FREE SHIPPING over $40
OVER 9000 FIVE-STAR REVIEWS
5% OFF ALL SUBSCRIPTIONS
100% HAPPINESS GUARANTEE
Analyze Diet
0
Home / Equine Research Bank / Sci Rep / Improving gait classification in horses by using inertial me...
Scientific reports2020; 10(1); 17785; doi: 10.1038/s41598-020-73215-9

Improving gait classification in horses by using inertial measurement unit (IMU) generated data and machine learning.

Abstract: For centuries humans have been fascinated by the natural beauty of horses in motion and their different gaits. Gait classification (GC) is commonly performed through visual assessment and reliable, automated methods for real-time objective GC in horses are warranted. In this study, we used a full body network of wireless, high sampling-rate sensors combined with machine learning to fully automatically classify gait. Using data from 120 horses of four different domestic breeds, equipped with seven motion sensors, we included 7576 strides from eight different gaits. GC was trained using several machine-learning approaches, both from feature-extracted data and from raw sensor data. Our best GC model achieved 97% accuracy. Our technique facilitated accurate, GC that enables in-depth biomechanical studies and allows for highly accurate phenotyping of gait for genetic research and breeding. Our approach lends itself for potential use in other quadrupedal species without the need for developing gait/animal specific algorithms.
Get Full Text
Publication Date: 2020-10-20 PubMed ID: 33082367PubMed Central: PMC7576586DOI: 10.1038/s41598-020-73215-9Google 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.

This research study involves using a network of wireless sensors and machine learning to accurately identify different gaits in horses. The technique proved successful, achieving a 97% rate of accuracy, and may have applications for other four-legged species.

Study Objective and Methodology

  • The main objective of this study was to develop an automated, reliable method for real-time gait classification (GC) in horses. The researchers wanted a more objective method than visual assessment which has been commonly used till now.
  • The researchers employed a full body network of wireless, high sampling-rate sensors or inertial measurement unit (IMU) which were used in combination with machine learning to accomplish automatic classification of gait.
  • Data was gathered from 120 horses of four different domestic breeds. All horses were equipped with seven motion sensors and from these, data from a total of 7576 strides covering eight different gaits were included in the study.

Findings and Advancements

  • Gait classification was trained using various methods of machine learning. This was done by working with both raw sensor data and data from which features were extracted.
  • The best model developed through the use of machine learning for gait classification was able to achieve an impressive 97% accuracy. Thus proving the use of wireless sensors and machine learning in the gait classification of horses to be a successful technique.
  • This technique serves as an advancement in the field by facilitating accurate GC that can greatly help in conducting detailed biomechanical studies. It also enables highly accurate phenotyping of gait for genetic research and breeding in horses.

Potential Applications

  • One important aspect of this technique is its potential to be applied to other four-legged species. There is no need to develop species or gait-specific algorithms making this approach quite versatile.
  • Apart from benefiting horse breeding and studying horse biomechanics, this cutting edge combination of sensor technology and machine learning has the potential to significantly enhance our understanding and handling of other quadrupedal species.

Cite This Article

APA
Serra Bragança FM, Broomé S, Rhodin M, Björnsdóttir S, Gunnarsson V, Voskamp JP, Persson-Sjodin E, Back W, Lindgren G, Novoa-Bravo M, Gmel AI, Roepstorff C, van der Zwaag BJ, Van Weeren PR, Hernlund E. (2020). Improving gait classification in horses by using inertial measurement unit (IMU) generated data and machine learning. Sci Rep, 10(1), 17785. https://doi.org/10.1038/s41598-020-73215-9

Publication

Scientific reports
ISSN: 2045-2322
NlmUniqueID: 101563288
Country: England
Language: English
Volume: 10
Issue: 1
Pages: 17785

Researcher Affiliations

Serra Bragança, F M
  • Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, 3584CM, Utrecht, The Netherlands. f.m.serrabraganca@uu.nl.
Broomé, S
  • Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden.
Rhodin, M
  • Department of Anatomy, Physiology and Biochemistry, Swedish University of Agricultural Sciences, Uppsala, Sweden.
Björnsdóttir, S
  • Agricultural University of Iceland, Hvanneyri, Borgarnes, Iceland.
Gunnarsson, V
  • Department of Equine Science, Hólar University College, Hólar, Iceland.
Voskamp, J P
  • Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, 3584CM, Utrecht, The Netherlands.
Persson-Sjodin, E
  • Department of Anatomy, Physiology and Biochemistry, Swedish University of Agricultural Sciences, Uppsala, Sweden.
Back, W
  • Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, 3584CM, Utrecht, The Netherlands.
  • Department of Surgery and Anaesthesiology of Domestic Animals, Faculty of Veterinary Medicine, Ghent University, 9820, Merelbeke, Belgium.
Lindgren, G
  • Department of Animal Breeding and Genetics, Swedish University of Agricultural Sciences, 75007, Uppsala, Sweden.
  • Livestock Genetics, Department of Biosystems, KU Leuven, 3001, Leuven, Belgium.
Novoa-Bravo, M
  • Department of Animal Breeding and Genetics, Swedish University of Agricultural Sciences, 75007, Uppsala, Sweden.
  • Genética Animal de Colombia Ltda, Bogotá, Colombia.
Gmel, A I
  • Agroscope - Swiss National Stud Farm, Les Longs-Prés, 1580, Avenches, Switzerland.
  • Institute of Genetics, Vetsuisse Faculty, University of Bern, Bremgartenstrasse 109a, 3012 , Bern, Switzerland.
Roepstorff, C
  • Equine Department, Vetsuisse Faculty, University of Zurich, Winterthurerstrasse 260, 8057, Zurich, Switzerland.
van der Zwaag, B J
  • Inertia Technology B.V., Enschede, The Netherlands.
Van Weeren, P R
  • Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, 3584CM, Utrecht, The Netherlands.
Hernlund, E
  • Department of Anatomy, Physiology and Biochemistry, Swedish University of Agricultural Sciences, Uppsala, Sweden.

MeSH Terms

  • Algorithms
  • Animals
  • Automation / methods
  • Biomechanical Phenomena
  • Computer Simulation
  • Gait
  • Horses
  • Image Processing, Computer-Assisted / methods
  • Lameness, Animal / diagnosis
  • Machine Learning
  • Motion
  • Phenotype

Conflict of Interest Statement

The authors declare no competing interests.

References

This article includes 22 references
  1. Clayton, Hobbs. A review of biomechanical gait classification with reference to collected trot, passage and piaffe in dressage horses.. Animals 2019;9:763.
    doi: 10.3390/ani9100763pmc: PMC6826507pubmed: 31623360google scholar: lookup
  2. Grillner S. Biological pattern generation: the cellular and computational logic of networks in motion.. Neuron 2006;52:751–766.
    doi: 10.1016/j.neuron.2006.11.008pubmed: 17145498google scholar: lookup
  3. Andersson LS. Mutations in DMRT3 affect locomotion in horses and spinal circuit function in mice.. Nature 2012;488:642–646.
    doi: 10.1038/nature11399pmc: PMC3523687pubmed: 22932389google scholar: lookup
  4. Wutke S. The origin of ambling horses.. Curr. Biol. 2016;26:697–699.
    doi: 10.1016/j.cub.2016.07.001pubmed: 27505236google scholar: lookup
  5. Hildebrand M. Symmetrical gaits of horses.. Science 1965;150:701–708.
    doi: 10.1126/science.150.3697.701pubmed: 5844074google scholar: lookup
  6. Robilliard JJ, Pfau T, Wilson AM. Gait characterisation and classification in horses.. J. Exp. Biol. 2007;210:187–197.
    doi: 10.1242/jeb.02611pubmed: 17210956google scholar: lookup
  7. Starke SD, Robilliard JJ, Weller R, Wilson AM, Pfau T. Walk-run classification of symmetrical gaits in the horse: a multidimensional approach.. J. R. Soc. Interface 2009;6:335–342.
    doi: 10.1098/rsif.2008.0238pmc: PMC2658658pubmed: 18664427google scholar: lookup
  8. Egan S, Brama P, McGrath D. Research trends in equine movement analysis, future opportunities and potential barriers in the digital age: a scoping review from 1978 to 2018.. Equine Vet. J. 2019;51:813–824.
    doi: 10.1111/evj.13076pubmed: 30659639google scholar: lookup
  9. Serra Bragança FM. Validation of distal limb mounted imu sensors for stride detection and locomotor quantification in warmblood horses at walk and trot.. Equine Vet. J. 2016;48:17–17.
    pmc: PMC5484301pubmed: 27862238
  10. Keegan KG. Evidence-based lameness detection and quantification.. Vet. Clin. North Am. Equine Pract. 2007;23:403–423.
    doi: 10.1016/j.cveq.2007.04.008pubmed: 17616320google scholar: lookup
  11. Arkell M, Archer RM, Guitian FJ, May SA. Evidence of bias affecting the interpretation of the results of local anaesthetic nerve blocks when assessing lameness in horses.. Vet. Rec. 2006;159:346–349.
    doi: 10.1136/vr.159.11.346pubmed: 16963714google scholar: lookup
  12. Novoa-Bravo M. Selection on the Colombian Paso horse’s gaits has produced kinematic differences partly explained by the DMRT3 gene.. PLoS ONE 2018;13:e0202584.
    doi: 10.1371/journal.pone.0202584pmc: PMC6097835pubmed: 30118522google scholar: lookup
  13. Ablondi M, Viklund Å, Lindgren G, Eriksson S, Mikko S. Signatures of selection in the genome of Swedish warmblood horses selected for sport performance.. BMC Genom. 2019;20:1.
    doi: 10.1186/s12864-019-6079-1pmc: PMC6751828pubmed: 31533613google scholar: lookup
  14. 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
  15. Holt D, St. George LB, Clayton HM, Hobbs SJ. A simple method for equine kinematic gait event detection.. Equine Vet. J. 2017;49:688–619.
    doi: 10.1111/evj.12669pubmed: 28117488google scholar: lookup
  16. Olsen E, Andersen PH, Pfau T. Accuracy and precision of equine gait event detection during walking with limb and trunk mounted inertial sensors.. Sensors 2012;12:8145–8156.
    doi: 10.3390/s120608145pmc: PMC3436021pubmed: 22969392google scholar: lookup
  17. 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;42:530–537.
    doi: 10.1111/j.2042-3306.2010.00190.xpubmed: 21059056google scholar: lookup
  18. 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
  19. Ask K. Objective pain assessment during rest and locomotion in horses with two types of induced lameness.. Comp. Exerc. Physiol. 2018;14:42.
  20. St. George L, Spoormakers T, Serra Bragança FM, van Weeren PR, Hobbs SJ. The use of surface electromyography for quantification of changes in biceps femoris and triceps brachii muscle activity during induced forelimb and hindlimb lameness.. Equine Vet. J. 2019;51:28.
  21. Gunnarsson V. Objective evaluation of stride parameters in the five-gaited Icelandic horse.. Comp. Exerc. Physiol. 2018;14:S52.
  22. Weishaupt MA. Speed dependence of limb and body kinematics of horses walking and trotting on a treadmill.. Comp. Exerc. Physiol. 2018;14:S43.

Citations

This article has been cited 21 times.
  1. Schumacher A, Merle R, Stöckle S, Gehlen H. Player-Reported Perceptions of Lameness Risks and Contributing Factors for Polo Horses: Results from a Survey. Animals (Basel) 2025 Oct 29;15(21).
    doi: 10.3390/ani15213136pubmed: 41227466google scholar: lookup
  2. Staiger EA, Pereira de Toledo A, Rizzato Paschoal V, Patterson Rosa L. Variation in Four Horse Gait Categories Illustrated by Quantitative Analysis With ANALOC-E. Vet Med Int 2025;2025:4906015.
    doi: 10.1155/vmi/4906015pubmed: 40809801google scholar: lookup
  3. Samanci Tekin C, Kiliç Z. eHealth literacy and cancer screening attitudes among chronic patients. Sci Rep 2025 May 29;15(1):18877.
    doi: 10.1038/s41598-025-03595-3pubmed: 40442277google scholar: lookup
  4. Rhodin M, Serra Bragança FM, Persson-Sjodin E, Björnsdóttir S, Gunnarsdottir H, Gunnarsson V, Hernlund E, Smit IH. Adaptation strategies of Icelandic horses with induced transient hindlimb lameness at walk, trot and tölt. Equine Vet J 2026 Jan;58(1):230-242.
    doi: 10.1111/evj.14525pubmed: 40371819google scholar: lookup
  5. Akbarein H, Taaghi MH, Mohebbi M, Soufizadeh P. Applications and Considerations of Artificial Intelligence in Veterinary Sciences: A Narrative Review. Vet Med Sci 2025 May;11(3):e70315.
    doi: 10.1002/vms3.70315pubmed: 40173266google scholar: lookup
  6. 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
  7. 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
  8. Bussiman F, Richter J, Hidalgo J, Silva FFE, Ventura RV, Carvalho RSB, Mattos EC, Ferraz JBS, Eler JP, de Carvalho Balieiro JC. Bayesian Recursive and Structural Equation Models to Infer Causal Links Among Gait Visual Scores on Campolina Horses. J Anim Breed Genet 2025 Sep;142(5):463-477.
    doi: 10.1111/jbg.12919pubmed: 39698947google scholar: lookup
  9. Bussiman F, Alves AAC, Richter J, Hidalgo J, Veroneze R, Oliveira T. Supervised Machine Learning Techniques for Breeding Value Prediction in Horses: An Example Using Gait Visual Scores. Animals (Basel) 2024 Sep 20;14(18).
    doi: 10.3390/ani14182723pubmed: 39335312google scholar: lookup
  10. Gmel AI, Haraldsdóttir EH, Serra-Bragança F, Lamas LP, Rosa TV, Stefaniuk-Szmukier M, Klecel W, Neuditschko M, Weishaupt MA. Inertial sensor data of horses from four breeds at walk and trot in hand on a straight line. Data Brief 2024 Aug;55:110764.
    doi: 10.1016/j.dib.2024.110764pubmed: 39183964google scholar: lookup
  11. Calle-González N, Lo Feudo CM, Ferrucci F, Requena F, Stucchi L, Muñoz A. Objective Assessment of Equine Locomotor Symmetry Using an Inertial Sensor System and Artificial Intelligence: A Comparative Study. Animals (Basel) 2024 Mar 16;14(6).
    doi: 10.3390/ani14060921pubmed: 38540019google scholar: lookup
  12. 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
  13. Parmentier JIM, Bosch S, van der Zwaag BJ, Weishaupt MA, Gmel AI, Havinga PJM, van Weeren PR, Braganca FMS. Prediction of continuous and discrete kinetic parameters in horses from inertial measurement units data using recurrent artificial neural networks. Sci Rep 2023 Jan 13;13(1):740.
    doi: 10.1038/s41598-023-27899-4pubmed: 36639409google scholar: lookup
  14. Davíðsson HB, Rees T, Ólafsdóttir MR, Einarsson H. Efficient Development of Gait Classification Models for Five-Gaited Horses Based on Mobile Phone Sensors. Animals (Basel) 2023 Jan 3;13(1).
    doi: 10.3390/ani13010183pubmed: 36611791google scholar: lookup
  15. Rhodin M, Smit IH, Persson-Sjodin E, Pfau T, Gunnarsson V, Björnsdóttir S, Zetterberg E, Clayton HM, Hobbs SJ, Serra Bragança F, Hernlund E. Timing of Vertical Head, Withers and Pelvis Movements Relative to the Footfalls in Different Equine Gaits and Breeds. Animals (Basel) 2022 Nov 7;12(21).
    doi: 10.3390/ani12213053pubmed: 36359178google scholar: lookup
  16. Maldonado MD, Parkinson SD, Story MR, Haussler KK. The Effect of Chiropractic Treatment on Limb Lameness and Concurrent Axial Skeleton Pain and Dysfunction in Horses. Animals (Basel) 2022 Oct 19;12(20).
    doi: 10.3390/ani12202845pubmed: 36290230google scholar: lookup
  17. Topczewska J, Bartman J, Kwater T. Assessing the utility value of Hucul horses using classification models, based on artificial neural networks. PLoS One 2022;17(7):e0271340.
    doi: 10.1371/journal.pone.0271340pubmed: 35881630google scholar: lookup
  18. Pasquiet B, Biau S, Trébot Q, Debril JF, Durand F, Fradet L. Detection of Horse Locomotion Modifications Due to Training with Inertial Measurement Units: A Proof-of-Concept. Sensors (Basel) 2022 Jul 1;22(13).
    doi: 10.3390/s22134981pubmed: 35808476google scholar: lookup
  19. 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
  20. Tijssen M, Serra Braganςa FM, Ask K, Rhodin M, Andersen PH, Telezhenko E, Bergsten C, Nielen M, Hernlund E. Kinematic gait characteristics of straight line walk in clinically sound dairy cows. PLoS One 2021;16(7):e0253479.
    doi: 10.1371/journal.pone.0253479pubmed: 34288912google scholar: lookup
  21. 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
Subscribe to our newsletter
Join 99,359 horse owners like you who receive our email updates on horse health and nutrition.