{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T23:07:13Z","timestamp":1772060833423,"version":"3.50.1"},"reference-count":53,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T00:00:00Z","timestamp":1760400000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Tennis serves heavily impact match outcomes, yet analysis by coaches is limited by human vision. The design of an automated tennis serve analysis system could facilitate enhanced performance analysis. As serve location and serve success are directly correlated, predicting the outcome of a serve could provide vital information for performance analysis. This article proposes a tennis serve analysis system powered by Machine Learning, which classifies the outcome of serves as \u201cin\u201d, \u201cout\u201d or \u201cnet\u201d, and predicts the coordinate outcome of successful serves. Additionally, this work details the collection of three-dimensional spatio-temporal data on tennis serves, using marker-based optoelectronic motion capture. The classification uses a Stacked Bidirectional Long Short-Term Memory architecture, whilst a 3D Convolutional Neural Network architecture is harnessed for serve coordinate prediction. The proposed method achieves 89% accuracy for tennis serve classification, outperforming the current state-of-the-art whilst performing finer-grain classification. The results achieve an accuracy of 63% in predicting the serve coordinates, with a mean absolute error of 0.59 and a root mean squared error of 0.68, exceeding the current state-of-the-art with a new method. The system contributes towards the long-term goal of designing a non-invasive tennis serve analysis system that functions in training and match conditions.<\/jats:p>","DOI":"10.3390\/make7040118","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T14:34:15Z","timestamp":1760452455000},"page":"118","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploratory Proof-of-Concept: Predicting the Outcome of Tennis Serves Using Motion Capture and Deep Learning"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5167-9058","authenticated-orcid":false,"given":"Gustav","family":"Durlind","sequence":"first","affiliation":[{"name":"Department of Electronic and Electrical Engineering, University of Bath, Bath BA2 7AY, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9922-7912","authenticated-orcid":false,"given":"Uriel","family":"Martinez-Hernandez","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, University of Bath, Bath BA2 7AY, UK"},{"name":"Multimodal Interaction and Robot Active Perception (Inte-R-Action), University of Bath, Bath BA2 7AY, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9972-0275","authenticated-orcid":false,"given":"Tareq","family":"Assaf","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, University of Bath, Bath BA2 7AY, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Crego, R. (2003). Sports and Games of the 18th and 19th Centuries, Bloomsbury Academic.","DOI":"10.5040\/9798216987383"},{"key":"ref_2","unstructured":"ITF (2021). ITF Global Tennis Report, International Tennis Federation."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1533\/9781855738546.2.222","article-title":"Materials and tennis rackets","volume":"1","author":"Lammer","year":"2003","journal-title":"Mater. Sports Equip."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1080\/19346182.2008.9648446","article-title":"Review of tennis ball aerodynamics","volume":"1","author":"Mehta","year":"2008","journal-title":"Sports Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"107","DOI":"10.2478\/v10237-012-0006-6","article-title":"Hawk Eye: A logical innovative technology use in sports for effective decision making","volume":"21","author":"Bal","year":"2012","journal-title":"Sport Sci. Rev."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"175","DOI":"10.33545\/27077012.2022.v3.i2c.117","article-title":"Innovative evolution of technology used among racket sports: An overview","volume":"3","author":"Chauhan","year":"2022","journal-title":"J. Sports Sci. Nutr."},{"key":"ref_7","first-page":"1","article-title":"Sensors and data retention in Grand Slam tennis","volume":"1","author":"Larson","year":"2018","journal-title":"IEEE Sens. Appl. Symp."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1080\/24748668.2001.11868254","article-title":"Performance analysis: Can bringing together biomechanics and notational analysis benefit coaches?","volume":"1","author":"Bartlett","year":"2001","journal-title":"Int. J. Perform. Anal. Sport"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1123\/ijsb.2.4.260","article-title":"A three-dimensional cinematographic analysis of the tennis serve","volume":"2","author":"Elliott","year":"1986","journal-title":"Int. J. Sport Biomech."},{"key":"ref_10","first-page":"40","article-title":"Performance analysis in tennis since 2000: A systematic review focused on the methods of data collection","volume":"4","author":"Takahashi","year":"2022","journal-title":"Int. J. Racket Sport. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"103275","DOI":"10.1016\/j.cviu.2021.103275","article-title":"A review of 3D human pose estimation algorithms for markerless motion capture","volume":"212","author":"Desmarais","year":"2021","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_12","first-page":"141","article-title":"The relationships among stakeholders in the organization of men\u2019s professional tennis events","volume":"3","author":"Sorrentini","year":"2011","journal-title":"Glob. Bus. Manag. Res."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kovalchik, S. (2021). Why Tennis Is Still Not Ready to Play Moneyball. Harv. Data Sci. Rev., 3.","DOI":"10.1162\/99608f92.b665c0f4"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1017\/S193029750000869X","article-title":"Randomization and serial dependence in professional tennis matches: Do strategic considerations, player rankings and match characteristics matter?","volume":"13","author":"Spiliopoulos","year":"2018","journal-title":"Judgm. Decis. Mak."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1086\/732529","article-title":"Disequilibrium play in tennis","volume":"133","author":"Anderson","year":"2025","journal-title":"J. Polit. Econ."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Brefeld, U., Davis, J., Van Haaren, J., and Zimmermann, A. (2023). Predicting tennis serve directions with machine learning. Machine Learning and Data Mining for Sports Analytics, Springer Nature.","DOI":"10.1007\/978-3-031-27527-2"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Gourgari, S., Goudelis, G., Karpouzis, K., and Kollias, S. (2013, January 23\u201328). THETIS: Three dimensional tennis shots, a human action dataset. Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Portland, OR, USA.","DOI":"10.1109\/CVPRW.2013.102"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ni, J., and Wang, J. (2025). Tennis serve recognition based on bidirectional long- and short-term memory neural networks. Mol. Cell. Biomech., 22.","DOI":"10.62617\/mcb1546"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Sumi, K., Na, I.S., and Kaneko, N. (2022). Sequence recognition of indoor tennis actions using transfer learning and long short-term memory. Frontiers of Computer Vision, Springer International Publishing.","DOI":"10.1007\/978-3-031-06381-7"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Bayro-Corrochano, E., and Hancock, E. (2014, January 2\u20135). Modeling video activity with dynamic phrases and its application to action recognition in tennis videos. Proceedings of the Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, Puerto Vallarta, Mexico.","DOI":"10.1007\/978-3-319-12568-8"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Mora, S.V., and Knottenbelt, W.J. (2017, January 21\u201326). Deep learning for domain-specific action recognition in tennis. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.27"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1016\/j.neucom.2020.03.111","article-title":"Deep historical long short-term memory network for action recognition","volume":"407","author":"Cai","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"18093","DOI":"10.1007\/s00500-023-09215-4","article-title":"Hybrid LSTM and GAN model for action recognition and prediction of lawn tennis sport activities","volume":"27","author":"Sun","year":"2023","journal-title":"Soft Comput."},{"key":"ref_24","unstructured":"Jabaren, A. (2020). Tennis Serve Classification Using Machine Learning. [Ph.D. Thesis, University of California]."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wei, X., Lucey, P., Morgan, S., Carr, P., Reid, M., and Sridharan, S. (2015, January 10\u201313). Predicting serves in tennis using style priors. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, NSW, Australia.","DOI":"10.1145\/2783258.2788598"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1080\/02640414.2016.1183805","article-title":"Spatial characteristics of professional tennis serves with implications for serving aces: A machine learning approach","volume":"35","author":"Whiteside","year":"2017","journal-title":"J. Sports Sci."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1007\/s10479-021-04481-7","article-title":"The analysis of serve decisions in tennis using Bayesian hierarchical models","volume":"325","author":"Tea","year":"2022","journal-title":"Ann. Oper. Res."},{"key":"ref_28","unstructured":"Thanaporn, S., Kanongchaiyos, P., and Tangmanee, C. (2010, January 13\u201318). Using motion capture for analysis struggle of judo. Proceedings of the IEEE CVPR Workshops, San Francisco, CA, USA."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Noiumkar, S., and Tirakoat, S. (2013, January 4\u20136). Use of optical motion capture in sports science: A case study of golf swing. Proceedings of the 2013 International Conference on Informatics and Creative Multimedia, Kuala Lumpur, Malaysia.","DOI":"10.1109\/ICICM.2013.58"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1080\/14763141.2010.535843","article-title":"Effect of skill decomposition on racket and ball kinematics of the elite junior tennis serve","volume":"9","author":"Reid","year":"2010","journal-title":"Sports Biomech."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Cheze, L. (2015). Biom\u00e9canique du mouvement et mod\u00e9lisation musculo-squelettique. Technol. Biom\u00e9d.","DOI":"10.51257\/a-v1-med8050"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1249\/MSS.0b013e3182a45cca","article-title":"Back pain in tennis players: A link with lumbar serve kinematics and range of motion","volume":"46","author":"Campbell","year":"2014","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/S1440-2440(03)80011-7","article-title":"Technique effects on upper limb loading in the tennis serve","volume":"6","author":"Elliott","year":"2003","journal-title":"J. Sci. Med. Sport"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Skublewska-Paszkowska, M., Powroznik, P., and Lukasik, E. (2020). Learning three-dimensional tennis shots using graph convolutional networks. Sensors, 20.","DOI":"10.3390\/s20216094"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Skublewska-Paszkowska, M., Powroznik, P., and Lukasik, E. (2022, January 18\u201323). Attention temporal graph convolutional network for tennis groundstrokes phases classification. Proceedings of the 2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Padua, Italy.","DOI":"10.1109\/FUZZ-IEEE55066.2022.9882822"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Skublewska-Paszkowska, M., and Powroznik, P. (2023). Temporal pattern attention for multivariate time series of tennis strokes classification. Sensors, 23.","DOI":"10.3390\/s23052422"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1136\/bjsports-2012-091371","article-title":"Biomechanical analysis of three tennis serve types using a markerless system","volume":"48","author":"Abrams","year":"2014","journal-title":"Br. J. Sports Med."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1080\/14763141.2011.629302","article-title":"Review of tennis serve motion analysis and the biomechanics of three serve types with implications for injury","volume":"10","author":"Abrams","year":"2011","journal-title":"Sports Biomech."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1016\/j.proeng.2014.06.060","article-title":"Markerless Tracking of Tennis Racket Motion Using a Camera","volume":"72","author":"Elliott","year":"2014","journal-title":"Procedia Eng."},{"key":"ref_40","first-page":"27","article-title":"Comparison of markerless and marker-based motion capture for estimating external mechanical work in tennis: A pilot study","volume":"41","author":"Emmerson","year":"2023","journal-title":"ISBS Proc. Arch."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Vives, F., L\u00e1zaro, J., Guzm\u00e1n, J.F., Mart\u00ednez-Gallego, R., and Crespo, M. (2023). Optimizing Sporting Actions Effectiveness: A Machine Learning Approach to Uncover Key Variables in the Men\u2019s Professional Doubles Tennis Serve. Appl. Sci., 13.","DOI":"10.3390\/app132413213"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"11917","DOI":"10.1109\/JSEN.2024.3366781","article-title":"Comprehensive Tennis Serve Training System Based on Local Attention-Based CNN Model","volume":"24","author":"Ye","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"e70029","DOI":"10.1002\/cpe.70029","article-title":"Hybrid deep learning models for tennis action recognition: Enhancing professional training through CNN-BiLSTM integration","volume":"37","author":"Chen","year":"2025","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"ref_44","unstructured":"Gholamy, A., Kreinovich, V., and Kosheleva, O. (2024, May 07). Why 70\/30 or 80\/20 Relation Between Training and Testing Sets: A Pedagogical Explanation. Available online: https:\/\/scholarworks.utep.edu\/cs_techrep\/1209\/."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1063","DOI":"10.1016\/B978-0-323-95879-0.50178-8","article-title":"A Comparative Study on the Influence of Different Prediction Models on the Performance of Residual-based Monitoring Methods","volume":"51","author":"Ma","year":"2022","journal-title":"Comput. Aided Chem. Eng."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1016\/B978-0-323-88506-5.50086-3","article-title":"A Dual-Layer Attention-Based LSTM Network for Fed-batch Fermentation Process Modelling","volume":"50","author":"Liu","year":"2021","journal-title":"Comput. Aided Chem. Eng."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Hung, C.-L. (2023). Chapter 11\u2014Deep learning in biomedical informatics. Intelligent Nanotechnology, Elsevier. Merging Nanoscience and Artificial Intelligence Materials Today.","DOI":"10.1016\/B978-0-323-85796-3.00011-1"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"102674","DOI":"10.1016\/j.trc.2020.102674","article-title":"Stacked Bidirectional and Unidirectional LSTM Recurrent Neural Network for Forecasting Network-Wide Traffic State with Missing Values","volume":"118","author":"Cui","year":"2020","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Graves, A., Jaitly, N., and Mohamed, A. (2013). Hybrid Speech Recognition with Deep Bidirectional LSTM. Proc. IEEE ASRU, 273\u2013278.","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep Learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"101730","DOI":"10.1016\/j.media.2020.101730","article-title":"Deep learning with 4D spatio-temporal data representations for OCT-based force estimation","volume":"64","author":"Gessert","year":"2020","journal-title":"Med. Image Anal."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1007\/s13244-018-0639-9","article-title":"Convolutional neural networks: An overview and application in radiology","volume":"9","author":"Yamashita","year":"2018","journal-title":"Insights Imaging"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/3-540-46805-6_19","article-title":"Object recognition with gradient-based learning","volume":"1681","author":"LeCun","year":"1999","journal-title":"Lect. Notes Comput. Sci."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/4\/118\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T04:10:52Z","timestamp":1761106252000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/4\/118"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,14]]},"references-count":53,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["make7040118"],"URL":"https:\/\/doi.org\/10.3390\/make7040118","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,14]]}}}