FREE SHIPPING over $40
OVER 9000 FIVE-STAR REVIEWS
5% OFF ALL SUBSCRIPTIONS
100% HAPPINESS GUARANTEE
Analyze Diet
0
Home / Equine Research Bank / Animals (Basel) / Efficient Development of Gait Classification Models for Five...
Animals : an open access journal from MDPI2023; 13(1); doi: 10.3390/ani13010183

Efficient Development of Gait Classification Models for Five-Gaited Horses Based on Mobile Phone Sensors.

Abstract: Automated gait classification has traditionally been studied using horse-mounted sensors. However, smartphone-based sensors are more accessible, but the performance of gait classification models using data from such sensors has not been widely known or accessible. In this study, we performed horse gait classification using deep learning models and data from mobile phone sensors located in the rider's pocket. We gathered data from 17 horses and 14 riders. The data were gathered simultaneously from movement sensors in a mobile phone located in the rider's pocket and a gait classification system based on four wearable sensors attached to the horse's limbs. With this efficient approach to acquire labelled data, we trained a Bi-LSTM model for gait classification. The only input to the model was a 50 Hz signal from the phone's accelerometer and gyroscope that was rotated to the horse's frame of reference. We demonstrate that sensor data from mobile phones can be used to classify the five gaits of the Icelandic horse with up to 94.4% accuracy. The result suggests that horse riding activities can be studied at a large scale using mobile phones to gather data on gaits. While our study showed that mobile phone sensors could be effective for gait classification, there are still some limitations that need to be addressed in future research. For example, further studies could explore the effects of different riding styles or equipment on gait classification accuracy or investigate ways to minimize the influence of factors such as phone placement. By addressing these questions, we can continue to improve our understanding of horse gait and its role in horse riding activities.
Get Full Text
Publication Date: 2023-01-03 PubMed ID: 36611791PubMed Central: PMC9817528DOI: 10.3390/ani13010183Google 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 article focuses on the development of an efficient model for classifying horse gaits using mobile phone sensors, resulting in an accuracy of up to 94.4%.

Objective of the Study

  • The main goal of the study was to demonstrate the capabilities of mobile phone sensors in accurately classifying different horse gaits. While previous research leaned towards using horse-mounted sensors, this study focused on innovatively harnessing easily accessible mobile phone sensors.

Methodology of the Study

  • Data was collected from 17 horses and 14 riders. The horses had sensors attached to their limbs while the riders carried mobile phones in their pockets.
  • This approach intended to gather labeled data from both horse-based wearable sensors and mobile phone ones simultaneously, providing a more comprehensive data pool.
  • This collected data was then used to train a Bi-LSTM (Bidirectional Long Short-Term Memory) model, a type of deep learning neural network.
  • The only input to the model was a 50Hz signal from the phone’s accelerometer and gyroscope, rotated to match the horse’s frame of reference.

Results of the Study

  • The mobile phone-based gait classification model successfully managed to classify the five gaits of the Icelandic horse with an accuracy of up to 94.4%.
  • This result affirms the viability of using mobile phone sensors for large-scale studies of horse gaits during riding activities, offering a cost-efficient and accessible alternative to traditional horse-mounted sensors.

Limitations and Future Recommendations

  • Despite the promising results, the study acknowledged several limitations that require further research, such as the influence of differing riding styles or equipment on the accuracy of gait classification.
  • The model could also be improved by finding ways to minimize the impact of factors like the placement of the phone.
  • Addressing these limitations can potentially enhance the accuracy and versatility of gait classification models and increase our understanding of horse gait dynamics in a variety of horse riding scenarios.

Cite This Article

APA
Davíðsson HB, Rees T, Ólafsdóttir MR, Einarsson H. (2023). Efficient Development of Gait Classification Models for Five-Gaited Horses Based on Mobile Phone Sensors. Animals (Basel), 13(1). https://doi.org/10.3390/ani13010183

Publication

Animals : an open access journal from MDPI
ISSN: 2076-2615
NlmUniqueID: 101635614
Country: Switzerland
Language: English
Volume: 13
Issue: 1

Researcher Affiliations

Davíðsson, Haraldur B
  • Department of Computer Science, University of Iceland, 101 Reykjavík, Iceland.
  • Horseday ehf., 102 Reykjavík, Iceland.
Rees, Torben
  • TöltSense Ltd., Newton Abbot TQ12 5ND, UK.
Ólafsdóttir, Marta Rut
  • Horseday ehf., 102 Reykjavík, Iceland.
Einarsson, Hafsteinn
  • Department of Computer Science, University of Iceland, 101 Reykjavík, Iceland.

Grant Funding

  • Icelandic directorate of labour
  • Horseday ehf.
  • The University of Iceland

Conflict of Interest Statement

H.E. declares no conflict of interest. H.B.D.’s work in the summer of 2021 was partially funded by Horseday ehf., and he has been employed by Horseday ehf. since the fall of 2021. M.R.Ó. is a shareholder of Horseday ehf., and T.R. is the owner of Toltsense Ltd.

References

This article includes 34 references
  1. Hildebrand M. Symmetrical Gaits of Horses. Science 1965;150:701–708.
    doi: 10.1126/science.150.3697.701pubmed: 5844074google scholar: lookup
  2. Olsen E, Haubro Andersen P, 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
  3. Holt D, George L.B.S., Clayton H.M., Hobbs S.J. A simple method for equine kinematic gait event detection. Equine Vet. J. 2017;49:688–691.
    doi: 10.1111/evj.12669pubmed: 28117488google scholar: lookup
  4. Bosch S, Serra Bragança F, Marin-Perianu M, Marin-Perianu R, Van der Zwaag B.J, Voskamp J, Back W, Van Weeren R, 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
  5. 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
  6. Pasquiet B, Biau S, Trébot Q, Debril J.F, Durand F, Fradet L. Detection of Horse Locomotion Modifications Due to Training with Inertial Measurement Units: A Proof-of-Concept. Sensors 2022;22:4981.
    doi: 10.3390/s22134981pmc: PMC9269723pubmed: 35808476google scholar: lookup
  7. Robilliard J.J, Pfau T, Wilson A.M. Gait characterisation and classification in horses. J. Exp. Biol. 2007;210:187–197.
    doi: 10.1242/jeb.02611pubmed: 17210956google scholar: lookup
  8. Serra Bragança F.M, Broomé S, Rhodin M, Björnsdóttir S, Gunnarsson V, Voskamp J.P, Persson-Sjodin E, Back W, Lindgren G, Novoa-Bravo M. 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
  9. Pfau T, Weller R. Comparison of a standalone consumer grade smartphone with a specialist inertial measurement unit for quantification of movement symmetry in the trotting horse. Equine Vet. J. 2017;49:124–129.
    doi: 10.1111/evj.12529pubmed: 26518143google scholar: lookup
  10. Hochreiter S, Schmidhuber J. Long Short-Term Memory. Neural Comput. 1997;9:1735–1780.
    doi: 10.1162/neco.1997.9.8.1735pubmed: 9377276google scholar: lookup
  11. Eerdekens A, Deruyck M, Fontaine J, Martens L, De Poorter E. Automatic equine activity detection by convolutional neural networks using accelerometer data. Comput. Electron. Agric. 2020;168:105139.
    doi: 10.1016/j.compag.2019.105139google scholar: lookup
  12. Casella E, Khamesi A, 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
  13. Maga M, Björnsdotter S. Development of Equine Gait Recognition Algorithm. Master’s Thesis. Lund University; Lund, Sweden: 2017.
  14. Andersson L.S, Larhammar M, Memic F, Wootz H, Schwochow D, Rubin C.J, Patra K, Arnason T, Wellbring L, Hjälm G. 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
  15. Kristjánsson Þ, Reynisson G, Bárðarson S, Ævarsson S. The Gaits of the Icelandic Horse, Basic Definitions. 2014.
  16. Pfau T, Witte T.H, Wilson A.M. A method for deriving displacement data during cyclical movement using an inertial sensor. J. Exp. Biol. 2005;208:2503–2514.
    doi: 10.1242/jeb.01658pubmed: 15961737google scholar: lookup
  17. 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
  18. Chung J, Gulcehre C, Cho K, Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv 20141412.3555.
  19. Graves A, Schmidhuber J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 2005;18:602–610.
    doi: 10.1016/j.neunet.2005.06.042pubmed: 16112549google scholar: lookup
  20. Kingma D.P, Ba J. Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015; San Diego, CA, USA. 7–9 May 2015.
  21. Zips S, Peham C, Scheidl M, Licka 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
  22. Persson-Sjodin E, Hernlund E, Pfau T, Haubro Andersen P, Rhodin M. Influence of seating styles on head and pelvic vertical movement symmetry in horses ridden at trot. PLoS ONE 2018;13:e0195341.
    doi: 10.1371/journal.pone.0195341pmc: PMC5886531pubmed: 29621299google scholar: lookup
  23. Li S, Li W, Cook C, Zhu C, Gao Y. Independently recurrent neural network (indrnn): Building a longer and deeper rnn. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Salt Lake City, UT, USA. 18–23 June 2018; pp. 5457–5466.
  24. Khandelwal U, He H, Qi P, Jurafsky D. Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context. Proceedings of the Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); Melbourne, Australia. 15–20 July 2018; pp. 284–294.
  25. Kaur H, Pannu H.S, Malhi A.K. A Systematic Review on Imbalanced Data Challenges in Machine Learning: Applications and Solutions. ACM Comput. Surv. 2019;52:79:1–79:36.
    doi: 10.1145/3343440google scholar: lookup
  26. Serra Braganca F, Rhodin M, Wiestner T, Hernlund E, Pfau T, Van Weeren P, Weishaupt M.A. Quantification of the effect of instrumentation error in objective gait assessment in the horse on hindlimb symmetry parameters. Equine Vet. J. 2018;50:370–376.
    doi: 10.1111/evj.12766pmc: PMC5900976pubmed: 29032614google scholar: lookup
  27. Pfau T, Bruce O, Edwards W.B, Leguillette R. Stride frequency derived from GPS speed fluctuations in galloping horses. J. Biomech. 2022;145:111364.
    doi: 10.1016/j.jbiomech.2022.111364pubmed: 36343415google scholar: lookup
  28. Darbandi H, Serra Bragança F, van der Zwaag B.J, Voskamp J, Gmel A.I, Haraldsdóttir E.H, Havinga P. Using different combinations of body-mounted imu sensors to estimate speed of horses—A machine learning approach. Sensors 2021;21:798.
    doi: 10.3390/s21030798pmc: PMC7865839pubmed: 33530288google scholar: lookup
  29. Marunova E, Dod L, Witte S, Pfau T. Smartphone-Based Pelvic Movement Asymmetry Measures for Clinical Decision Making in Equine Lameness Assessment. Animals 2021;11:1665.
    doi: 10.3390/ani11061665pmc: PMC8228485pubmed: 34204921google scholar: lookup
  30. Keegan K.G, Kramer J, Yonezawa Y, Maki H, Pai P.F, Dent E.V, Kellerman T.E, Wilson D.A, Reed S.K. Assessment of repeatability of a wireless, inertial sensor–based lameness evaluation system for horses. Am. J. Vet. Res. 2011;72:1156–1163.
    doi: 10.2460/ajvr.72.9.1156pubmed: 21879972google scholar: lookup
  31. McCracken M.J, Kramer J, Keegan K.G, Lopes M, Wilson D.A, Reed S.K, LaCarrubba A, Rasch M. Comparison of an inertial sensor system of lameness quantification with subjective lameness evaluation. Equine Vet. J. 2012;44:652–656.
    doi: 10.1111/j.2042-3306.2012.00571.xpubmed: 22563674google scholar: lookup
  32. Yigit T, Han F, Rankins E, Yi J, McKeever K, Malinowski K. Wearable IMU-based Early Limb Lameness Detection for Horses using Multi-Layer Classifiers. Proceedings of the 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE); Hong Kong, China. 20–21 August 2020; pp. 955–960.
    doi: 10.1109/CASE48305.2020.9216873google scholar: lookup
  33. Keegan K.G. Evidence-based lameness detection and quantification. Vet. Clin. N. Am. Equine Pract. 2007;23:403–423.
    doi: 10.1016/j.cveq.2007.04.008pubmed: 17616320google scholar: lookup
  34. Arkell M, Archer R, Guitian F, May S. Evidence of bias affecting the interpretation of the results of local anaesthetic nerve blocks when assessing lameness in horses. Vet. Rec. 2006;159:346–348.
    doi: 10.1136/vr.159.11.346pubmed: 16963714google scholar: lookup
Subscribe to our newsletter
Join 99,359 horse owners like you who receive our email updates on horse health and nutrition.