Search Results

You are looking at 1 - 10 of 156 items for :

  • "machine learning" x
  • Refine by Access: All Content x
Clear All
Restricted access

S. Sofie Lövdal, Ruud J.R. Den Hartigh, and George Azzopardi

witnessed a growth in technologies and machine learning applications, which can be employed to make predictions about future performance, injuries, and thereby improve data-driven guidance in sports. 8 – 10 In the current study, we use a supervised machine learning approach, which relies principally on

Restricted access

Reed D. Gurchiek, Hasthika S. Rupasinghe Arachchige Don, Lasanthi C. R. Pelawa Watagoda, Ryan S. McGinnis, Herman van Werkhoven, Alan R. Needle, Jeffrey M. McBride, and Alan T. Arnholt

velocity estimation error. The MIMU methods discussed here are limited by sensor imperfections and model assumptions. In other biomechanics contexts, some employ machine learning (ML) techniques both for classification 14 – 17 and regression. 18 – 24 Mannini and Sabatini 18 estimated running speeds less

Restricted access

Anantha Narayanan, Farzanah Desai, Tom Stewart, Scott Duncan, and Lisa Mackay

but the use of cut points is still necessary when organizing these data into intensity categories. Manually defined algorithms have also been used to classify raw data into activity types with varying levels of success. 14 More recently, researchers have employed machine-learning techniques to

Restricted access

Arne Jaspers, Tim Op De Beéck, Michel S. Brink, Wouter G.P. Frencken, Filip Staes, Jesse J. Davis, and Werner F. Helsen

Australian football (AFL) found that artificial neural networks (ANNs), a machine learning approach, more accurately predicted the RPE in response to ELIs compared with traditional statistics. 9 Other machine learning techniques could be used for this task as well, and each technique has strengths and

Restricted access

Enrico Perri, Carlo Simonelli, Alessio Rossi, Athos Trecroci, Giampietro Alberti, and F. Marcello Iaia

. In recent years, data mining approaches have been gaining interest in sport science. Among these techniques, machine learning (ML) allows for the development of algorithms based on mathematical models able to discover multidimensional linear and nonlinear patterns in large data sets. 18 , 19

Restricted access

Yumeng Li, Shuqi Zhang, and Christina Odeh

, it is still unclear which postural control variables could be used for the early detection of PD. Machine learning is a branch of artificial intelligence that enables computer systems to learn from data and analyze data without being explicitly programmed. Interest in machine learning has grown

Open access

Kerstin Bach, Atle Kongsvold, Hilde Bårdstu, Ellen Marie Bardal, Håkon S. Kjærnli, Sverre Herland, Aleksej Logacjov, and Paul Jarle Mork

classify different postures and physical activity types by use of rule-based algorithms ( Crowley et al., 2019 ; Skotte et al., 2014 ) or machine learning classifiers ( Arvidsson et al., 2019 ; Narayanan et al., 2020 ; Stewart et al., 2018 ). Which postures and activity types that can be detected and

Restricted access

Scott Small, Sara Khalid, Paula Dhiman, Shing Chan, Dan Jackson, Aiden Doherty, and Andrew Price

 Hz with the AX3 accelerometer. The objectives were to: (a) identify any effect of sampling rate on device-measured activity for both overall and in specific free-living activities, (b) characterize the effect of reduced sampling rate on machine learning activity classification, and (c) develop a

Restricted access

Lenore Dedeyne, Jorgen A. Wullems, Jolan Dupont, Jos Tournoy, Evelien Gielen, and Sabine Verschueren

needed for exercise classification, state-of-the-art data processing techniques may also be required. Although traditional regression-based methods are sufficient for classifying linear data, such as walking, the nonlinear data registered during exercising require machine learning techniques. Previous

Restricted access

David Whiteside, Olivia Cant, Molly Connolly, and Machar Reid


Quantifying external workload is fundamental to training prescription in sport. In tennis, global positioning data are imprecise and fail to capture hitting loads. The current gold standard (manual notation) is time intensive and often not possible given players’ heavy travel schedules.


To develop an automated stroke-classification system to help quantify hitting load in tennis.


Nineteen athletes wore an inertial measurement unit (IMU) on their wrist during 66 video-recorded training sessions. Video footage was manually notated such that known shot type (serve, rally forehand, slice forehand, forehand volley, rally backhand, slice backhand, backhand volley, smash, or false positive) was associated with the corresponding IMU data for 28,582 shots. Six types of machine-learning models were then constructed to classify true shot type from the IMU signals.


Across 10-fold cross-validation, a cubic-kernel support vector machine classified binned shots (overhead, forehand, or backhand) with an accuracy of 97.4%. A second cubic-kernel support vector machine achieved 93.2% accuracy when classifying all 9 shot types.


With a view to monitoring external load, the combination of miniature inertial sensors and machine learning offers a practical and automated method of quantifying shot counts and discriminating shot types in elite tennis players.