FREE SHIPPING over $40
OVER 10000 FIVE-STAR REVIEWS
5% OFF ALL SUBSCRIPTIONS
100% HAPPINESS GUARANTEE
Analyze Diet
0
Animals : an open access journal from MDPI2025; 15(8); doi: 10.3390/ani15081080

Detecting Equine Gaits Through Rider-Worn Accelerometers.

Abstract: Automatic horse gait classification offers insights into training intensity, but directsensor attachment to horses raises concerns about discomfort, behavioral disruption, andentanglement risks. To address this, our study leverages rider-centric accelerometers formovement classification. The position of a sensor, sampling frequency, and window size ofsegmented signal data have a major impact on classification accuracy in activity recognition.Yet, there are no studies that have evaluated the effect of all these factors simultaneouslyusing accelerometer data from four distinct rider locations (the knee, backbone, chest, andarm) across five riders and seven horses performing three gaits. A total of eight modelswere compared, and an LSTM-convolutional network (ConvLSTM2D) achieved the highestaccuracy, with an average accuracy of 89.72% considering four movements (halt, walk,trot, and canter). The model performed best with an interval width of four seconds anda sampling frequency of 25 Hz. Additionally, an F1-score of 86.18% was achieved andvalidated using LOSOCV (Leave One Subject Out Cross-Validation).
Get Full Text
Publication Date: 2025-04-08 PubMed ID: 40281916PubMed Central: PMC12024389DOI: 10.3390/ani15081080Google 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 study explores the use of accelerometers worn by horse riders for identifying horse gaits rather than attaching sensors directly to the horses. Through data gathered from various rider positions, it was found that a combination of LSTM and a convolutional network provided the highest accuracy for gait classification.

Research Objectives and Approach

  • The aim of this research was to utilize wearable accelerometers on riders as a means of identifying horse gaits, providing an alternative to potentially uncomfortable or disruptive sensors attached directly to the horses.
  • Four rider locations were selected for sensor placement – knee, backbone, chest, and arm – and data was collected from five riders and seven horses performing three different gaits.
  • The position of the sensor, the frequency with which data was sampled, and the size of the window of segmented signal data were considered for their impact on classification accuracy.

Methodology and Analysis

  • A total of eight models were compared to determine the most accurate in classifying horse gaits based on the sensor data collected.
  • The study applied LSTM (Long Short-Term Memory) and a convolutional network (ConvLSTM2D) to analyze the data, testing intervals of four seconds at a sampling frequency of 25 Hz.

Findings

  • The ConvLSTM2D model achieved the highest accuracy out of the eight compared, averaging 89.72% in identifying four distinct movements – halt, walk, trot, and canter.
  • The best performance was achieved with an interval width of four seconds and a sampling frequency of 25 Hz.
  • The model also achieved an F1-score of 86.18% and was validated using LOSOCV (Leave One Subject Out Cross-Validation), a specific technique for validating models by training the model on all but one of the test subjects and then testing on the left-out subject.

Significance

  • The research introduces a novel approach of using rider-worn sensors to classify horse gaits, overcoming concerns around direct attachment of sensors to horses.
  • It demonstrates that rider-centric accelerometers coupled with proper data modeling can yield high accuracy for gait classification.
  • The findings highlight the potential for further applications of this method in studying training intensity for both horse and rider.

Cite This Article

APA
Schampheleer J, Eerdekens A, Joseph W, Martens L, Deruyck M. (2025). Detecting Equine Gaits Through Rider-Worn Accelerometers. Animals (Basel), 15(8). https://doi.org/10.3390/ani15081080

Publication

Animals : an open access journal from MDPI
ISSN: 2076-2615
NlmUniqueID: 101635614
Country: Switzerland
Language: English
Volume: 15
Issue: 8

Researcher Affiliations

Schampheleer, Jorn
  • WAVES, Department of Information Technology, Ghent University-IMEC, 9052 Ghent, Belgium.
Eerdekens, Anniek
  • WAVES, Department of Information Technology, Ghent University-IMEC, 9052 Ghent, Belgium.
Joseph, Wout
  • WAVES, Department of Information Technology, Ghent University-IMEC, 9052 Ghent, Belgium.
Martens, Luc
  • WAVES, Department of Information Technology, Ghent University-IMEC, 9052 Ghent, Belgium.
Deruyck, Margot
  • WAVES, Department of Information Technology, Ghent University-IMEC, 9052 Ghent, Belgium.

Conflict of Interest Statement

The authors declare no conflicts of interest.

References

This article includes 44 references
  1. Laricchia F. Global Connected Wearable Devices 2016–2022. Statista Hamburg, Germany: 2022.
  2. Kim E, Helal S, Cook D. Human Activity Recognition and Pattern Discovery. IEEE Pervasive Comput 2010;9:48–53.
    doi: 10.1109/MPRV.2010.7pmc: PMC3023457pubmed: 21258659google scholar: lookup
  3. Mao A, Huang E, Wang X, Liu K. Deep learning-based animal activity recognition with wearable sensors: Overview, challenges, and future directions. Comput. Electron. Agric. 2023;211:108043.
    doi: 10.1016/j.compag.2023.108043google scholar: lookup
  4. Munsters C.C.B.M., van Iwaarden A, van Weeren R, Sloet van Oldruitenborgh-Oosterbaan M.M.. Exercise testing in Warmblood sport horses under field conditions. Vet. J. 2014;202:11–19.
    doi: 10.1016/j.tvjl.2014.07.019pubmed: 25172838google scholar: lookup
  5. Robilliard J, Pfau T, Wilson A. Gait characterisation and classification in horses. J. Exp. Biol. 2007;210:187–197.
    doi: 10.1242/jeb.02611pubmed: 17210956google scholar: lookup
  6. Bosch S, Bragança F.S., Marin-Perianu M, Marin-Perianu R, Zwaag B.J.v.d., Voskamp J, Back W, Weeren R.V., Havinga P. 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
  7. 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 2021;11:2904.
    doi: 10.3390/ani11102904pmc: PMC8532712pubmed: 34679925google scholar: lookup
  8. Casella E, Khamesi A.R., Silvestri S. A framework for the recognition of horse gaits through wearable devices. Pervasive Mob. Comput. 2020;67:101213.
    doi: 10.1016/j.pmcj.2020.101213google scholar: lookup
  9. Alessandrini M, Biagetti G, Crippa P, Falaschetti L, Turchetti C. Recurrent Neural Network for Human Activity Recognition in Embedded Systems Using PPG and Accelerometer Data. Electronics 2021;10:1715.
    doi: 10.3390/electronics10141715google scholar: lookup
  10. Agarwal P, Alam M. A Lightweight Deep Learning Model for Human Activity Recognition on Edge Devices. Procedia Comput. Sci. 2020;167:2364–2373.
    doi: 10.1016/j.procs.2020.03.289google scholar: lookup
  11. Mekruksavanich S, Jitpattanakul A. Biometric User Identification Based on Human Activity Recognition Using Wearable Sensors: An Experiment Using Deep Learning Models. Electronics 2021;10:308.
    doi: 10.3390/electronics10030308google scholar: lookup
  12. Fridriksdottir E, Bonomi A.G. Accelerometer-Based Human Activity Recognition for Patient Monitoring Using a Deep Neural Network. Sensors 2020;20:6424.
    doi: 10.3390/s20226424pmc: PMC7697281pubmed: 33182813google scholar: lookup
  13. Conners M.G, Michelot T, Heywood E.I, Orben R.A, Phillips R.A, Vyssotski A.L, Shaffer S.A, Thorne L.H. Hidden Markov models identify major movement modes in accelerometer and magnetometer data from four albatross species. Mov. Ecol. 2021;9:7.
    doi: 10.1186/s40462-021-00243-zpmc: PMC7901071pubmed: 33618773google scholar: lookup
  14. Hussain A, Begum K, Armand T.P.T., Mozumder M.A.I, Ali S, Kim H.C, Joo M.I. Long Short-Term Memory (LSTM)-Based Dog Activity Detection Using Accelerometer and Gyroscope. Appl. Sci. 2022;12:9427.
    doi: 10.3390/app12199427google scholar: lookup
  15. Kasnesis P, Doulgerakis V, Uzunidis D, Kogias D.G, Funcia S.I, González M.B, Giannousis C, Patrikakis C.Z. Deep Learning Empowered Wearable-Based Behavior Recognition for Search and Rescue Dogs. Sensors 2022;22:993.
    doi: 10.3390/s22030993pmc: PMC8840386pubmed: 35161741google scholar: lookup
  16. Schmeling L, Elmamooz G, Hoang P.T, Kozar A, Nicklas D, Sünkel M, Thurner S, Rauch E. Training and Validating a Machine Learning Model for the Sensor-Based Monitoring of Lying Behavior in Dairy Cows on Pasture and in the Barn. Animals 2021;11:2660.
    doi: 10.3390/ani11092660pmc: PMC8468529pubmed: 34573627google scholar: lookup
  17. Bloch V, Frondelius L, Arcidiacono C, Mancino M, Pastell M. Development and Analysis of a CNN- and Transfer-Learning-Based Classification Model for Automated Dairy Cow Feeding Behavior Recognition from Accelerometer Data. Sensors 2023;23:2611.
    doi: 10.3390/s23052611pmc: PMC10006954pubmed: 36904813google scholar: lookup
  18. Voorend R.W.A. Deep Unsupervised Representation Learning For Animal Activity Recognition. University of Twente Enschede, The Netherlands: 2021.
  19. Arablouei R, Wang L, Currie L, Yates J, Alvarenga F.A.P., Bishop-Hurley G.J. Animal behavior classification via deep learning on embedded systems. Comput. Electron. Agric. 2023;207:107707.
    doi: 10.1016/j.compag.2023.107707google scholar: lookup
  20. Eerdekens A, Deruyck M, Fontaine J, Martens L, De Poorter E, Plets D, Joseph W. A framework for energy-efficient equine activity recognition with leg accelerometers. Comput. Electron. Agric. 2021;183:106020.
    doi: 10.1016/j.compag.2021.106020google scholar: lookup
  21. Birant D, Tepe E. Classifying horse activities with big data using machine learning. Kuwait J. Sci. 2022.
    doi: 10.48129/kjs.splml.19571google scholar: lookup
  22. Hysenllari E, Ottenbacher J, McLennan D. Validation of human activity recognition using a convolutional neural network on accelerometer and gyroscope data. Ger. J. Exerc. Sport Res. 2022;52:248–252.
    doi: 10.1007/s12662-022-00817-ygoogle scholar: lookup
  23. Kleanthous N, Hussain A, Khan W, Sneddon J, Liatsis P. Deep transfer learning in sheep activity recognition using accelerometer data. Expert Syst. Appl. 2022;207:117925.
    doi: 10.1016/j.eswa.2022.117925google scholar: lookup
  24. Kleanthous N, Hussain A.J., Khan W, Sneddon J, Al-Shamma’a A, Liatsis P. A survey of machine learning approaches in animal behaviour. Neurocomputing 2022;491:442–463.
    doi: 10.1016/j.neucom.2021.10.126google scholar: lookup
  25. Decandia M, Giovanetti V, Molle G, Acciaro M, Mameli M, Cabiddu A, Cossu R, Serra M.G., Manca C, Rassu S.P.G.. The effect of different time epoch settings on the classification of sheep behaviour using tri-axial accelerometry. Comput. Electron. Agric. 2018;154:112–119.
    doi: 10.1016/j.compag.2018.09.002google scholar: lookup
  26. Alvarenga F.A.P., Borges I, Palkovič L, Rodina J, Oddy V.H., Dobos R.C. Using a three-axis accelerometer to identify and classify sheep behaviour at pasture. Appl. Anim. Behav. Sci. 2016;181:91–99.
    doi: 10.1016/j.applanim.2016.05.026google scholar: lookup
  27. Hobbs S.J., Licka T, Polman R. The difference in kinematics of horses walking, trotting and cantering on a flat and banked 10 m circle. Equine Vet. J. 2011;43:686–694.
    doi: 10.1111/j.2042-3306.2010.00334.xpubmed: 21496095google scholar: lookup
  28. Back W, Clayton H.M.. Equine Locomotion. 2nd ed. Saunders Ltd.; Edinburgh, Scotland: London, UK: New York, NY, USA: 2013.
  29. Pfau T, Reilly P. How low can we go? Influence of sample rate on equine pelvic displacement calculated from inertial sensor data. Equine Vet. J. 2021;53:1075–1081.
    doi: 10.1111/evj.13371pubmed: 33113248google scholar: lookup
  30. Rhodin M, Smit I.H., Persson-Sjodin E, Pfau T, Gunnarsson V, Björnsdóttir S, Zetterberg E, Clayton H.M., Hobbs S.J., Serra Bragança F. Timing of Vertical Head, Withers and Pelvis Movements Relative to the Footfalls in Different Equine Gaits and Breeds. Animals 2022;12:3053.
    doi: 10.3390/ani12213053pmc: PMC9657284pubmed: 36359178google scholar: lookup
  31. . ELAN | The Language Archive. [(accessed on 2 March 2023)].
  32. Pfau T, Guire R. Automated Detection of Basic Equestrian Exercises Based on Smartphone Accelerometer Data. Equine Vet. J. 2016;48:36.
    doi: 10.1111/evj.72_12595google scholar: lookup
  33. Debauche O, Elmoulat M, Mahmoudi S, Bindelle J, Lebeau F. Farm Animals’ Behaviors and Welfare Analysis with AI Algorithms: A Review. Rev. D’Intelligence Artif. 2021;35:243–253.
    doi: 10.18280/ria.350308google scholar: lookup
  34. Oord A.v.d., Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A, Kavukcuoglu K. WaveNet: A Generative Model for Raw Audio. arXiv 2016.
    doi: 10.48550/arXiv.1609.03499google scholar: lookup
  35. Pfau T, Witte T, Wilson A. Centre of mass movement and mechanical energy fluctuation during gallop locomotion in the Thoroughbred racehorse. J. Exp. Biol. 2006;209:3742–3757.
    doi: 10.1242/jeb.02439pubmed: 16985191google scholar: lookup
  36. Hobbs S.J., Clayton H.M.. 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
  37. Buchner H.H.F., Obermüller S, Scheidl M. Body Centre of Mass Movement in the Sound Horse. Vet. J. 2000;160:225–234.
    doi: 10.1053/tvjl.2000.0507pubmed: 11061959google scholar: lookup
  38. Jorna L. Een Stille Hand … Is Voortdurend in Beweging. 2020 [(accessed on 19 April 2023)].
  39. Eisersiö M. The Movement of the Rider’s Hand Related to the Horse’s Behaviour and the Stride Cycle. Swedish University of Agricultural Sciences; Uppsala, Sverige: 2012.
  40. Heroy A, Gill Z, Sprague S, Stroud D, Santerre J. Stationary Exercise Classification using IMUs and Deep Learning. SMU Data Sci. Rev. 2020;3:1.
  41. Vesa A, Antal M, Antal C, Anghel I, Cioara T, Salomie I. Human Activity Recognition using Smartphone Sensors and Beacon-based Indoor Localization for Ambient Assisted Living Systems. Proceedings of the 2020 IEEE 16th International Conference on Intelligent Computer Communication and Processing (ICCP); Cluj-Napoca, Romania. 3–5 September 2020.
    doi: 10.1109/ICCP51029.2020.9266158google scholar: lookup
  42. Kamminga J.W., Meratnia N, Havinga P.J. Dataset: Horse Movement Data and Analysis of Its Potential for Activity Recognition. Proceedings of the 2nd Workshop on Data Acquisition to Analysis (DATA’19); New York, NY, USA. 10 November 2019; pp. 22–25.
    doi: 10.1145/3359427.3361908google scholar: lookup
  43. Kleanthous N, Hussain A, Khan W, Sneddon J, Mason A. Feature Extraction and Random Forest to Identify Sheep Behavior from Accelerometer Data. In: Huang D.S., Premaratne P., editors. Proceedings of the Intelligent Computing Methodologies; Cham, Switzerland. 5 October 2020; Cham, Switzerland: Springer; 2020. pp. 408–419. Lecture Notes in Computer Science.
    doi: 10.1007/978-3-030-60796-8_35google scholar: lookup
  44. Maga M, Björnsdotter S. Development of Equine Gait Recognition Algorithm. Master’s Thesis. Lund University; Lund, Sverige: 2017.

Citations

This article has been cited 1 times.
  1. Liu H, Song P, Xin X, Rong Y, Gao J, Wang Z, Zhang Y. A Cattle Behavior Recognition Method Based on Graph Neural Network Compression on the Edge. Animals (Basel) 2026 Jan 29;16(3).
    doi: 10.3390/ani16030430pubmed: 41681413google scholar: lookup
Subscribe to our newsletter
Join 99,780 horse owners like you who receive our email updates on horse health and nutrition.