FREE SHIPPING over $40
OVER 10000 FIVE-STAR REVIEWS
5% OFF ALL SUBSCRIPTIONS
100% HAPPINESS GUARANTEE
Analyze Diet
0
Scientific reports2023; 13(1); 740; doi: 10.1038/s41598-023-27899-4

Prediction of continuous and discrete kinetic parameters in horses from inertial measurement units data using recurrent artificial neural networks.

Abstract: Vertical ground reaction force (GRFz) measurements are the best tool for assessing horses' weight-bearing lameness. However, collection of these data is often impractical for clinical use. This study evaluates GRFz predicted using data from body-mounted IMUs and long short-term memory recurrent neural networks (LSTM-RNN). Twenty-four clinically sound horses, equipped with IMUs on the upper-body (UB) and each limb, walked and trotted on a GRFz measuring treadmill (TiF). Both systems were time-synchronised. Data from randomly selected 16, 4, and 4 horses formed training, validation, and test datasets, respectively. LSTM-RNN with different input sets (All, Limbs, UB, Sacrum, or Withers) were trained to predict GRFz curves or peak-GRFz. Our models could predict GRFz shapes at both gaits with RMSE below 0.40 N.kg-1. The best peak-GRFz values were obtained when extracted from the predicted curves by the all dataset. For both GRFz curves and peak-GRFz values, predictions made with the All or UB datasets were systematically better than with the Limbs dataset, showing the importance of including upper-body kinematic information for kinetic parameters predictions. More data should be gathered to confirm the usability of LSTM-RNN for GRFz predictions, as they highly depend on factors like speed, gait, and the presence of weight-bearing lameness.
© 2023. The Author(s).
Get Full Text
Publication Date: 2023-01-13 PubMed ID: 36639409PubMed Central: PMC9839734DOI: 10.1038/s41598-023-27899-4Google 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
  • Research Support
  • Non-U.S. Gov't

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 study uses artificial neural networks to predict Ground Reaction Force (GRFz) measurements in horses from Inertial Measurement Units (IMUs) data. The goal is to easier assess weight-bearing lameness in horses, which may enable better, less invasive, and more practical clinical use.

Methodology

  • The researchers used a group of 24 clinically sound horses for their experiment. These horses were equipped with IMUs on their upper bodies and on each limb.
  • The horses walked and trotted on a Ground Reaction Force (GRFz) treadmill – a device used to measure the force exerted by the horse on the treadmill surface.
  • The data from these devices was time-synchronized for accuracy.
  • The horses were split into groups of 16, 4, and 4 which were used for training, validation, and testing datasets respectively.
  • These datasets were then fed into Long Short-Term Memory Recurrent Neural Networks (LSTM-RNNs). These are a type of artificial neural network known for their ability to make predictions based on time series data.
  • The LSTM-RNNs trained on different input sets (All, Limbs, UB, Sacrum, or Withers) to predict the GRFz curves, or peak-GRFz values.

Results

  • The study found that their models could predict the shape of the GRFz recently enough (below 0.40 N.kg for the Root Mean Square Error) at both the walking and trotting gaits.
  • The best predictions of peak-GRFz values were achieved by utilizing data from all IMUs.
  • When predicting both GRFz curves and peak-GRFz values, the models trained on all the data or just the upper body data consistently performed better than models trained on just the limbs’ data.
  • This indicates the importance of kinematic data from the upper body in making accurate predictions of kinetic parameters.

Conclusion

  • The successful performance of the LSTM-RNN models in this study suggests that this approach could be a viable method for more practical assessment of weight-bearing lameness in horses.
  • However, the researchers caution that more data is required to confirm the effectiveness of this approach, as GRFz predictions can depend heavily on factors such as the speed of the horse, its gait, and the presence of any weight-bearing lameness.

Cite This Article

APA
Parmentier JIM, Bosch S, van der Zwaag BJ, Weishaupt MA, Gmel AI, Havinga PJM, van Weeren PR, Braganca FMS. (2023). Prediction of continuous and discrete kinetic parameters in horses from inertial measurement units data using recurrent artificial neural networks. Sci Rep, 13(1), 740. https://doi.org/10.1038/s41598-023-27899-4

Publication

Scientific reports
ISSN: 2045-2322
NlmUniqueID: 101563288
Country: England
Language: English
Volume: 13
Issue: 1
Pages: 740

Researcher Affiliations

Parmentier, J I M
  • Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, 3584 CM, Utrecht, The Netherlands. j.i.m.parmentier@uu.nl.
  • Pervasive Systems Group, Department of Computer Science, University of Twente, 7522 NB, Enschede, The Netherlands. j.i.m.parmentier@uu.nl.
Bosch, S
  • Inertia Technology B.V., 7521 AG, Enschede, The Netherlands.
  • Pervasive Systems Group, Department of Computer Science, University of Twente, 7522 NB, Enschede, The Netherlands.
van der Zwaag, B J
  • Inertia Technology B.V., 7521 AG, Enschede, The Netherlands.
  • Pervasive Systems Group, Department of Computer Science, University of Twente, 7522 NB, Enschede, The Netherlands.
Weishaupt, M A
  • Equine Department, Vetsuisse Faculty, University of Zürich, Winterhurerstrasse 260, Zurich, Switzerland.
Gmel, A I
  • Equine Department, Vetsuisse Faculty, University of Zürich, Winterhurerstrasse 260, Zurich, Switzerland.
  • Animal GenoPhenomics, Agroscope, 1725, Posieux, Switzerland.
Havinga, P J M
  • Pervasive Systems Group, Department of Computer Science, University of Twente, 7522 NB, Enschede, The Netherlands.
van Weeren, P R
  • Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, 3584 CM, Utrecht, The Netherlands.
Braganca, F M Serra
  • Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, 3584 CM, Utrecht, The Netherlands.

MeSH Terms

  • Horses
  • Animals
  • Lameness, Animal
  • Hindlimb
  • Gait
  • Walking
  • Biomechanical Phenomena
  • Neural Networks, Computer
  • Forelimb

Conflict of Interest Statement

S.B. and B.J.vdZ. are also employees of Inertia Technology B.V., which manufactures and sells the sensors used in this study. The authors declare no other competing interests.

References

This article includes 58 references
  1. Buchner HHF. Gait adaptation in lameness. In Equine Locomotion (eds. Clayton, H. M. & Back, W.) 175 (2013).
  2. Serra Bragança FM, Rhodin M, Van Weeren PR. On the brink of daily clinical application of objective gait analysis: What evidence do we have so far from studies using an induced lameness model?. Vet. J. 2018;234:11–23.
    doi: 10.1016/j.tvjl.2018.01.006pubmed: 29680381google scholar: lookup
  3. Clayton HM, Hobbs SJ. Ground reaction forces: The Sine Qua Non of legged locomotion. J. Equine Vet. Sci. 2019;76:25–35.
    doi: 10.1016/j.jevs.2019.02.022pubmed: 31084749google scholar: lookup
  4. Ishihara A, Bertone AL, Rajala-Schultz PJ. Association between subjective lameness grade and kinetic gait parameters in horses with experimentally induced forelimb lameness. Am. J. Vet. Res. 2005;66:1805–1815.
    doi: 10.2460/ajvr.2005.66.1805pubmed: 16273915google scholar: lookup
  5. Weishaupt MA, Wiestner T, Hogg HP, Jordan P, Auer JA. Compensatory load redistribution of horses with induced weight-bearing forelimb lameness trotting on a treadmill. Vet. J. 2006;171:135–146.
    doi: 10.1016/j.tvjl.2004.09.004pubmed: 15974567google scholar: lookup
  6. Serra Bragança FM. Adaptation strategies of horses with induced forelimb lameness walking on a treadmill. Equine Vet. J. 2020.
    doi: 10.1111/evj.13344pmc: PMC8048804pubmed: 32888199google scholar: lookup
  7. Weishaupt MA, Wiestner T, Hogg HP, Jordan P, Auer JA. Compensatory load redistribution of horses with induced weightbearing hindlimb lameness trotting on a treadmill. Equine Vet. J. 2004;36(1):727–733.
    doi: 10.2746/0425164044848244pubmed: 15656505google scholar: lookup
  8. Clayton HM, Schamhardt HC, Willemen MA, Lanovaz JL, Colborne GR. Kinematics and ground reaction forces in horses with superficial digital flexor tendinitis. Am. J. Vet. Res. 2000;61(2):191–196.
    doi: 10.2460/ajvr.2000.61.191pubmed: 10685692google scholar: lookup
  9. Abdelhadi J. Load redistribution in walking and trotting beagles with induced forelimb lameness. Am. J. Vet. Res. 2013;74(1):34–39.
    doi: 10.2460/ajvr.74.1.34pubmed: 23270343google scholar: lookup
  10. Fanchon L, Grandjean D. Reaction forces for diagnosis of hind limb lameness in dogs. Am. J. Vet. Res. 2007;68(10):1089–1094.
    doi: 10.2460/ajvr.68.10.1089pubmed: 17916016google scholar: lookup
  11. Fischer S, Anders A, Nolte I, Schilling N. Compensatory load redistribution in walking and trotting dogs with hind limb lameness. Vet. J. 2013;197(3):746–752.
    doi: 10.1016/j.tvjl.2013.04.009pubmed: 23683534google scholar: lookup
  12. Rajkondawar PG. A system for identifying lameness in dairy cattle. Appl. Eng. Agric. 2002;18:87–96.
    doi: 10.13031/2013.7707google scholar: lookup
  13. Merkens HW, Schamhardt HC, Osch GJVM, Bogert AJ. Ground reaction force patterns of Dutch Warmblood horses at normal trot. Equine Vet. J. 1993;25(2):134–137.
    doi: 10.1111/j.2042-3306.1993.tb02923.xpubmed: 8467772google scholar: lookup
  14. Merkens HW, Schamhardt HC, Hartman W, Kersjes AW. Ground reaction force patterns of Dutch Warmblood horses at normal walk. Equine Vet. J. 1986;18(3):207–214.
    doi: 10.1111/j.2042-3306.1986.tb03600.xpubmed: 3732241google scholar: lookup
  15. Oosterlinck M, Pille F, Huppes T, Gasthuys F, Back W. Comparison of pressure plate and force plate gait kinetics in sound Warmbloods at walk and trot. Vet. J. 2010;186(3):347–351.
    doi: 10.1016/j.tvjl.2009.08.024pubmed: 19751984google scholar: lookup
  16. Weishaupt MA. Instrumented treadmill for measuring vertical ground reaction forces in horses. Am. J. Vet. Res. 2002;63(4):520–527.
    doi: 10.2460/ajvr.2002.63.520pubmed: 11939313google scholar: lookup
  17. Chateau H. Biomechanical analysis of hoof landing and stride parameters in harness trotter horses running on different tracks of a sand beach (from wet to dry) and on an asphalt road. Equine Vet. J. 2010;42(s38):488–495.
    doi: 10.1111/j.2042-3306.2010.00277.xpubmed: 21059050google scholar: lookup
  18. Munoz-Nates F. External forces and impulses applied to the hind limb of 3 jumping horses at take-off-effects of the fence’s height. Comput. Methods Biomech. Biomed. Eng. 2019;22(sup1):S516–S518.
    doi: 10.1080/10255842.2020.1715002google scholar: lookup
  19. Lanovaz JL, Clayton HM, Colborne GR, Schamhardt HC. Forelimb kinematics and net joint moments during the swing phase of the trot. Equine Vet. J. 1999;30:235–239.
    doi: 10.1111/j.2042-3306.1999.tb05225.xpubmed: 10659259google scholar: lookup
  20. Rumpler B, Riha A, Licka T, Kotschwar A, Peham C. Influence of shoes with different weights on the motion of the limbs in Icelandic horses during toelt at different speeds. Equine Vet. J. 2010;38:451–454.
    doi: 10.1111/j.2042-3306.2010.00231.xpubmed: 21059044google scholar: lookup
  21. Willemen MA, Savelberg HH, Bruin G, Barneveld A. The effect of toe weights on linear and temporal stride characteristics of standardbred trotters. Vet. Q. 1994;16(Suppl 2):S97–100.
    doi: 10.1080/01652176.1994.9694511pubmed: 7801511google scholar: lookup
  22. Keegan KG. Evidence-based lameness detection and quantification. Vet. Clin. N. Am. Equine Pract. 2007;23(2):403–423.
    doi: 10.1016/j.cveq.2007.04.008pubmed: 17616320google scholar: lookup
  23. Witte TH, Knill K, Wilson AM. Determination of peak vertical ground reaction force from duty factor in the horse (Equus caballus). J. Exp. Biol. 2004;207:3639–3648.
    doi: 10.1242/jeb.01182pubmed: 15371472google scholar: lookup
  24. Alexander RMN, Maloiy GMO, Hunter B, Jayes AS, Nturibi J. Mechanical stresses in fast locomotion of buffalo (Syncews coffer) and elephant (Loxodonta africana). J. Zool. 1979;189:135–144.
    doi: 10.1111/j.1469-7998.1979.tb03956.xgoogle scholar: lookup
  25. Bobbert MF, Alvarez CBG, Van Weeren PR, Roepstorff L, Weishaupt MA. Validation of vertical ground reaction forces on individual limbs calculated from kinematics of horse locomotion. J. Exp. Biol. 2007;210:1885–1896.
    doi: 10.1242/jeb.02774pubmed: 17515415google scholar: lookup
  26. Roepstorff C. Modelling fore- and hindlimb peak vertical force differences in trotting horses using upper body kinematic asymmetry variables. J. Biomech. 2022;137:111097.
    doi: 10.1016/j.jbiomech.2022.111097pubmed: 35468550google scholar: lookup
  27. Gurchiek RD, Cheney N, McGinnis RS. Estimating biomechanical time-series with wearable sensors: A systematic review of machine learning techniques. Sensors 2019;19(23):5227.
    doi: 10.3390/s19235227pmc: PMC6928851pubmed: 31795151google scholar: lookup
  28. Alcantara RS, Edwards WB, Millet GY, Grabowski AM. Predicting continuous ground reaction forces from accelerometers during uphill and downhill running: A recurrent neural network solution. PeerJ 2022;10:e12752.
    doi: 10.7717/peerj.12752pmc: PMC8740512pubmed: 35036107google scholar: lookup
  29. Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9(8):1735–1780.
    doi: 10.1162/neco.1997.9.8.1735pubmed: 9377276google scholar: lookup
  30. Clayton HM. Comparison of the stride kinematics of the collected, working, medium and extended trot in horses. Equine Vet. J. 1994;26(3):230–234.
    doi: 10.1111/j.2042-3306.1994.tb04375.xpubmed: 8542844google scholar: lookup
  31. Clayton HM. Comparison of the collected, working, medium and extended canters. Equine Vet. J. 1994;26:16–19.
    doi: 10.1111/j.2042-3306.1994.tb04866.xpubmed: 8542844google scholar: lookup
  32. Deuel NR, Lawrence LM. Gallop velocity and limb contact variables of quarter horses. J. Equine Vet. Sci. 1986;6:143–147.
    doi: 10.1016/S0737-0806(86)80064-8google scholar: lookup
  33. Zips S, Peham C, Scheidl M, Llckat T, Girtler D. Motion pattern of the toelt of Icelandic horses at different speeds. Equine Vet. J. 2001;33:109–111.
    doi: 10.1111/j.2042-3306.2001.tb05371.xpubmed: 11721548google scholar: lookup
  34. Nicodemus MC, Clayton HM. Temporal variables of four-beat, stepping gaits of gaited horses. Appl. Anim. Behav. Sci. 2003;80:133–142.
    doi: 10.1016/S0168-1591(02)00219-8google scholar: lookup
  35. Weishaupt MA, Waldern NM, Amport C, Ramseier LC, Wiestner T. Effects of shoeing on intra- and inter-limb coordination and movement consistency in Icelandic horses at walk, tölt and trot. Vet. J. 2013;198:e109–e113.
    doi: 10.1016/j.tvjl.2013.09.043pubmed: 24345777google scholar: lookup
  36. Serra Bragança FM. Improving gait classification in horses by using inertial measurement unit (IMU) generated data and machine learning. Sci. Rep. 2020;10:17785.
    doi: 10.1038/s41598-020-73215-9pmc: PMC7576586pubmed: 33082367google scholar: lookup
  37. Mouloodi S. What can artificial intelligence and machine learning tell us? A review of applications to equine biomechanical research. J. Mech. Behav. Biomed. Mater. 2021;123:104728.
    doi: 10.1016/j.jmbbm.2021.104728pubmed: 34412024google scholar: lookup
  38. Savelberg HHCM, Loon T, Schamhardt HC. Ground reaction forces in horses, assessed from hoof wall deformation using artificial neural networks. Equine Vet. J. 1997;29:6–8.
    doi: 10.1111/j.2042-3306.1997.tb05041.xpubmed: 9354277google scholar: lookup
  39. Mouloodi S. The use of deep learning algorithms to predict mechanical strain from linear acceleration and angular rates of motion recorded from a horse hoof during exercise. Int. J. Mech. Sci. 2022;216:106972.
    doi: 10.1016/j.ijmecsci.2021.106972google scholar: lookup
  40. Schobesberger H, Peham C. Computerized detection of supporting forelimb lameness in the horse using an artificial neural network. Vet. J. 2002;163:77–84.
    doi: 10.1053/tvjl.2001.0608pubmed: 11749140google scholar: lookup
  41. Feuser A-K, Gesell-May S, Müller T, May A. Artificial intelligence for lameness detection in horses-a preliminary study. Animals 2022;12(20):37–45.
    doi: 10.3390/ani12202804pmc: PMC9597839pubmed: 36290189google scholar: lookup
  42. Yigit T. Wearable inertial sensor-based limb lameness detection and pose estimation for horses. IEEE Trans. Autom. Sci. Eng. 2022;19(3):1365–1379.
    doi: 10.1109/TASE.2022.3157793google scholar: lookup
  43. Wouda FJ. Estimation of vertical ground reaction forces and sagittal knee kinematics during running using three inertial sensors. Front. Physiol. 2018;9:218.
    doi: 10.3389/fphys.2018.00218pmc: PMC5874328pubmed: 29623042google scholar: lookup
  44. Ueda Y, Niki Y, Yoshida K, Masumitsu H. Force plate study of equine biomechanics floor reaction force of normal walking and trotting horses. Bull. Equine Res. Inst. 1981;18:28–41.
  45. Niki Y, Ueda Y, Yoshida K, Masumitsu H. A force plate study in equine biomechanics 2. The vertical and fore-aft components of floor reaction forces and motion of equine limbs at walk and trot. Bull. Equine Res. Inst. 1982;19:1–17.
  46. Merkens HW, Schamhardt HC. Distribution of ground reaction forces of the concurrently loaded limbs of the Dutch Warmblood horse at the normal walk. Equine Vet. J. 1988;20:209–213.
    doi: 10.1111/j.2042-3306.1988.tb01501.xpubmed: 3402418google scholar: lookup
  47. Hodson E, Clayton HM, Lanovaz JL. The forelimb in walking horses: 1. Kinematics and ground reaction forces. Equine Vet. J. 2000;32:287–294.
    doi: 10.2746/042516400777032237pubmed: 10952376google scholar: lookup
  48. Weishaupt MA, Hogg HP, Auer JA, Wiestner T. Velocity-dependent changes of time, force and spatial parameters in Warmblood horses walking and trotting on a treadmill. Equine Vet. J. 2010;42(s38):530–537.
    doi: 10.1111/j.2042-3306.2010.00190.xpubmed: 21059056google scholar: lookup
  49. Serra Bragança FM. Adaptation strategies of horses with induced forelimb lameness walking on a treadmill. Equine Vet. J. 2021;53:600–611.
    doi: 10.1111/evj.13344pmc: PMC8048804pubmed: 32888199google scholar: lookup
  50. Merkens HW, Schamhardt HC. Evaluation of equine locomotion during different degrees of experimentally induced lameness II: Distribution of ground reaction force patterns of the concurrently loaded limbs. Equine Vet. J. 1988;20:107–112.
    doi: 10.1111/j.2042-3306.1988.tb04656.xpubmed: 9079071google scholar: lookup
  51. Hobbs SJ, Clayton HM. Sagittal plane ground reaction forces, centre of pressure and centre of mass in trotting horses. Vet. J. 2013;198:e14–e19.
    doi: 10.1016/j.tvjl.2013.09.027pubmed: 24138935google scholar: lookup
  52. Buchner HHF, Savelberg HHCM, Schamhardt HC, Merkens HW, Barneveld A. Kinematics of treadmill versus overground locomotion in horses. Vet. Q. 1994;16:87–90.
    doi: 10.1080/01652176.1994.9694509pubmed: 7801509google scholar: lookup
  53. Smit IH. Continuous versus discrete data analysis for gait evaluation of horses with induced bilateral hindlimb lameness. Equine Vet. J. 2021;54(3):626–633.
    doi: 10.1111/evj.13451pmc: PMC9290451pubmed: 34085312google scholar: lookup
  54. Bosch S. EquiMoves: A wireless networked inertial measurement system for objective examination of horse gait. Sensors 2018;18:850.
    doi: 10.3390/s18030850pmc: PMC5877382pubmed: 29534022google scholar: lookup
  55. Bragança FM. Validation of distal limb mounted inertial measurement unit sensors for stride detection in Warmblood horses at walk and trot. Equine Vet. J. 2017;49:545–551.
    doi: 10.1111/evj.12651pmc: PMC5484301pubmed: 27862238google scholar: lookup
  56. Jiménez AB, Lázaro JL, Dorronsoro JR. Finding optimal model parameters by discrete grid search. In: Corchado E, et al., editors. Innovations in Hybrid Intelligent Systems. Berlin, Heidelberg: Springer; 2007.
  57. Robinson RO, Herzog W, Nigg BM. Use of force platform variables to quantify the effects of chiropractic manipulation on gait symmetry. J. Manip. Physiol. Ther. 1987;10:172–176.
    pubmed: 2958572
  58. Bland JM, Altman DG. Agreement between methods of measurement with multiple observations per individual. J. Biopharm. Stat. 2007;17:571–582.
    doi: 10.1080/10543400701329422pubmed: 17613642google scholar: lookup

Citations

This article has been cited 4 times.
  1. Poizat E, Gérard M, Macaire C, De Azevedo E, Denoix JM, Coudry V, Jacquet S, Bertoni L, Tallaj A, Audigié F, Hatrisse C, Hébert C, Martin P, Marin F, Hanne-Poujade S, Chateau H. Discrimination of the Lame Limb in Horses Using a Machine Learning Method (Support Vector Machine) Based on Asymmetry Indices Measured by the EQUISYM System. Sensors (Basel) 2025 Feb 12;25(4).
    doi: 10.3390/s25041095pubmed: 40006323google scholar: lookup
  2. Siegers EW, Parmentier JIM, Sloet van Oldruitenborgh-Oosterbaan MM, Munsters CCBM, Serra Bragança FM. Gait kinematics at trot before and after repeated ridden exercise tests in young Friesian stallions during a fatiguing 10-week training program. Front Vet Sci 2025;12:1456424.
    doi: 10.3389/fvets.2025.1456424pubmed: 39995550google scholar: lookup
  3. Fercher C, Bartsch J, Kluge S, Schneider F, Liedtke AM, Schleichardt A, Ueberschär O. Applying Multi-Purpose Commercial Inertial Sensors for Monitoring Equine Locomotion in Equestrian Training. Sensors (Basel) 2024 Dec 21;24(24).
    doi: 10.3390/s24248170pubmed: 39771905google scholar: lookup
  4. Belyaev RI, Boeskorov GG, Kuznetsov AN, Rotonda M, Prilepskaya NE. Comparative study of the body proportions in Elephantidae and other large herbivorous mammals. J Anat 2025 Jan;246(1):63-85.
    doi: 10.1111/joa.14143pubmed: 39395275google scholar: lookup
Subscribe to our newsletter
Join 99,824 horse owners like you who receive our email updates on horse health and nutrition.