Lucio Caprioli, Amani Najlaoui, Francesca Campoli, Aatheethyaa Dhanasekaran, Saeid Edriss, Cristian Romagnoli, Andrea Zanela, Elvira Padua, Vincenzo Bonaiuto, Giuseppe Annino
{"title":"Tennis Timing Assessment by a Machine Learning-Based Acoustic Detection System: A Pilot Study.","authors":"Lucio Caprioli, Amani Najlaoui, Francesca Campoli, Aatheethyaa Dhanasekaran, Saeid Edriss, Cristian Romagnoli, Andrea Zanela, Elvira Padua, Vincenzo Bonaiuto, Giuseppe Annino","doi":"10.3390/jfmk10010047","DOIUrl":null,"url":null,"abstract":"<p><p><b>Background/Objectives:</b> In tennis, timing plays a crucial factor as it influences the technique and effectiveness of strokes and, therefore, matches results. However, traditional technical evaluation methods rely on subjective observations or video motion-tracking technology, mainly focusing on spatial components. This study evaluated the reliability of an acoustic detection system in analyzing key temporal elements of the game, such as the rally rhythm and timing of strokes. <b>Methods:</b> Based on a machine learning algorithm, the proposed acoustic detection system classifies the sound of the ball's impact on the racket and the ground to measure the time between them and give immediate feedback to the player. We performed trials with expert and amateur players in controlled settings. <b>Results:</b> The ML algorithm showed a detection accuracy higher than 95%, while the average accuracy of the whole system that was applied on-court was 85%. Moreover, this system has proven effective in evaluating the technical skills of a group of players on the court and highlighting their areas for improvement, showing significant potential for practical applications in player training and performance analysis. <b>Conclusions:</b> Quantitatively assessing timing offers a new perspective for coaches and players to improve performance and technique, providing objective data to set training regimens and optimize game strategies.</p>","PeriodicalId":16052,"journal":{"name":"Journal of Functional Morphology and Kinesiology","volume":"10 1","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11843912/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Functional Morphology and Kinesiology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/jfmk10010047","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"SPORT SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Background/Objectives: In tennis, timing plays a crucial factor as it influences the technique and effectiveness of strokes and, therefore, matches results. However, traditional technical evaluation methods rely on subjective observations or video motion-tracking technology, mainly focusing on spatial components. This study evaluated the reliability of an acoustic detection system in analyzing key temporal elements of the game, such as the rally rhythm and timing of strokes. Methods: Based on a machine learning algorithm, the proposed acoustic detection system classifies the sound of the ball's impact on the racket and the ground to measure the time between them and give immediate feedback to the player. We performed trials with expert and amateur players in controlled settings. Results: The ML algorithm showed a detection accuracy higher than 95%, while the average accuracy of the whole system that was applied on-court was 85%. Moreover, this system has proven effective in evaluating the technical skills of a group of players on the court and highlighting their areas for improvement, showing significant potential for practical applications in player training and performance analysis. Conclusions: Quantitatively assessing timing offers a new perspective for coaches and players to improve performance and technique, providing objective data to set training regimens and optimize game strategies.