FREE SHIPPING over $40
OVER 10000 FIVE-STAR REVIEWS
5% OFF ALL SUBSCRIPTIONS
100% HAPPINESS GUARANTEE
Analyze Diet
0
Sensors (Basel, Switzerland)2020; 20(2); 518; doi: 10.3390/s20020518

A Method to Estimate Horse Speed per Stride from One IMU with a Machine Learning Method.

Abstract: With the emergence of numerical sensors in sports, there is an increasing need for tools and methods to compute objective motion parameters with great accuracy. In particular, inertial measurement units are increasingly used in the clinical domain or the sports one to estimate spatiotemporal parameters. The purpose of the present study was to develop a model that can be included in a smart device in order to estimate the horse speed per stride from accelerometric and gyroscopic data without the use of a global positioning system, enabling the use of such a tool in both indoor and outdoor conditions. The accuracy of two speed calculation methods was compared: one signal based and one machine learning model. Those two methods allowed the calculation of speed from accelerometric and gyroscopic data without any other external input. For this purpose, data were collected under various speeds on straight lines and curved paths. Two reference systems were used to measure the speed in order to have a reference speed value to compare each tested model and estimate their accuracy. Those models were compared according to three different criteria: the percentage of error above 0.6 m/s, the RMSE, and the Bland and Altman limit of agreement. The machine learning method outperformed its competitor by giving the lowest value for all three criteria. The main contribution of this work is that it is the first method that gives an accurate speed per stride for horses without being coupled with a global positioning system or a magnetometer. No similar study performed on horses exists to compare our work with, so the presented model is compared to existing models for human walking. Moreover, this tool can be extended to other equestrian sports, as well as bipedal locomotion as long as consistent data are provided to train the machine learning model. The machine learning model's accurate results can be explained by the large database built to train the model and the innovative way of slicing stride data before using them as an input for the model.
Get Full Text
Publication Date: 2020-01-17 PubMed ID: 31963422PubMed Central: PMC7014525DOI: 10.3390/s20020518Google Scholar: Lookup
The Equine Research Bank provides access to a large database of publicly available scientific literature. Inclusion in the Research Bank does not imply endorsement of study methods or findings by Mad Barn.
LinkedInCopy
  • Journal Article

Summary

This research summary has been generated with artificial intelligence and may contain errors and omissions. Refer to the original study to confirm details provided. Submit correction.

The research is about a method developed to calculate horse speed per stride from a single Inertial Measurement Unit (IMU) through machine learning, without needing a GPS system. This allows the model’s use in various conditions – whether indoor or outdoor. The developed method performs better than existing ones in terms of error margin and accuracy.

Overview of the Research

  • The study primarily focuses on developing a model to estimate horse speed per stride using data from an inertial measurement unit (IMU).
  • This research taps into the advancement of numerical sensors in sports and the growing demand for accurately measuring motion parameters.
  • The IMU, increasingly employed in the sports and clinical domain, utilizes accelerometric and gyroscopic data in estimating these parameters.

Objective & Methodology

  • The goal is to create a model suitable for integration into a smart device. The model should estimate horse speed per stride without appealing to a global positioning system, and should work in both indoor and outdoor settings.
  • The study pits two speed calculation methods against each other – a signal-based method and a machine-learning model. Both utilize accelerometric and gyroscopic data and do not require external input.
  • Data collection happened at various speeds, on both straight and curved routes.
  • Speed was measured using two reference systems, providing a benchmark against which the tested models’ accuracy was compared.

Evaluation & Findings

  • The evaluation of these models took place according to three criteria: error percentage above 0.6 m/s, Root Mean Square Error (RMSE), and the Bland and Altman agreement limit.
  • Results revealed the machine-learning model as the superior alternative, demonstrating the lowest values across all three evaluation criteria.
  • No similar research on horses existed for comparison, so the model was compared to those created for human walking.

Significance & Implications

  • The study’s salient contribution is the development of the first method to accurately calculate speed per stride for horses without necessitating a GPS or a magnetometer.
  • The model can also be extended to other equestrian sports, as well as bipedal locomotion, provided the machine learning model is taught with consistent data.
  • The accuracy of the machine learning model is attributed to the extensive database created to teach the model, and the novel way of dividing stride data before using them as model input.

Cite This Article

APA
Schmutz A, Chèze L, Jacques J, Martin P. (2020). A Method to Estimate Horse Speed per Stride from One IMU with a Machine Learning Method. Sensors (Basel), 20(2), 518. https://doi.org/10.3390/s20020518

Publication

Sensors (Basel, Switzerland)
ISSN: 1424-8220
NlmUniqueID: 101204366
Country: Switzerland
Language: English
Volume: 20
Issue: 2
PII: 518

Researcher Affiliations

Schmutz, Amandine
  • Lim France, Chemin Fontaine de Fanny, 24300 Nontron, France.
  • CWD-Vetlab, Ecole Nationale Vétérinaire d'Alfort, F-94700 Maisons-Alfort, France.
  • LBMC UMR T9406, Université de Lyon, Lyon 1, 69364 Lyon, France.
  • ERIC EA3083, Université de Lyon, Lyon 2, 69007 Lyon, France.
Chèze, Laurence
  • LBMC UMR T9406, Université de Lyon, Lyon 1, 69364 Lyon, France.
Jacques, Julien
  • ERIC EA3083, Université de Lyon, Lyon 2, 69007 Lyon, France.
Martin, Pauline
  • Lim France, Chemin Fontaine de Fanny, 24300 Nontron, France.
  • CWD-Vetlab, Ecole Nationale Vétérinaire d'Alfort, F-94700 Maisons-Alfort, France.

MeSH Terms

  • Accelerometry / methods
  • Animals
  • Equipment Design
  • Gait / physiology
  • Horses / physiology
  • Machine Learning
  • Signal Processing, Computer-Assisted

Grant Funding

  • contract ANR 16-LCV2-0002-01 / LabCom 'CWD-Vetlab'

Conflict of Interest Statement

The authors declare no conflict of interest.

References

This article includes 32 references
  1. Pfau T, Witte TH, Wilson AM. A method for deriving displacement data during cyclical movement using an inertial sensor.. J Exp Biol 2005 Jul;208(Pt 13):2503-14.
    doi: 10.1242/jeb.01658pubmed: 15961737google scholar: lookup
  2. van der Kruk E, Reijne MM. Accuracy of human motion capture systems for sport applications; state-of-the-art review.. Eur J Sport Sci 2018 Jul;18(6):806-819.
    doi: 10.1080/17461391.2018.1463397pubmed: 29741985google scholar: lookup
  3. Martin P, Cheze L, Pourcelot P, Desquilbet L, Duray L, Chateau H. Effects of the rider on the kinematics of the equine spine under the saddle during the trot using inertial measurement units: Methodological study and preliminary results.. Vet J 2017 Mar;221:6-10.
    doi: 10.1016/j.tvjl.2016.12.018pubmed: 28283082google scholar: lookup
  4. Pfau T, Boultbee H, Davis H, Walker A, Rhodin M. Agreement between two inertial sensor gait analysis systems for lameness examinations in horses.. Equine Vet. Educ. 2016;28:203–208.
    doi: 10.1111/eve.12400google scholar: lookup
  5. Filippeschi A, Schmitz N, Miezal M, Bleser G, Ruffaldi E, Stricker D. Survey of Motion Tracking Methods Based on Inertial Sensors: A Focus on Upper Limb Human Motion.. Sensors (Basel) 2017 Jun 1;17(6).
    doi: 10.3390/s17061257pmc: PMC5492902pubmed: 28587178google scholar: lookup
  6. Tan H, Wilson AM, Lowe J. Measurement of stride parameters using a wearable GPS and inertial measurement unit.. J Biomech 2008;41(7):1398-406.
    doi: 10.1016/j.jbiomech.2008.02.021pubmed: 18423472google scholar: lookup
  7. Zihajehzadeh S, Loh D, Lee TJ, Hoskinson R, Park EJ. A cascaded Kalman filter based GPS/MEMS-IMU integration for sports applications.. Measurement 2015;73:200–210.
    doi: 10.1016/j.measurement.2015.05.023google scholar: lookup
  8. Wing MG, Eklund A, Kellogg LD. Consumer-Grade Global Positioning System (GPS) Accuracy and Reliability.. J. For. 2005;103:169–173.
    doi: 10.1093/jof/103.4.169google scholar: lookup
  9. Duong HT, Suh YS. Walking distance estimation of a walker user using a wrist-mounted IMU. Proceedings of the 2017 56th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE); Kanazawa, Japan. 19–22 September 2017; pp. 1061–1064.
  10. Murphy J, Carr H, O’Neill M. Animating horse gaits and transitions.. Symposium on Theory and Practice of Computer Graphics The Eurographics Association; Sheffield, UK: 2010.
  11. Brzostowski K. Novel approach to human walking speed enhancement based on drift estimation.. Biomed. Signal Process. Control. 2018;42:18–29.
    doi: 10.1016/j.bspc.2018.01.002google scholar: lookup
  12. Bosch S, Serra Bragança F, Marin-Perianu M, Marin-Perianu R, van der Zwaag BJ, Voskamp J, Back W, van Weeren R, Havinga P. EquiMoves: A Wireless Networked Inertial Measurement System for Objective Examination of Horse Gait.. Sensors (Basel) 2018 Mar 13;18(3).
    doi: 10.3390/s18030850pmc: PMC5877382pubmed: 29534022google scholar: lookup
  13. Sabatini AM, Mannini A. Ambulatory Assessment of Instantaneous Velocity during Walking Using Inertial Sensor Measurements.. Sensors (Basel) 2016 Dec 21;16(12).
    doi: 10.3390/s16122206pmc: PMC5191184pubmed: 28009854google scholar: lookup
  14. Zihajehzadeh S, Park EJ. A Gaussian process regression model for walking speed estimation using a head-worn IMU.. Annu Int Conf IEEE Eng Med Biol Soc 2017 Jul;2017:2345-2348.
    pubmed: 29060368doi: 10.1109/embc.2017.8037326google scholar: lookup
  15. Zihajehzadeh S, Aziz O, Tae CG, Park EJ. Combined Regression and Classification Models for Accurate Estimation of Walking Speed Using a Wrist-worn IMU.. Annu Int Conf IEEE Eng Med Biol Soc 2018 Jul;2018:3272-3275.
    pubmed: 30441090doi: 10.1109/embc.2018.8513013google scholar: lookup
  16. Bishop CM. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer; Berlin/Heidelberg, Germany: 2006.
  17. Camomilla V, Bergamini E, Fantozzi S, Vannozzi G. Trends Supporting the In-Field Use of Wearable Inertial Sensors for Sport Performance Evaluation: A Systematic Review.. Sensors (Basel) 2018 Mar 15;18(3).
    doi: 10.3390/s18030873pmc: PMC5877384pubmed: 29543747google scholar: lookup
  18. Martin P. Saddle In Motion: Back Biomechanics of the Ridden Horse: Analysis of the Interactions Between the Saddle and the Back, and Application to the Development of News Prototypes of Saddles.. Ph.D. Thesis. Université Claude Bernard–Lyon I; Villeurbanne, France: 2015.
  19. Wilson RP, White CR, Quintana F, Halsey LG, Liebsch N, Martin GR, Butler PJ. Moving towards acceleration for estimates of activity-specific metabolic rate in free-living animals: the case of the cormorant.. J Anim Ecol 2006 Sep;75(5):1081-90.
    doi: 10.1111/j.1365-2656.2006.01127.xpubmed: 16922843google scholar: lookup
  20. R Core Team. R: A Language and Environment for Statistical Computing.. R Foundation for Statistical Computing; Vienna, Austria: 2017.
  21. Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning.. Springer; New York, NY, USA: 2001. (Springer Series in Statistics).
  22. Ferraty F, Vieu P. Nonparametric Functional Data Analysis.. Springer; New York, NY, USA: 2006. (Springer Series in Statistics).
  23. Ramsay JO, Silverman BW. Functional Data Analysis.. 2nd ed. Springer; New York, NY, USA: 2005. (Springer Series in Statistics).
  24. Smola AJ, Bernhard S. A Tutorial on Support Vector Regression.. Stat. Comput. 2004;14:199–222.
  25. Meyer D, Dimitriadou E, Hornik K, Weingessel A, Leisch F. e1071: Misc Functions of the Department of Statistics, Probability Theory Group (Formerly: E1071). R Packag. 2008;1:5–24.
  26. Bland JM, Altman DG. Measuring agreement in method comparison studies.. Stat Methods Med Res 1999 Jun;8(2):135-60.
    doi: 10.1177/096228029900800204pubmed: 10501650google scholar: lookup
  27. Lehnert B. BlandAltmanLeh: Plots (Slightly Extended) Bland-Altman Plots.. R Package Version 0.3.1 [(accessed on 17 January 2020)]; Available online: https://cran.r-project.org/web/packages/BlandAltmanLeh/index.html.
  28. Bichler S, Ogris G, Kremser V, Schwab F, Knott S, Baca A. Towards high-precision IMU/GPS based stride-parameter determination in an outdoor runners’ scenario.. Procedia Eng. 2012;34:592–597.
    doi: 10.1016/j.proeng.2012.04.101google scholar: lookup
  29. Mannini A, Sabatini AM. Walking speed estimation using foot-mounted inertial sensors: comparing machine learning and strap-down integration methods.. Med Eng Phys 2014 Oct;36(10):1312-21.
    doi: 10.1016/j.medengphy.2014.07.022pubmed: 25199588google scholar: lookup
  30. Zhao Y, Brahms M, Gerhard D, Barden J. Stance Phase Detection for Walking and Running Using an IMU Periodicity based Approach.. In: Chung P., Soltoggio A., Dawson C.W., Meng Q., Pain M., editors. Proceedings of the 10th International Symposium on Computer Science in Sports (ISCSS); Moscow, Russia. 8–10 July 2019; Cham, Switzerland: Springer; 2016. pp. 225–232.
  31. Zihajehzadeh S, Park EJ. Regression Model-Based Walking Speed Estimation Using Wrist-Worn Inertial Sensor.. PLoS One 2016;11(10):e0165211.
    doi: 10.1371/journal.pone.0165211pmc: PMC5072584pubmed: 27764231google scholar: lookup
  32. Greve L, Dyson S. Body lean angle in sound dressage horses in-hand, on the lunge and ridden.. Vet J 2016 Nov;217:52-57.
    doi: 10.1016/j.tvjl.2016.06.004pubmed: 27810211google scholar: lookup

Citations

This article has been cited 6 times.
  1. Crecan CM, Peștean CP. Inertial Sensor Technologies-Their Role in Equine Gait Analysis, a Review. Sensors (Basel) 2023 Jul 11;23(14).
    doi: 10.3390/s23146301pubmed: 37514599google scholar: lookup
  2. Eerdekens A, Deruyck M, Fontaine J, Damiaans B, Martens L, De Poorter E, Govaere J, Plets D, Joseph W. Horse Jumping and Dressage Training Activity Detection Using Accelerometer Data. Animals (Basel) 2021 Oct 7;11(10).
    doi: 10.3390/ani11102904pubmed: 34679925google scholar: lookup
  3. Pfau T, Persson-Sjodin E, Gardner H, Orssten O, Hernlund E, Rhodin M. Effect of Speed and Surface Type on Individual Rein and Combined Left-Right Circle Movement Asymmetry in Horses on the Lunge. Front Vet Sci 2021;8:692031.
    doi: 10.3389/fvets.2021.692031pubmed: 34322537google scholar: lookup
  4. Steinke SL, Montgomery JB, Barden JM. Accelerometry-Based Step Count Validation for Horse Movement Analysis During Stall Confinement. Front Vet Sci 2021;8:681213.
    doi: 10.3389/fvets.2021.681213pubmed: 34239913google scholar: lookup
  5. Darbandi H, Serra Bragança F, van der Zwaag BJ, Voskamp J, Gmel AI, Haraldsdóttir EH, Havinga P. Using Different Combinations of Body-Mounted IMU Sensors to Estimate Speed of Horses-A Machine Learning Approach. Sensors (Basel) 2021 Jan 26;21(3).
    doi: 10.3390/s21030798pubmed: 33530288google scholar: lookup
  6. Marin F. Human and Animal Motion Tracking Using Inertial Sensors. Sensors (Basel) 2020 Oct 26;20(21).
    doi: 10.3390/s20216074pubmed: 33114597google scholar: lookup
Subscribe to our newsletter
Join 99,850 horse owners like you who receive our email updates on horse health and nutrition.