{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T20:16:25Z","timestamp":1790799385448,"version":"4.1.0"},"reference-count":44,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T00:00:00Z","timestamp":1744070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Animals"],"abstract":"<jats:p>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).<\/jats:p>","DOI":"10.3390\/ani15081080","type":"journal-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T03:32:53Z","timestamp":1744169573000},"page":"1080","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Detecting Equine Gaits Through Rider-Worn Accelerometers"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7194-6298","authenticated-orcid":false,"given":"Jorn","family":"Schampheleer","sequence":"first","affiliation":[{"name":"WAVES, Department of Information Technology, Ghent University-IMEC, 9052 Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9544-4904","authenticated-orcid":false,"given":"Anniek","family":"Eerdekens","sequence":"additional","affiliation":[{"name":"WAVES, Department of Information Technology, Ghent University-IMEC, 9052 Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8807-0673","authenticated-orcid":false,"given":"Wout","family":"Joseph","sequence":"additional","affiliation":[{"name":"WAVES, Department of Information Technology, Ghent University-IMEC, 9052 Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9948-9157","authenticated-orcid":false,"given":"Luc","family":"Martens","sequence":"additional","affiliation":[{"name":"WAVES, Department of Information Technology, Ghent University-IMEC, 9052 Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0816-6465","authenticated-orcid":false,"given":"Margot","family":"Deruyck","sequence":"additional","affiliation":[{"name":"WAVES, Department of Information Technology, Ghent University-IMEC, 9052 Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,8]]},"reference":[{"key":"ref_1","unstructured":"Laricchia, F. (2022). Global Connected Wearable Devices 2016\u20132022, Statista."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1109\/MPRV.2010.7","article-title":"Human Activity Recognition and Pattern Discovery","volume":"9","author":"Kim","year":"2010","journal-title":"IEEE Pervasive Comput."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"108043","DOI":"10.1016\/j.compag.2023.108043","article-title":"Deep learning-based animal activity recognition with wearable sensors: Overview, challenges, and future directions","volume":"211","author":"Mao","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.tvjl.2014.07.019","article-title":"Exercise testing in Warmblood sport horses under field conditions","volume":"202","author":"Munsters","year":"2014","journal-title":"Vet. J."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1242\/jeb.02611","article-title":"Gait characterisation and classification in horses","volume":"210","author":"Robilliard","year":"2007","journal-title":"J. Exp. Biol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Bosch, S., Bragan\u00e7a, F.S., Marin-Perianu, M., Marin-Perianu, R., Zwaag, B.J.v.d., Voskamp, J., Back, W., Weeren, R.V., and Havinga, P. (2018). Equimoves: A wireless networked inertial measurement system for objective examination of horse gait. Sensors, 18.","DOI":"10.3390\/s18030850"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Eerdekens, A., Deruyck, M., Fontaine, J., Damiaans, B., Martens, L., De Poorter, E., Govaere, J., Plets, D., and Joseph, W. (2021). Horse Jumping and Dressage Training Activity Detection Using Accelerometer Data. Animals, 11.","DOI":"10.3390\/ani11102904"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"101213","DOI":"10.1016\/j.pmcj.2020.101213","article-title":"A framework for the recognition of horse gaits through wearable devices","volume":"67","author":"Casella","year":"2020","journal-title":"Pervasive Mob. Comput."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Alessandrini, M., Biagetti, G., Crippa, P., Falaschetti, L., and Turchetti, C. (2021). Recurrent Neural Network for Human Activity Recognition in Embedded Systems Using PPG and Accelerometer Data. Electronics, 10.","DOI":"10.3390\/electronics10141715"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2364","DOI":"10.1016\/j.procs.2020.03.289","article-title":"A Lightweight Deep Learning Model for Human Activity Recognition on Edge Devices","volume":"167","author":"Agarwal","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Mekruksavanich, S., and Jitpattanakul, A. (2021). Biometric User Identification Based on Human Activity Recognition Using Wearable Sensors: An Experiment Using Deep Learning Models. Electronics, 10.","DOI":"10.3390\/electronics10030308"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Fridriksdottir, E., and Bonomi, A.G. (2020). Accelerometer-Based Human Activity Recognition for Patient Monitoring Using a Deep Neural Network. Sensors, 20.","DOI":"10.3390\/s20226424"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/s40462-021-00243-z","article-title":"Hidden Markov models identify major movement modes in accelerometer and magnetometer data from four albatross species","volume":"9","author":"Conners","year":"2021","journal-title":"Mov. Ecol."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hussain, A., Begum, K., Armand, T.P.T., Mozumder, M.A.I., Ali, S., Kim, H.C., and Joo, M.I. (2022). Long Short-Term Memory (LSTM)-Based Dog Activity Detection Using Accelerometer and Gyroscope. Appl. Sci., 12.","DOI":"10.3390\/app12199427"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kasnesis, P., Doulgerakis, V., Uzunidis, D., Kogias, D.G., Funcia, S.I., Gonz\u00e1lez, M.B., Giannousis, C., and Patrikakis, C.Z. (2022). Deep Learning Empowered Wearable-Based Behavior Recognition for Search and Rescue Dogs. Sensors, 22.","DOI":"10.3390\/s22030993"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Schmeling, L., Elmamooz, G., Hoang, P.T., Kozar, A., Nicklas, D., S\u00fcnkel, M., Thurner, S., and Rauch, E. (2021). 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, 11.","DOI":"10.3390\/ani11092660"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bloch, V., Frondelius, L., Arcidiacono, C., Mancino, M., and Pastell, M. (2023). Development and Analysis of a CNN- and Transfer-Learning-Based Classification Model for Automated Dairy Cow Feeding Behavior Recognition from Accelerometer Data. Sensors, 23.","DOI":"10.3390\/s23052611"},{"key":"ref_18","unstructured":"Voorend, R.W.A. (2021). Deep Unsupervised Representation Learning For Animal Activity Recognition, University of Twente."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"107707","DOI":"10.1016\/j.compag.2023.107707","article-title":"Animal behavior classification via deep learning on embedded systems","volume":"207","author":"Arablouei","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"106020","DOI":"10.1016\/j.compag.2021.106020","article-title":"A framework for energy-efficient equine activity recognition with leg accelerometers","volume":"183","author":"Eerdekens","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Birant, D., and Tepe, E. (2022). Classifying horse activities with big data using machine learning. Kuwait J. Sci.","DOI":"10.48129\/kjs.splml.19571"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1007\/s12662-022-00817-y","article-title":"Validation of human activity recognition using a convolutional neural network on accelerometer and gyroscope data","volume":"52","author":"Hysenllari","year":"2022","journal-title":"Ger. J. Exerc. Sport Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"117925","DOI":"10.1016\/j.eswa.2022.117925","article-title":"Deep transfer learning in sheep activity recognition using accelerometer data","volume":"207","author":"Kleanthous","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1016\/j.neucom.2021.10.126","article-title":"A survey of machine learning approaches in animal behaviour","volume":"491","author":"Kleanthous","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.compag.2018.09.002","article-title":"The effect of different time epoch settings on the classification of sheep behaviour using tri-axial accelerometry","volume":"154","author":"Decandia","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.applanim.2016.05.026","article-title":"Using a three-axis accelerometer to identify and classify sheep behaviour at pasture","volume":"181","author":"Alvarenga","year":"2016","journal-title":"Appl. Anim. Behav. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1111\/j.2042-3306.2010.00334.x","article-title":"The difference in kinematics of horses walking, trotting and cantering on a flat and banked 10 m circle","volume":"43","author":"Hobbs","year":"2011","journal-title":"Equine Vet. J."},{"key":"ref_28","unstructured":"Back, W., and Clayton, H.M. (2013). Equine Locomotion, Saunders Ltd.. [2nd ed.]."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1111\/evj.13371","article-title":"How low can we go? Influence of sample rate on equine pelvic displacement calculated from inertial sensor data","volume":"53","author":"Pfau","year":"2021","journal-title":"Equine Vet. J."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Rhodin, M., Smit, I.H., Persson-Sjodin, E., Pfau, T., Gunnarsson, V., Bj\u00f6rnsd\u00f3ttir, S., Zetterberg, E., Clayton, H.M., Hobbs, S.J., and Serra Bragan\u00e7a, F. (2022). Timing of Vertical Head, Withers and Pelvis Movements Relative to the Footfalls in Different Equine Gaits and Breeds. Animals, 12.","DOI":"10.3390\/ani12213053"},{"key":"ref_31","unstructured":"(2023, March 02). ELAN | The Language Archive. Available online: https:\/\/archive.mpi.nl\/tla\/elan."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1111\/evj.72_12595","article-title":"Automated Detection of Basic Equestrian Exercises Based on Smartphone Accelerometer Data","volume":"48","author":"Pfau","year":"2016","journal-title":"Equine Vet. J."},{"key":"ref_33","first-page":"243","article-title":"Farm Animals\u2019 Behaviors and Welfare Analysis with AI Algorithms: A Review","volume":"35","author":"Debauche","year":"2021","journal-title":"Rev. D\u2019Intelligence Artif."},{"key":"ref_34","unstructured":"Oord, A.v.d., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., and Kavukcuoglu, K. (2016). WaveNet: A Generative Model for Raw Audio. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3742","DOI":"10.1242\/jeb.02439","article-title":"Centre of mass movement and mechanical energy fluctuation during gallop locomotion in the Thoroughbred racehorse","volume":"209","author":"Pfau","year":"2006","journal-title":"J. Exp. Biol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"e14","DOI":"10.1016\/j.tvjl.2013.09.027","article-title":"Sagittal plane ground reaction forces, centre of pressure and centre of mass in trotting horses","volume":"198","author":"Hobbs","year":"2013","journal-title":"Vet. J."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1053\/tvjl.2000.0507","article-title":"Body Centre of Mass Movement in the Sound Horse","volume":"160","author":"Buchner","year":"2000","journal-title":"Vet. J."},{"key":"ref_38","unstructured":"Jorna, L. (2023, April 19). Een Stille Hand \u2026 Is Voortdurend in Beweging. Available online: https:\/\/www.sporthorsemanshipunited.nl\/stillehand\/."},{"key":"ref_39","unstructured":"Eisersi\u00f6, M. (2012). The Movement of the Rider\u2019s Hand Related to the Horse\u2019s Behaviour and the Stride Cycle, Swedish University of Agricultural Sciences."},{"key":"ref_40","first-page":"1","article-title":"Stationary Exercise Classification using IMUs and Deep Learning","volume":"3","author":"Heroy","year":"2020","journal-title":"SMU Data Sci. Rev."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Vesa, A., Antal, M., Antal, C., Anghel, I., Cioara, T., and Salomie, I. (2020, January 3\u20135). 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.","DOI":"10.1109\/ICCP51029.2020.9266158"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Kamminga, J.W., Meratnia, N., and Havinga, P.J. (2019, January 10). Dataset: Horse Movement Data and Analysis of Its Potential for Activity Recognition. Proceedings of the 2nd Workshop on Data Acquisition to Analysis (DATA\u201919), New York, NY, USA.","DOI":"10.1145\/3359427.3361908"},{"key":"ref_43","unstructured":"Huang, D.S., and Premaratne, P. (2020, January 5). Feature Extraction and Random Forest to Identify Sheep Behavior from Accelerometer Data. Proceedings of the Intelligent Computing Methodologies, Cham, Switzerland. Lecture Notes in Computer Science."},{"key":"ref_44","unstructured":"Maga, M., and Bj\u00f6rnsdotter, S. (2017). Development of Equine Gait Recognition Algorithm. [Master\u2019s Thesis, Lund University]."}],"container-title":["Animals"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-2615\/15\/8\/1080\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:12:47Z","timestamp":1760029967000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-2615\/15\/8\/1080"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,8]]},"references-count":44,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["ani15081080"],"URL":"https:\/\/doi.org\/10.3390\/ani15081080","relation":{},"ISSN":["2076-2615"],"issn-type":[{"value":"2076-2615","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,8]]}}}