi.org/10.2165/00007256-199723050-00004 (1997).
doi: 10.2165/00007256-199723050-00004
pubmed: 9181668
Murtagh, E. M., Murphy, M. H. & Boone-Heinonen, J. Walking: The first steps in cardiovascular disease prevention. Curr. Opin. Cardiol. 25, 490–496. https://doi.org/10.1097/HCO.0b013e32833ce972 (2010).
doi: 10.1097/HCO.0b013e32833ce972
pubmed: 20625280
pmcid: 3098122
Wunderlich, F. M. Walking and rhythmicity: Sensing urban space. J. Urban Des. 13, 125–139. https://doi.org/10.1080/13574800701803472 (2008).
doi: 10.1080/13574800701803472
Lee, I. M. & Buchner, D. M. The importance of walking to public health. Med. Sci. Sports Exerc. 40, 512–518. https://doi.org/10.1249/MSS.0b013e31817c65d0 (2008).
doi: 10.1249/MSS.0b013e31817c65d0
Ramanujam, E., Perumal, T. & Padmavathi, S. Human activity recognition with smartphone and wearable sensors using deep learning techniques: A review. IEEE Sens. J. 21, 13029–13040. https://doi.org/10.1109/JSEN.2021.3069927 (2021).
doi: 10.1109/JSEN.2021.3069927
Ann, O. C. & Theng, L. B. Human activity recognition: A review. In Proceedings—4th IEEE International Conference on Control System, Computing and Engineering, ICCSCE 2014 389–393. https://doi.org/10.1109/ICCSCE.2014.7072750 (2014).
Vrigkas, M., Nikou, C. & Kakadiaris, I. A. A review of human activity recognition methods. Front. Robot. AI 2, 1–28. https://doi.org/10.3389/frobt.2015.00028 (2015).
doi: 10.3389/frobt.2015.00028
Lee, S. M., Yoon, S. M. & Cho, H. Human activity recognition from accelerometer data using convolutional neural network. In 2017 IEEE International Conference on Big Data and Smart Computing, BigComp 2017 131–134. https://doi.org/10.1109/BIGCOMP.2017.7881728 (2017).
Albert, M. V., Toledo, S., Shapiro, M. & Kording, K. Using mobile phones for activity recognition in Parkinson’s patients. Front. Neurol. 1, 1–7. https://doi.org/10.3389/fneur.2012.00158 (2012).
doi: 10.3389/fneur.2012.00158
Prelipcean, A. C., Gidófalvi, G. & Susilo, Y. O. Transportation mode detection-an in-depth review of applicability and reliability. Transp. Rev. 37, 442–464. https://doi.org/10.1080/01441647.2016.1246489 (2017).
doi: 10.1080/01441647.2016.1246489
Nikolíc, M. & Bierlaire, M. Review of transportation mode detection approaches based on smartphone data. In 17th Swiss Transport Research Conference 1–20 (2017).
Kowalsky, D., Rebula, J., Ojeda, L., Adamczyk, P. & Kuo, A. Human walking in the real world: Interactions between terrain type, gait parameters, and energy expenditure. BioRxiv 3, 890434. https://doi.org/10.1101/2019.12.29.890434 (2019).
doi: 10.1101/2019.12.29.890434
Hashmi, M. Z. U. H., Riaz, Q., Hussain, M. & Shahzad, M. What lies beneath one’s feet? Terrain classification using inertial data of human walk. Appl. Sci. 9, 3099. https://doi.org/10.3390/app9153099 (2019).
doi: 10.3390/app9153099
Kim, J., Colabianchi, N., Wensman, J. & Gates, D. H. Wearable sensors quantify mobility in people with lower limb amputation during daily life. IEEE Trans. Neural Syst. Rehabil. Eng. 28, 1282–1291. https://doi.org/10.1109/TNSRE.2020.2990824 (2020).
doi: 10.1109/TNSRE.2020.2990824
pubmed: 32356753
Twardzik, E. et al. What features of the built environment matter most for mobility? Using wearable sensors to capture real-time outdoor environment demand on gait performance. Gait Posture 68, 437–442. https://doi.org/10.1016/j.gaitpost.2018.12.028 (2019).
doi: 10.1016/j.gaitpost.2018.12.028
pubmed: 30594872
Twardzik, E. et al. The relationship between environmental exposures and post-stroke physical activity. Am. J. Prev. Med. 63, 251–261. https://doi.org/10.1016/j.amepre.2022.01.026 (2022).
doi: 10.1016/j.amepre.2022.01.026
pubmed: 35361506
pmcid: 9310088
Baroudi, L., Barton, K., Cain, S. M. & Shorter, K. A. Understanding the influence of context on real-world walking energetics. J. Exp. Biol. 1, 1. https://doi.org/10.1242/jeb.xxxxxx (2023).
doi: 10.1242/jeb.xxxxxx
Quiroz, J. C., Geangu, E. & Yong, M. H. Emotion recognition using smart watch sensor data: Mixed-design study. JMIR Mental Health 5, 10153. https://doi.org/10.2196/10153 (2018).
doi: 10.2196/10153
Zhang, Z., Song, Y., Cui, L., Liu, X. & Zhu, T. Emotion recognition based on customized smart bracelet with built-in accelerometer. PeerJ 1–14, 2016. https://doi.org/10.7717/peerj.2258 (2016).
doi: 10.7717/peerj.2258
Michalak, J. et al. Embodiment of sadness and depression-gait patterns associated with dysphoric mood. Psychosom. Med. 71, 580–587. https://doi.org/10.1097/PSY.0b013e3181a2515c (2009).
doi: 10.1097/PSY.0b013e3181a2515c
pubmed: 19414617
Procter, D. S. et al. An open-source tool to identify active travel from hip-worn accelerometer, GPS and GIS data. Int. J. Behav. Nutr. Phys. Act. 15, 1–10. https://doi.org/10.1186/s12966-018-0724-y (2018).
doi: 10.1186/s12966-018-0724-y
Brondeel, R., Pannier, B. & Chaix, B. Using GPS, GIS, and accelerometer data to predict transportation modes. Med. Sci. Sports Exerc. 47, 2669–2675. https://doi.org/10.1249/MSS.0000000000000704 (2015).
doi: 10.1249/MSS.0000000000000704
pubmed: 25984892
Siła-Nowicka, K. et al. Analysis of human mobility patterns from GPS trajectories and contextual information. Int. J. Geogr. Inf. Sci. 30, 881–906. https://doi.org/10.1080/13658816.2015.1100731 (2016).
doi: 10.1080/13658816.2015.1100731
Cleland, I. et al. Evaluation of prompted annotation of activity data recorded from a smart phone. Sensors (Switzerland) 14, 15861–15879. https://doi.org/10.3390/s140915861 (2014).
doi: 10.3390/s140915861
Chang, Y. J., Paruthi, G., Wu, H. Y., Lin, H. Y. & Newman, M. W. An investigation of using mobile and situated crowdsourcing to collect annotated travel activity data in real-word settings. Int. J. Hum. Comput. Stud. 102, 81–102. https://doi.org/10.1016/j.ijhcs.2016.11.001 (2017).
doi: 10.1016/j.ijhcs.2016.11.001
Doherty, A. R. et al. Using wearable cameras to categorise type and context of accelerometer-identified episodes of physical activity. Int. J. Behav. Nutr. Phys. Act. 10, 1–11. https://doi.org/10.1186/1479-5868-10-22 (2013).
doi: 10.1186/1479-5868-10-22
Diaz, J. P., Da Silva, R. L., Zhong, B., Huang, H. H. & Lobaton, E. Visual terrain identification and surface inclination estimation for improving human locomotion with a lower-limb prosthetic. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, Vol. 2018-July, 1817–1820. https://doi.org/10.1109/EMBC.2018.8512614 (2018).
Hu, B., Dixon, P. C., Jacobs, J. V., Dennerlein, J. T. & Schiffman, J. M. Machine learning algorithms based on signals from a single wearable inertial sensor can detect surface- and age-related differences in walking. J. Biomech. 71, 37–42. https://doi.org/10.1016/j.jbiomech.2018.01.005 (2018).
doi: 10.1016/j.jbiomech.2018.01.005
pubmed: 29452755
Ali, M., Elbatt, T. & Youssef, M. SenseIO: Realistic ubiquitous indoor outdoor detection system using smartphones. IEEE Sens. J. 18, 3684–3693. https://doi.org/10.1109/JSEN.2018.2810193 (2018).
doi: 10.1109/JSEN.2018.2810193
Esmaeili Kelishomi, A., Garmabaki, A. H., Bahaghighat, M. & Dong, J. Mobile user indoor–outdoor detection through physical daily activities. Sensors 19, 511. https://doi.org/10.3390/s19030511 (2019).
doi: 10.3390/s19030511
pubmed: 30691148
pmcid: 6387420
Baroudi, L. et al. Investigating walking speed variability of young adults in the real world. Gait Posture 98, 69–77. https://doi.org/10.1016/j.gaitpost.2022.08.012 (2022).
doi: 10.1016/j.gaitpost.2022.08.012
pubmed: 36057208
Wu, Y., Petterson, J. L., Bray, N. W., Kimmerly, D. S. & O’Brien, M. W. Validity of the activPAL monitor to measure stepping activity and activity intensity: A systematic review. Gait Posture 97, 165–173. https://doi.org/10.1016/j.gaitpost.2022.08.002 (2022).
doi: 10.1016/j.gaitpost.2022.08.002
pubmed: 35964334
Ryan, C. G., Grant, P. M., Tigbe, W. W. & Granat, M. H. The validity and reliability of a novel activity monitor as a measure of walking. Br. J. Sports Med. 40, 779–784. https://doi.org/10.1136/bjsm.2006.027276 (2006).
doi: 10.1136/bjsm.2006.027276
pubmed: 16825270
pmcid: 2564393
Hof, A. L. Scaling gait data to body size. Gait Posture 4, 222–223. https://doi.org/10.1016/0966-6362(95)01057-2 (1996).
doi: 10.1016/0966-6362(95)01057-2
Sejdic, E., Lowry, K. A., Bellanca, J., Redfern, M. S. & Brach, J. S. A comprehensive assessment of gait accelerometry signals in time, frequency and time–frequency domains. IEEE Trans. Neural Syst. Rehabil. Eng. 22, 603–612. https://doi.org/10.1109/TNSRE.2013.2265887 (2014).
doi: 10.1109/TNSRE.2013.2265887
pubmed: 23751971
Sabatini, A. M., Martelloni, C., Scapellato, S. & Cavallo, F. Assessment of walking features from foot inertial sensing. IEEE Trans. Biomed. Eng. 52, 486–494. https://doi.org/10.1109/TBME.2004.840727 (2005).
doi: 10.1109/TBME.2004.840727
pubmed: 15759579
Cortes, C. & Vapnik, V. Support-vector networks. Mach. Learn. 20, 273–297. https://doi.org/10.1007/BF00994018 (1995).
doi: 10.1007/BF00994018
Breiman, L. Random forests. Mach. Learn. 45, 5–32. https://doi.org/10.1023/A:1010933404324 (2001).
doi: 10.1023/A:1010933404324
Zhang, C. & Ma, Y. Ensemble Machine Learning: Methods and Applications (2012).
Pedregosa, F. et al. Scikit-learn: Machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Baroudi, L. et al. Estimating walking speed in the wild. Front. Sports Act. Living 2, 1–14. https://doi.org/10.3389/fspor.2020.583848 (2020).
doi: 10.3389/fspor.2020.583848
Grieve, D. W. & Gear, R. J. The relationships between length of stride, step frequency, time of swing and speed of walking for children and adults. Ergonomics 9, 379–399. https://doi.org/10.1080/00140136608964399 (1966).
doi: 10.1080/00140136608964399
pubmed: 5976536
Kuo, A. D. A simple model of bipedal walking predicts the preferred speed-step length relationship. J. Biomech. Eng. 123, 264–269. https://doi.org/10.1115/1.1372322 (2001).
doi: 10.1115/1.1372322
pubmed: 11476370
Pinheiro, J., Bates, D. & R Core Team. nlme: Nonlinear Mixed Effects Models (R Core Team, 2022).
Field, A. P. & Wright, D. B. A primer on using multilevel models in clinical and experimental psychopathology research. J. Exp. Psychopathol. 2, 271–293. https://doi.org/10.5127/jep.013711 (2011).
doi: 10.5127/jep.013711
Akaike, H. Information theory and an extension of the maximum likelihood principle. J. Am. Stat. Assoc. 93, 199–213. https://doi.org/10.1007/978-1-4612-1694-0_15 (1998).
doi: 10.1007/978-1-4612-1694-0_15
Karas, M. et al. Estimation of free-living walking cadence from wrist-worn sensor accelerometry data and its association with SF-36 quality of life scores. Physiol. Meas. 42, 1. https://doi.org/10.1088/1361-6579/ac067b (2021).
doi: 10.1088/1361-6579/ac067b
Paraschiv-Ionescu, A. et al. Correction: Locomotion and cadence detection using a single trunk-fixed accelerometer: Validity for children with cerebral palsy in daily life-like conditions. J. NeuroEng. Rehabil. 16, 1–11. https://doi.org/10.1186/s12984-019-0498-8 (2019).
doi: 10.1186/s12984-019-0498-8
Fasel, B. et al. A wrist sensor and algorithm to determine instantaneous walking cadence and speed in daily life walking. Med. Biol. Eng. Comput. 55, 1773–1785. https://doi.org/10.1007/s11517-017-1621-2 (2017).
doi: 10.1007/s11517-017-1621-2
pubmed: 28197810
Fritz, S. & Lusardi, M. White paper: “Walking speed: The sixth vital sign’’. J. Geriatr. Phys. Therapy 32, 2–5. https://doi.org/10.1519/00139143-200932020-00002 (2009).
doi: 10.1519/00139143-200932020-00002
Graham, J. E., Ostir, G. V., Fisher, S. R. & Ottenbacher, K. J. Assessing walking speed in clinical research: A systematic review. J. Eval. Clin. Pract. 14, 552–562. https://doi.org/10.1111/j.1365-2753.2007.00917.x (2008).
doi: 10.1111/j.1365-2753.2007.00917.x
pubmed: 18462283
pmcid: 2628962
Afilalo, J. et al. Gait speed and operative mortality in older adults following cardiac surgery. JAMA Cardiol. 1, 314–321. https://doi.org/10.1001/jamacardio.2016.0316 (2016).
doi: 10.1001/jamacardio.2016.0316
pubmed: 27438112
Del Din, S., Godfrey, A., Galna, B., Lord, S. & Rochester, L. Free-living gait characteristics in ageing and Parkinson’s disease: Impact of environment and ambulatory bout length. J. Neuroeng. Rehabil. 13, 1–12. https://doi.org/10.1186/s12984-016-0154-5 (2016).
doi: 10.1186/s12984-016-0154-5
Murtagh, E. M., Mair, J. L., Aguiar, E., Tudor-Locke, C. & Murphy, M. H. Outdoor walking speeds of apparently healthy adults: A systematic review and meta-analysis. Sports Med. 51, 125–141. https://doi.org/10.1007/s40279-020-01351-3 (2021).
doi: 10.1007/s40279-020-01351-3
pubmed: 33030707
Krinski, K. et al. Let’s walk outdoors! Self-paced walking outdoors improves future intention to exercise in women with obesity. J. Sport Exerc. Psychol. 39, 145–157. https://doi.org/10.1123/jsep.2016-0220 (2017).
doi: 10.1123/jsep.2016-0220
pubmed: 28787251
Fuegen, K. & Breitenbecher, K. H. Walking and being outdoors in nature increase positive affect and energy. Ecopsychology 10, 14–25. https://doi.org/10.1089/eco.2017.0036 (2018).
doi: 10.1089/eco.2017.0036