sensors-logo

Journal Browser

Journal Browser

Mobile Computing and Sensing for Sport Performance Analysis

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Physical Sensors".

Deadline for manuscript submissions: closed (25 February 2023) | Viewed by 11037
Please feel free to contact the Guest Editor or Special Issue Editor ([email protected]) for any queries.

Special Issue Editor


E-Mail Website
Guest Editor
Centre for Sport Science and University Sports, University of Vienna, Auf der Schmelz 6A, 1150 Wien, Austria
Interests: biomechanical research in sports; biomechanical modeling; human motion analysis; performance analysis; computer science in sport
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The availability of miniaturized and wireless sensor and computing technologies has created enormous potential for performance analysis in sport in recent years. The acquisition of performance-relevant parameter values ​​and their analysis is not limited to laboratory conditions, but can be carried out directly during training and competitions. Respective studies can, therefore, be performed under ecologically valid conditions. Measured or derived performance indicators can be passed on to coaches and advisors during the ongoing sporting activity or immediately afterward, and the athletes receive direct feedback and recommendations. The development and application of creative solutions can be observed in both individual and team sports, in elite and mass sports.

The rapid availability of manifold analysis results also offers innovative opportunities for media reporting to illustrate and visualize live and post-event news. New possibilities also arise in the context of the use of social media.

Due to the processing of sensitive personal information, appropriate measures must also be taken when developing respective systems to ensure mobile security.

This Special Issue deals with all facets of this subject area including technological approaches (sensors, communication, data processing units), system development and validation, system security, and applications.

Prof. Dr. Arnold Baca
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • ubiquitous computing in sports
  • intelligent systems
  • biomedical systems
  • feedback

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

10 pages, 420 KiB  
Article
Reliability of Repeated Isometric Neck Strength in Rugby Union Players Using a Load Cell Device
by Christian Chavarro-Nieto, Martyn Beaven, Nicholas Gill and Kim Hébert-Losier
Sensors 2022, 22(8), 2872; https://doi.org/10.3390/s22082872 - 8 Apr 2022
Cited by 2 | Viewed by 2058
Abstract
Concussion is the most common injury in professional Rugby Union (RU) players, with increasing incidence and severity each year. Strengthening the neck is an intervention used to decrease concussion incidence and severity, which can only be proven effective if strength neck measures are [...] Read more.
Concussion is the most common injury in professional Rugby Union (RU) players, with increasing incidence and severity each year. Strengthening the neck is an intervention used to decrease concussion incidence and severity, which can only be proven effective if strength neck measures are reliable. We conducted a repeated-measures reliability study with 23 male RU players. Neck strength was assessed seated in a ‘make’ test fashion in flexion, extension, and bilateral-side flexion. Flexion-to-extension and left-to-right side ratios were also computed. Three testing sessions were undertaken over three consecutive weeks. Intrasession and intersession reliabilities were assessed using typical errors, coefficient of variations (CV), and intraclass correlation coefficients (ICC). Intrasession reliability demonstrated good-to-excellent relative (ICC > 0.75) and good absolute (CV ≤ 20%) reliability in all directions (ICC = 0.86–0.95, CV = 6.4–8.8%), whereas intersession reliability showed fair relative (ICC: 0.40 to 0.75) and acceptable absolute (CV ≤ 20%) reliability for mean and maximal values (ICC = 0.51–0.69, CV = 14.5–19.8%). Intrasession reliability for flexion-to-extension ratio was good (relative, ICC = 0.86) and acceptable (absolute, CV = 11.5%) and was fair (relative, ICC = 0.75) and acceptable (absolute, CV = 11.5%) for left-to-right ratio. Intersession ratios from mean and maximal values were fair (relative, ICC = 0.52–0.55) but not always acceptable (absolute, CV = 16.8–24%). Assessing isometric neck strength with a head harness and a cable with a load cell device seated in semi-professional RU players is feasible and demonstrates good-to-excellent intrasession and fair intersession reliability. We provide data from RU players to inform practice and assist standardisation of testing methods. Full article
(This article belongs to the Special Issue Mobile Computing and Sensing for Sport Performance Analysis)
Show Figures

Figure 1

17 pages, 1237 KiB  
Article
Wearable Sensors for Activity Recognition in Ultimate Frisbee Using Convolutional Neural Networks and Transfer Learning
by Johannes Link, Timur Perst, Maike Stoeve and Bjoern M. Eskofier
Sensors 2022, 22(7), 2560; https://doi.org/10.3390/s22072560 - 27 Mar 2022
Cited by 9 | Viewed by 4246
Abstract
In human activity recognition (HAR), activities are automatically recognized and classified from a continuous stream of input sensor data. Although the scientific community has developed multiple approaches for various sports in recent years, marginal sports are rarely considered. These approaches cannot directly be [...] Read more.
In human activity recognition (HAR), activities are automatically recognized and classified from a continuous stream of input sensor data. Although the scientific community has developed multiple approaches for various sports in recent years, marginal sports are rarely considered. These approaches cannot directly be applied to marginal sports, where available data are sparse and costly to acquire. Thus, we recorded and annotated inertial measurement unit (IMU) data containing different types of Ultimate Frisbee throws to investigate whether Convolutional Neural Networks (CNNs) and transfer learning can solve this. The relevant actions were automatically detected and were classified using a CNN. The proposed pipeline reaches an accuracy of 66.6%, distinguishing between nine different fine-grained classes. For the classification of the three basic throwing techniques, we achieve an accuracy of 89.9%. Furthermore, the results were compared to a transfer learning-based approach using a beach volleyball dataset as the source. Even if transfer learning could not improve the classification accuracy, the training time was significantly reduced. Finally, the effect of transfer learning on a reduced dataset, i.e., without data augmentations, is analyzed. While having the same number of training subjects, using the pre-trained weights improves the generalization capabilities of the network, i.e., increasing the accuracy and F1 score. This shows that transfer learning can be beneficial, especially when dealing with small datasets, as in marginal sports, and therefore, can improve the tracking of marginal sports. Full article
(This article belongs to the Special Issue Mobile Computing and Sensing for Sport Performance Analysis)
Show Figures

Figure 1

28 pages, 7754 KiB  
Article
Mobile Computing with a Smart Cricket Ball: Discovery of Novel Performance Parameters and Their Practical Application to Performance Analysis, Advanced Profiling, Talent Identification and Training Interventions of Spin Bowlers
by Franz Konstantin Fuss, Batdelger Doljin and René E. D. Ferdinands
Sensors 2021, 21(20), 6942; https://doi.org/10.3390/s21206942 - 19 Oct 2021
Cited by 4 | Viewed by 3460
Abstract
Introduction: Profiling of cricket bowlers is performed with motion analyses systems that require the placement of markers on the bowler’s body and on the ball. Conventional smart balls such as cricket and baseballs provide only one speed and one spin rate datum at [...] Read more.
Introduction: Profiling of cricket bowlers is performed with motion analyses systems that require the placement of markers on the bowler’s body and on the ball. Conventional smart balls such as cricket and baseballs provide only one speed and one spin rate datum at the release point, which is insufficient for biomechanical profiling. Method: In this study, we used an advanced smart cricket ball that measures the angular velocity at 815 Hz and calculates four further physical performance parameters (resultant torque, spin torque, power and angular acceleration) and five new skill parameters (precession, normalised precession, precession torque, efficiency and ratio of angular acceleration to spin rate), which we used for profiling and talent identification of spin bowlers. Results: The results showed that the spin rate is a function of physical (torque) and skill proficiency, namely how efficiently the torque is converted to angular velocity rather than being wasted for precession. The kind of delivery also influences the efficiency, as finger-spin deliveries were less efficient than wrist-spin ones by 6.8% on average; and topspin deliveries were generally more efficient than backspin ones by 15% on average. We tested three bowlers in terms of physical and skill performance during a 10-over spell, revealing that some parameters can improve or decline. When profiling a topspinner, we detected from the performance parameters a lower skill performance than expected, because there was an initial arm motion for backspin delivery before releasing the ball with a topspin. After training intervention, the skill parameters improved significantly (the efficiency increased from 39% to 59%). Conclusions: The advanced smart cricket ball is a classic example of mobile computing for sport performance analysis that can conducted indoors as well as outdoors, generating instant data from 10 performance parameters that provide critical feedback to the coach and bowler. Full article
(This article belongs to the Special Issue Mobile Computing and Sensing for Sport Performance Analysis)
Show Figures

Graphical abstract

Back to TopTop