Hostname: page-component-745bb68f8f-g4j75 Total loading time: 0 Render date: 2025-02-02T22:30:46.068Z Has data issue: false hasContentIssue false
  • English
  • Français

Stride segmentation of inertial sensor data using statistical methods for different walking activities

Published online by Cambridge University Press:  27 December 2021

Rahul Jain Open the ORCID record for Rahul Jain [Opens in a new window] ,
Vijay Bhaskar Semwal  and
Praveen Kaushik
Rahul Jain*
Affiliation:
Maulana Azad National Institute of Technology, Bhopal, India.
Vijay Bhaskar Semwal
Affiliation:
Maulana Azad National Institute of Technology, Bhopal, India.
Praveen Kaushik
Affiliation:
Maulana Azad National Institute of Technology, Bhopal, India.
*
*Corresponding author. E-mail: [email protected].
Get access Rights & Permissions [Opens in a new window]

Abstract

Human gait data can be collected using inertial measurement units (IMUs). An IMU is an electronic device that uses an accelerometer and gyroscope to capture three-axial linear acceleration and three-axial angular velocity. The data so collected are time series in nature. The major challenge associated with these data is the segmentation of signal samples into stride-specific information, that is, individual gait cycles. One empirical approach for stride segmentation is based on timestamps. However, timestamping is a manual technique, and it requires a timing device and a fixed laboratory set-up which usually restricts its applicability outside of the laboratory. In this study, we have proposed an automatic technique for stride segmentation of accelerometry data for three different walking activities. The autocorrelation function (ACF) is utilized for the identification of stride boundaries. Identification and extraction of stride-specific data are done by devising a concept of tuning parameter ( $t_{p}$ ) which is based on minimum standard deviation ( $\sigma$ ). Rigorous experimentation is done on human activities and postural transition and Osaka University – Institute of Scientific and Industrial Research gait inertial sensor datasets. Obtained mean stride duration for level walking, walking upstairs, and walking downstairs is 1.1, 1.19, and 1.02 s with 95% confidence interval [1.08, 1.12], [1.15, 1.22], and [0.97, 1.07], respectively, which is on par with standard findings reported in the literature. Limitations of accelerometry and ACF are also discussed. stride segmentation; human activity recognition; accelerometry; gait parameter estimation; gait cycle; inertial measurement unit; autocorrelation function; wearable sensors; IoT; edge computing; tinyML.

Keywords

stride segmentationhuman activity recognitionaccelerometrygait parameter estimationgait cycleinertial measurement unitautocorrelation functionwearable sensorsIoTedge computingtinyML
Type
Research Article
Information
Robotica , Volume 40 , Issue 8 , August 2022 , pp. 2567 - 2580
Copyright
© The Author(s), 2021. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Semwal, V. and Nandi, G., Data Driven Computational Model for Bipedal Walking and Push Recovery. PhD thesis (June 2017).Google Scholar
Semwal, V. B., Kumar, C., Mishra, P. K. and Nandi, G. C., “Design of vector field for different subphases of gait and regeneration of gait pattern,” IEEE Trans. Automat. Sci. Eng. 15(1), 104–110 (2018).10.1109/TASE.2016.2594191CrossRefGoogle Scholar
Jarchi, D., Pope, J., Lee, T. K. M., Tamjidi, L., Mirzaei, A. and Sanei, S., “A review on accelerometry-based gait analysis and emerging clinical applications,” IEEE Rev. Biomed. Eng. 11, 177–194 (2018).CrossRefGoogle ScholarPubMed
Semwal, V. B., Raj, M. and Nandi, G., “Biometric gait identification based on a multilayer perceptron,” Robot. Autonom. Syst. 65, 65–75 (2015).CrossRefGoogle Scholar
Lara, O. D. and Labrador, M. A., “A survey on human activity recognition using wearable sensors,” IEEE Commun. Surv. Tutor. 15(3), 1192–1209 (2013).10.1109/SURV.2012.110112.00192CrossRefGoogle Scholar
Semwal, V. B. and Nandi, G. C., “Generation of joint trajectories using hybrid automate-based model: A rocking block-based approach,” IEEE Sens. J. 16(14), 5805–5816 (2016).10.1109/JSEN.2016.2570281CrossRefGoogle Scholar
Semwal, V. B., Katiyar, S. A., Chakraborty, R. and Nandi, G., “Biologically-inspired push recovery capable bipedal locomotion modeling through hybrid automata,” Robot. Auton. Syst. 70, 181–190 (2015).Google Scholar
Semwal, V. B. and Nandi, G. C., “Toward developing a computational model for bipedal push recovery–a brief,” IEEE Sens. J. 15(4), 2021–2022 (2015).Google Scholar
Torvi, V. G., Bhattacharya, A. and Chakraborty, S., “Deep Domain Adaptation to Predict Freezing of gait in Patients with Parkinson’s Disease,” In: 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) (2018) pp. 1001–1006.Google Scholar
Deb, S., Ou Yang, Y., Chua, M. C. H. and Tian, J., “Gait identification using a new time-warped similarity metric based on smartphone inertial signals,” J. Amb. Intel. Human. Comput. 11(10), 4041–4053 (2020).10.1007/s12652-019-01659-7CrossRefGoogle Scholar
Torrealba, R., Cappelletto, J., Fermıın-Leoın, L., Grieco, J. and Fernandez, G., “Statistics-based technique for automated detection of gait events from accelerometer signals,” Electron. Lett. 46(22), 1483–1485 (2010).10.1049/el.2010.2118CrossRefGoogle Scholar
Hannink, J., Kautz, T., Pasluosta, C. F., Gasmann, K. G., Klucken, J. and Eskofier, B. M., “Sensor-based Gait parameter extraction with deep convolutional neural networks,” IEEE J. Biomed. Health Inform. 21(1), 85–93 (2017).10.1109/JBHI.2016.2636456CrossRefGoogle Scholar
Jain, R., Semwal, V. B. and Kaushik, P., “Deep ensemble learning approach for lower extremity activities recognition using wearable sensors,” Exp. Syst. e12743 (2021). Available: https://doi.org/10.1111/exsy.12743 CrossRefGoogle Scholar
Shi, W., Cao, J., Zhang, Q., Li, Y. and Xu, L., Edge computing: Vision and challenges, IEEE Internet Things J. 3(5), 637–646 (2016).CrossRefGoogle Scholar
Banbury, C. R., Reddi, V. J., Lam, M., Fu, W., Fazel, A., Holleman, J., Huang, X., Hurtado, R., Kanter, D., Lokhmotov, A., Patterson, D., Pau, D., Sun Seo, J., Sieracki, J., Thakker, U., Verhelst, M. and Yadav, P., Benchmarking Tinyml Systems: Challenges and Direction (2021). Available: https://arxiv.org/abs/2003.04821v4 Google Scholar
Reyes-Ortiz, J.-L., Oneto, L., Samà, A., Parra, X. and Anguita, D., “Transition-aware human activity recognition using smartphones,” Neurocomputing 171, 754–767 (2016).Google Scholar
Ngo, T. T., Makihara, Y., Nagahara, H., Mukaigawa, Y. and Yagi, Y., “The largest inertial sensor-based gait database and performance evaluation of gait-based personal authentication,” Pattern Recognit. 47(1), 228–237 (2014).CrossRefGoogle Scholar
Brajdic, A. and Harle, R., “Walk Detection and Step Counting on Unconstrained Smartphones,” In: UbiComp 2013 - Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing (2013) pp. 225–234.Google Scholar
Moe-Nilssen, R. and Helbostad, J. L., “Estimation of gait cycle characteristics by trunk accelerometry,” J. Biomech. 37(1), 121–126 (2004).10.1016/S0021-9290(03)00233-1CrossRefGoogle ScholarPubMed
Jagos, H., Reich, S., Rattay, F., Mehnen, L., Pils, K., Wassermann, C., Chhatwal, C. and Reichel, M., “Determination of gait parameters from the wearable motion analysis system eSHOE,” Biomed. Tech. (Berl.) 58(Suppl. 1) (2013).Google ScholarPubMed
Lueken, M., Ten Kate, W., Batista, J. P., Ngo, C., Bollheimer, C. and Leonhardt, S., “Peak Detection Algorithm for Gait Segmentation in Long-Term Monitoring for Stride Time Estimation Using Inertial Measurement Sensors,” In: 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings (2019).10.1109/BHI.2019.8834542CrossRefGoogle Scholar
Yang, C. C., Hsu, Y. L., Shih, K. S. and Lu, J. M., “Real-time gait cycle parameter recognition using a wearable accelerometry system,” Sensors (Basel) 11(8), 7314–7326 (2011).CrossRefGoogle Scholar
O’Callaghan, B. P., Doheny, E. P., Goulding, C., Fortune, E. and Lowery, M. M., “Adaptive Gait Segmentation Algorithm for Walking Bout Detection Using Tri-Axial Accelerometers,” In: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, vol. 2020-July (2020) pp. 4592–4595.Google Scholar
Gill, S., Seth, N. and Scheme, E., “A multi-sensor matched filter approach to robust segmentation of assisted gait,” Sensors (Switzerland) 18(9), 16–23 (2018).10.3390/s18092970CrossRefGoogle ScholarPubMed
Anwary, A. R., Yu, H. and Vassallo, M., “Optimal foot location for placing wearable IMU sensors and automatic feature extraction for gait analysis,” IEEE Sens. J. 18(6), 2555–2567 (2018).CrossRefGoogle Scholar
Sun, F., Zang, W., Gravina, R., Fortino, G. and Li, Y., “Gait-based identification for elderly users in wearable healthcare systems,” Inform. Fus. 53(June 2019), 134–144 (2020).10.1016/j.inffus.2019.06.023CrossRefGoogle Scholar
Qiu, S., Wang, Z., Zhao, H. and Hu, H., “Using distributed wearable sensors to measure and evaluate human lower limb motions,” IEEE Trans. Instrument. Meas. 65(4), 939–950 (2016).10.1109/TIM.2015.2504078CrossRefGoogle Scholar
Rampp, A., Barth, J., Schülein, S., K. G. Gaßmann, J. Klucken and B. M. Eskofier, “Inertial sensor-based stride parameter calculation from gait sequences in geriatric patients,” IEEE Trans. Biomed. Eng. 62(4), 1089–1097 (2015).10.1109/TBME.2014.2368211CrossRefGoogle Scholar
Barth, J., Oberndorfer, C., Kugler, P., Schuldhaus, D., Winkler, J., Klucken, J. and Eskofier, B., “Subsequence Dynamic Time Warping as a Method for Robust Step Segmentation Using Gyroscope Signals of Daily Life Activities,” In: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 6744–6747 (2013).Google Scholar
Barth, J., Oberndorfer, C., Pasluosta, C., Schülein, S., Gassner, H., Reinfelder, S., Kugler, P., Schuldhaus, D., Winkler, J., Klucken, J. and Eskofier, B. M., “Stride segmentation during free walk movements using multi-dimensional subsequence dynamic time warping on inertial sensor data,” Sensors (Switzerland), 15(3), 6419–6440 (2015).CrossRefGoogle ScholarPubMed
Eddy, S. R., “What is a hidden Markov model?,” Nat. Biotechnol. 22(10), 1315–1316 (2004).CrossRefGoogle ScholarPubMed
Roth, N., Küderle, A., Ullrich, M., Gladow, T., Marxreiter, F., Klucken, J., Eskofier, B. M. and Kluge, F., “Hidden Markov model based stride segmentation on unsupervised free-living gait data in Parkinson’s disease patients,” J. NeuroEng. Rehab. 18, 1–15 (2021).10.1186/s12984-021-00883-7CrossRefGoogle ScholarPubMed
Liu, L., Wang, H., Li, H., Liu, J., Qiu, S., Zhao, H., and Guo, X., “Ambulatory Human Gait Phase Detection Using Wearable Inertial Sensors and Hidden Markov Model,” Sens. 21(4), 1347 (2021).CrossRefGoogle ScholarPubMed
Martindale, C. F., Christlein, V., Klumpp, P. and Eskofier, B. M., “Wearables-based multi-task gait and activity segmentation using recurrent neural networks,” Neurocomputing 432, 250–261 (2021).Google Scholar
Murray, M. P., Drought, A. B. and Kory, R. C., “Walking patterns of normal men,” J. Bone. Joint Surg. Am. 46(2), 335–360 (1964).CrossRefGoogle ScholarPubMed
Livingston, L. A., Stevenson, J. M. and Olney, S. J., “Stairclimbing kinematics on stairs of differing dimensions,” Arch. Phys. Med. Rehabil. 72(6), 398–402 (1991).Google ScholarPubMed
Warlop, T. B., Bollens, B., Detrembleur, C., Stoquart, G., Lejeune, T. and Crevecoeur, F., “Impact of series length on statistical precision and sensitivity of autocorrelation assessment in human locomotion,” Hum. Mov. Sci. 55, 31–42 (2017).CrossRefGoogle ScholarPubMed