Restricted access

Purchase article

USD $24.95

Student 1 year subscription

USD $87.00

1 year subscription

USD $116.00

Student 2 year subscription

USD $165.00

2 year subscription

USD $215.00

Field-based sprint performance assessments rely on metrics derived from a simple model of sprinting dynamics parameterized by 2 constants, v0 and τ, which indicate a sprinter’s maximal theoretical velocity and the time it takes to approach v0, respectively. This study aims to automate sprint assessment by estimating v0 and τ using machine learning and accelerometer data. To this end, photocells recorded 10-m split times of 28 subjects for three 40-m sprints while wearing an accelerometer around the waist. Features extracted from the accelerometer data were used to train a classifier to identify the sprint start and regression models to estimate the sprint model parameters. Estimates of v0, τ, and 30-m sprint time (t30) were compared between the proposed method and a photocell method using root mean square error and Bland–Altman analysis. The root mean square error of the sprint start estimate was .22 seconds and ranged from .52 to .93 m/s for v0, .14 to .17 seconds for τ, and .23 to .34 seconds for t30. Model-derived sprint performance metrics from most regression models were significantly (P < .01) correlated with t30. Comparison of the proposed method and a physics-based method suggests pursuit of a combined approach because their strengths appear to complement each other.

Gurchiek, van Werkhoven, Needle, and McBride are with the Department of Health & Exercise Science, Appalachian State University, Boone, NC, USA. Rupasinghe Arachchige Don, Pelawa Watagoda, and Arnholt are with the Department of Mathematical Sciences, Appalachian State University, Boone, NC, USA. Gurchiek and McGinnis are with the Department of Electrical and Biomedical Engineering, The University of Vermont, Burlington, VT, USA.

Gurchiek (reed.gurchiek@uvm.edu) is corresponding author.
Journal of Applied Biomechanics
Article Sections
References
  • 1.

    Samozino PRabita GDorel Set al. A simple method for measuring power, force, velocity properties, and mechanical effectiveness in sprint running. Scand J Med Sci Sports. 2015;26(6):648658. PubMed ID: 25996964 doi:10.1111/sms12490

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 2.

    Setuain ILecumberri PAhtiainen JPMero AAHäkkinen KIzquierdo M. Sprint mechanics evaluation using inertial sensor-based technology: a laboratory validation study. Scand J Med Sci Sports. 2018;28(2):463472. PubMed ID: 28685862 doi:10.1111/sms.12946

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 3.

    Gurchiek RDMcGinnis RSNeedle ARMcBride JMvan Werkhoven H. An adaptive filtering algorithm to estimate sprint velocity using a single inertial sensor. Sports Eng. 2018;21(4):389399. doi:10.1007/s12283-018-0285-y

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 4.

    Romero-Franco NJiménez-Reyes PCastaño-Zambudio Aet al. Sprint performance and mechanical outputs computed with an iPhone app: comparison with existing reference methods. Eur J Sport Sci. 2017;17:386392. doi:10.1080/17461391.2016.1249031

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 5.

    Nagahara RBotter ARejc Eet al. Concurrent validity of GPS for deriving mechanical properties of sprint acceleration. Int J Sports Physiol Perform. 2017;12(1):129132. PubMed ID: 27002693 doi:10.1123/ijspp.2015-0566

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 6.

    Cross MRBrughelli MSamozino PMorin JB. Methods of power-force-velocity profiling during sprint running: a narrative review. Sports Med. 2017;47(7):12551269. PubMed ID: 27896682 doi:10.1007/s40279-016-0653-3

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 7.

    Simperingham KDCronin JBRoss A. Advances in sprint acceleration profiling for field-based team-sport athletes: utility, reliability, validity and limitations. Sports Med. 2016;46(11):16191645. PubMed ID: 26914267 doi:10.1007/s40279-016-0508-y

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 8.

    Furusawa KHill AVParkinson JL. The dynamics of “sprint” running. Proc R Soc Lond Ser B. 1927;102(713):2942. doi:10.1098/rspb.1927.0035

  • 9.

    Gurchiek RDMcGinnis RSNeedle ARMcBride JMvan Werkhoven H. The use of a single inertial sensor to estimate 3-dimensional ground reaction force during accelerative running tasks. J Biomech. 2017;61:263268. PubMed ID: 28830590 doi:10.1016/j.jbiomech.2017.07.035

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 10.

    Parrington LPhillips EWong AFinch MWain EMacMahon C. Validation of inertial measurement units for tracking 100m sprint data. Paper presented at: 34th International Conference of Biomechanics in Sport; Tsukuba Japan. July 18-22 2016. https://ojs.ub.uni-konstanz.de/cpa/issue/view/127. Accessed October 3 2016.

    • Export Citation
  • 11.

    Bergamini EGuillon PCamomilla VPillet HSkalli WCappozzo A. Trunk inclination estimate during the sprint start using an inertial measurement unit: a validation study. J Appl Biomech. 2013;29(5):622627. PubMed ID: 23182857 doi:10.1123/jab.29.5.622

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 12.

    Lee JBMellifont RBBurkett BJ. The use of a single inertial sensor to identify stride, step, and stance durations of running gait. J Sci Med Sport. 2010;13(2):270273. PubMed ID: 19574098 doi:10.1016/j.jsams.2009.01.005

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 13.

    Bergamini EPicerno PPillet HNatta FThoreux PCamomilla V. Estimation of temporal parameters during sprint running using a trunk-mounted inertial measurement unit. J Biomech. 2012;45(6):11231126. PubMed ID: 22325976 doi:10.1016/j.jbiomech.2011.12.020

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 14.

    Mannini AMartinez-Manzanera OLawerman TFet al. Automatic classification of gait in children with early-onset ataxia or developmental coordination disorder and controls using inertial sensors. Gait Posture. 2017;52(suppl C):287292. doi:10.1016/j.gaitpost.2016.12.002

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 15.

    Mannini ATrojaniello DCereatti ASabatini AM. A machine learning framework for gait classification using inertial sensors: application to elderly, post-stroke and Huntington’s disease patients. Sensors. 2016;16(1):E134. doi:10.3390/s16010134

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 16.

    Mannini ATrojaniello DCroce UDSabatini AM. Automatic recognition of altered gait using wearable inertial sensors. Gait Posture. 2016;49:9. doi:10.1016/j.gaitpost.2016.07.035

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 17.

    Whiteside DCant OConnolly MReid M. Monitoring hitting load in tennis using inertial sensors and machine learning. Int J Sports Physiol Perform. 2017;12(9):12121217. PubMed ID: 28182523 doi:10.1123/ijspp.2016-0683

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 18.

    Mannini ASabatini AM. Automatic machine learning methods for analysis of signals from accelerometers: classification of human activity and walking–running speed estimation. Gait Posture. 2011;33:S24. doi:10.1016/j.gaitpost.2010.10.031

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 19.

    Mannini ASabatini AM. Single stride speed estimation using support vector regression. Gait Posture. 2013;37:S2526. doi:10.1016/j.gaitpost.2012.12.054

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 20.

    Mannini ASabatini AM. Walking speed estimation using foot-mounted inertial sensors: comparing machine learning and strap-down integration methods. Med Eng Phys. 2014;36(10):13121321. PubMed ID: 25199588 doi:10.1016/j.medengphy.2014.07.022

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 21.

    McGinnis RSMahadevan NMoon Yet al. A machine learning approach for gait speed estimation using skin-mounted wearable sensors: from healthy controls to individuals with multiple sclerosis. PLoS ONE. 2017;12(6):e0178366. doi:10.1371/journal.pone.0178366

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 22.

    Zihajehzadeh SPark EJ. A Gaussian process regression model for walking speed estimation using a head-worn IMU. Paper presented at: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Seogwipo South Korea. July 11-15 2017:23452348. doi:10.1109/EMBC.2017.8037326. https://ieeexplore.ieee.org/document/8037326. Accessed November 11 2017.

    • PubMed
    • Export Citation
  • 23.

    Zihajehzadeh SPark EJ. Experimental evaluation of regression model-based walking speed estimation using lower body-mounted IMU. Paper presented at: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Orlando FL. August 16-20 2016:243246. doi:10.1109/EMBC.2016.7590685. https://ieeexplore.ieee.org/document/7590685. Accessed November 11 2017.

    • PubMed
    • Export Citation
  • 24.

    Zihajehzadeh SPark EJ. Regression model-based walking speed estimation using wrist-worn inertial sensor. PLoS ONE. 2016;11(10):e0165211. PubMed ID: 27764231 doi:10.1371/journal.pone.0165211

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 25.

    Meyer DDimitriadou EHornik KWeingessel ALeisch F. E1071: misc functions of the Department of Statistics, Probability Theory Group (formerly: E1071), TU Wien. 2017. https://CRAN.R-project.org/package=e1071. Accessed February 9 2018.

    • Export Citation
  • 26.

    Friedman JHastie TSimon NQian JTibshirani R. Glmnet: lasso and elastic-net regularized generalized linear models. 2017. https://CRAN.R-project.org/package=glmnet. Accessed February 9 2018.

    • Export Citation
  • 27.

    Giavarina D. Understanding Bland Altman analysis. Biochem Medica. 2015;25(2):141151. doi:10.11613/BM.2015.015

Article Metrics
All Time Past Year Past 30 Days
Abstract Views 235 235 29
Full Text Views 40 40 14
PDF Downloads 24 24 12
Altmetric Badge
PubMed
Google Scholar
Cited By