kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Digital Coaching for Tennis Serve with Machine Learning
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems.
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Digital coaching för tennisserve med maskinlärning (Swedish)
Abstract [en]

This project develops a novel approach to analysis and understanding of tennis shot and serve performance, with the help of machine learning for digital coaching purposes. Using the PlayReplay system, two models are developed to generate shot return probabilities and quantified serve quality. Shot return probability is used to provide insight into the decisiveness of a shot and its effectiveness. Built on that, serve quality is measured as the impact of such serves on subsequent shots, allowing for a more comprehensive understanding of serve quality. Key metrics for both shots and serves are computed on multiple samples obtained by rigorous data collection in other to maximize models’ performance. Ultimately, this mentioned process allows the development of a final tool that offers specific feature analysis of a given serve, providing a suggestion on performance improvement of serve. The results show the potential of machine learning and data driven techniques to be implemented in real world scenarios and be used by players and coaches to improve player performance. 

Abstract [sv]

Detta projekt utvecklar ett nytt tillvägagångssätt för analys och förståelse av tennisslag och serveprestationer, med hjälp av maskininlärning för digitala coachningsändamål. Med hjälp av PlayReplay-systemet utvecklas två modeller för att generera skottretursannolikheter och kvantifierad servekvalitet. Sannolikhet för skottretur används för att ge insikt i ett skotts beslutsamhet och dess effektivitet. Baserad på det mäts servekvaliteten som effekten av sådana servar på efterföljande skott, vilket möjliggör en mer omfattande förståelse av servens kvalitet. Nyckelmått för både skott och servar beräknas på flera exempel som erhållits genom noggrann datainsamling i andra för att maximera modellernas prestanda. I slutändan tillåter den här nämnda processen utvecklingen av ett sista verktyg som erbjuder specifik funktionsanalys av en given serve, vilket ger ett förslag på prestandaförbättring av serven. Resultaten visar potentialen hos maskininlärning och datadrivna tekniker att implementeras i verkliga scenarier och användas av spelare och tränare för att förbättra spelarens prestation.

Place, publisher, year, edition, pages
2024. , p. 53
Series
TRITA-CBH-GRU ; 2024:336
Keywords [en]
Digital coaching, tennis, serve, shot, sports performance, machine learning
Keywords [sv]
Digital coaching, tennis, serve, skott, sportprestationer, maskininlärning
National Category
Electrical Engineering, Electronic Engineering, Information Engineering Sport and Fitness Sciences Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-356896OAI: oai:DiVA.org:kth-356896DiVA, id: diva2:1915806
Educational program
Master of Science - Sports Technology
Supervisors
Examiners
Available from: 2024-11-25 Created: 2024-11-25 Last updated: 2025-02-11Bibliographically approved

Open Access in DiVA

fulltext(1389 kB)116 downloads
File information
File name FULLTEXT01.pdfFile size 1389 kBChecksum SHA-512
8a683f6c8a7173bf7c5f3a3347d90ef857cb29b37d21b2f96ef9315e59e1b4952660b5a749546d5ff0a7bf3ca9f6e81f9925c324b296ef9d426db3a1d86a8f08
Type fulltextMimetype application/pdf

By organisation
Biomedical Engineering and Health Systems
Electrical Engineering, Electronic Engineering, Information EngineeringSport and Fitness SciencesComputer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 117 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 376 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf