Submit to Special Issue Submit Abstract to Special Issue Review for Sensors Propose a Special Issue

Journal Browser

► Journal Browser

Sensors and Artificial Intelligence for Analyzing Human Behavior in Sports and Physical Activity

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

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

Deadline for manuscript submissions: 15 October 2024 | Viewed by 10153

Share This Special Issue

Special Issue Editors

Dr. John Komar

E-Mail Website
Guest Editor

Physical Education and Sports Sciences, National Institute of Education, Nanyang Technological University, 1 Nanyang Walk, Singapore 637616, Singapore
Interests: complexity; coordination; movement variability; pedagogy; performance analysis; data analytics

Prof. Dr. Ludovic Seifert

E-Mail Website
Guest Editor

CETAPS Lab., Faculty of Sport Sciences, University of Rouen, Boulevard Siegfried, 76821 Mont Saint Aignan CEDEX, France
Interests: ecological dynamics; complexity; skill acquisition; dynamical systems theory; performance analysis; expertise

Special Issue Information

Dear Colleagues,

The rapid development of motion sensors now allows the collection of data out of the laboratory during training but also during competitive events. Although the data availability and/or data accuracy may be lower compared to a laboratory-based analysis, the possibility to collect data live in the performance context appears key to obtaining relevant insights into the activity of the performers. As such, the benefits of an in situ analysis of the performers is the result of a constant balance between the raw data that can be captured in situ, the accuracy and reliability of those data, and the possible analysis to be performed to really access insights into the performance. For instance, in team sports, indoor and outdoor tracking technologies have helped to provide physical information on the team, but the absence of information on the opposition team as well as on the ball drastically limits the potential for technical and tactical analysis. To overcome this situation, machine learning could help to learn from a small sample of full data (i.e., both teams’ positional data) to predict where the opposition players will be. Similarly, automatic detection of technical actions using machine learning does not always require the collection of full body kinematics with the sensors. On the other hand, advancements in computer vision and body pose estimation also today allow the collection of positional and kinematics data on every player without the need to wear sensors.

This Special Issue intends to highlight research works wherein sensor technologies, coupled with advanced analysis, allow the collection of insights into sports performance in the actual performance environment. We welcome the submission of basic and applied research studies, tutorials, reviews, and position papers that address the use of motion sensors in physical activity and sport sciences. We will accept high-quality, original, unpublished papers that are not currently under review by any other journal or conference.

Dr. John Komar
Prof. Dr. Ludovic Seifert
Guest Editors

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

global positioning systems
inertial measurement units
indoor tracking
local positioning systems
performance analysis
motion analysis
computer vision
machine learning
positional data

Published Papers (6 papers)

Download All Papers

Research

22 pages, 594 KiB

Open AccessArticle

Engineering Features from Raw Sensor Data to Analyse Player Movements during Competition

by Valerio Antonini, Alessandra Mileo and Mark Roantree

Sensors 2024, 24(4), 1308; https://doi.org/10.3390/s24041308 - 18 Feb 2024

Viewed by 681

Abstract

Research in field sports often involves analysis of running performance profiles of players during competitive games with individual, per-position, and time-related descriptive statistics. Data are acquired through wearable technologies, which generally capture simple data points, which in the case of many team-based sports are times, latitudes, and longitudes. While the data capture is simple and in relatively high volumes, the raw data are unsuited to any form of analysis or machine learning functions. The main goal of this research is to develop a multistep feature engineering framework that delivers the transformation of sequential data into feature sets more suited to machine learning applications. Full article

(This article belongs to the Special Issue Sensors and Artificial Intelligence for Analyzing Human Behavior in Sports and Physical Activity)

► Show Figures

Figure 1

18 pages, 6045 KiB

Open AccessArticle

Automated Service Height Fault Detection Using Computer Vision and Machine Learning for Badminton Matches

by Guo Liang Goh, Guo Dong Goh, Jing Wen Pan, Phillis Soek Po Teng and Pui Wah Kong

Sensors 2023, 23(24), 9759; https://doi.org/10.3390/s23249759 - 11 Dec 2023

Cited by 4 | Viewed by 2558

Abstract

In badminton, accurate service height detection is critical for ensuring fairness. We developed an automated service fault detection system that employed computer vision and machine learning, specifically utilizing the YOLOv5 object detection model. Comprising two cameras and a workstation, our system identifies elements, such as shuttlecocks, rackets, players, and players’ shoes. We developed an algorithm that can pinpoint the shuttlecock hitting event to capture its height information. To assess the accuracy of the new system, we benchmarked the results against a high sample-rate motion capture system and conducted a comparative analysis with eight human judges that used a fixed height service tool in a backhand low service situation. Our findings revealed a substantial enhancement in accuracy compared with human judgement; the system outperformed human judges by 3.5 times, achieving a 58% accuracy rate for detecting service heights between 1.150 and 1.155 m, as opposed to a 16% accuracy rate for humans. The system we have developed offers a highly reliable solution, substantially enhancing the consistency and accuracy of service judgement calls in badminton matches and ensuring fairness in the sport. The system’s development signifies a meaningful step towards leveraging technology for precision and integrity in sports officiation. Full article

(This article belongs to the Special Issue Sensors and Artificial Intelligence for Analyzing Human Behavior in Sports and Physical Activity)

► Show Figures

Figure 1

10 pages, 797 KiB

Open AccessArticle

Physical Demands in the Worst-Case Scenarios of Elite Futsal Referees Using a Local Positioning System

by Gemma Martinez-Torremocha, Javier Sanchez-Sanchez, Antonio Alonso-Callejo, Maria Luisa Martin-Sanchez, Carlos Serrano, Leonor Gallardo, Jorge Garcia-Unanue and Jose Luis Felipe

Sensors 2023, 23(21), 8662; https://doi.org/10.3390/s23218662 - 24 Oct 2023

Cited by 1 | Viewed by 737

Abstract

The aim of this study is to analyze the worst-case scenarios of professional futsal referees during the first and second half of official matches in the Spanish Futsal Cup using a Local Positioning System (LPS) for monitoring their movement patterns. Eight professional futsal referees (40 ± 3.43 years; 1.80 ± 0.03 m; 72.84 ± 4.01 kg) participated in the study. The external load (total distance, high-speed running distance and efforts, sprint distance and efforts, and accelerations and decelerations distances) of the referees was monitored and collected using an LPS. The results revealed significant differences in the worst-case scenarios of the futsal referees during the match according to the time window analyzed (p < 0.05). The longest time windows (120 s, 180 s, and 300 s) showed lower relative total distances in the worst-case scenarios (p < 0.05). The high-speed running distances were significatively higher in the first half for the 120 s (+2.65 m·min⁻¹; ES: 1.25), 180 s (+1.55 m·min⁻¹; ES: 1.28), and 300 s (+0.95 m·min⁻¹; ES: 1.14) time windows (p < 0.05). No differences were found between the first and second half for the high-intensity deceleration distance (p > 0.05). These results will serve to prepare the referees in the best conditions for the competition and adapt the training plans to the worst-case scenarios. Full article

(This article belongs to the Special Issue Sensors and Artificial Intelligence for Analyzing Human Behavior in Sports and Physical Activity)

► Show Figures

Figure 1

11 pages, 2131 KiB

Open AccessArticle

Assessment of a New Change of Direction Detection Algorithm Based on Inertial Data

by Roberto Avilés, Diego Brito Souza, José Pino-Ortega and Julen Castellano

Sensors 2023, 23(6), 3095; https://doi.org/10.3390/s23063095 - 14 Mar 2023

Cited by 1 | Viewed by 1457

Abstract

The purpose of this study was to study the validity and reproducibility of an algorithm capable of combining information from Inertial and Magnetic Measurement Units (IMMUs) to detect changes of direction (COD). Five participants wore three devices at the same time to perform five CODs in three different conditions: angle (45°, 90°, 135° and 180°), direction (left and right), and running speed (13 and 18 km/h). For the testing, the combination of different % of smoothing applied to the signal (20%, 30% and 40%) and minimum intensity peak (PmI) for each event (0.8 G, 0.9 G, and 1.0 G) was applied. The values recorded with the sensors were contrasted with observation and coding from video. At 13 km/h, the combination of 30% smoothing and 0.9 G PmI was the one that showed the most accurate values (IMMU1: Cohen’s d (d) = −0.29;%Diff = −4%; IMMU2: d = 0.04 %Diff = 0%, IMMU3: d = −0.27, %Diff = 13%). At 18 km/h, the 40% and 0.9 G combination was the most accurate (IMMU1: d = −0.28; %Diff = −4%; IMMU2 = d = −0.16; %Diff = −1%; IMMU3 = d = −0.26; %Diff = −2%). The results suggest the need to apply specific filters to the algorithm based on speed, in order to accurately detect COD. Full article

(This article belongs to the Special Issue Sensors and Artificial Intelligence for Analyzing Human Behavior in Sports and Physical Activity)

► Show Figures

Figure 1

9 pages, 528 KiB

Open AccessArticle

Evaluating Physical and Tactical Performance and Their Connection during Female Soccer Matches Using Global Positioning Systems

by Ibai Errekagorri, Ibon Echeazarra, Aratz Olaizola and Julen Castellano

Sensors 2023, 23(1), 69; https://doi.org/10.3390/s23010069 - 21 Dec 2022

Viewed by 1729

Abstract

The objective of the present study was to evaluate the tactical and physical performance during official matches of a women’s soccer league and to correlate both dimensions in periods of 15 min. To do this, eight official matches of a semi-professional soccer team belonging to the Women’s Second Division of Spain (Reto Iberdrola) were analysed during the 2020–2021 season. The variables recorded were classified into two dimensions: tactical variables (i.e., Width, Length, Height and Surface Area) and physical variables (i.e., Total Distance Covered (TD), Total Distance Covered in High-Speed Running (HSR) and Total Distance Covered in Sprint). The main results were: (1) there were no differences between the periods in any of the tactical dimension variables; (2) in the physical dimension, a significant decrease in TD and HSR was described at the end of the match (period 60–75); and (3) some positive correlations were found among some variables of the tactical and physical dimension at the beginning and at the end of the match (periods 0–15, 60–75 and 75–90). The findings of the study suggest that connecting the tactical and physical dimension in the interpretation of team performance would allow for a better understanding of player and team performance and during competition. Full article

(This article belongs to the Special Issue Sensors and Artificial Intelligence for Analyzing Human Behavior in Sports and Physical Activity)

► Show Figures

Figure 1

10 pages, 1737 KiB

Open AccessArticle

Reliability of Repeated Nordic Hamstring Strength in Rugby Players Using a Load Cell Device

by Christian Chavarro-Nieto, Martyn Beaven, Nicholas Gill and Kim Hébert-Losier

Sensors 2022, 22(24), 9756; https://doi.org/10.3390/s22249756 - 13 Dec 2022

Cited by 2 | Viewed by 2190

Abstract

Hamstring strain injuries are one of the most common injuries in Rugby Union players, representing up to 15% of all sustained injuries. The Nordic eccentric hamstring test assesses the maximal hamstring eccentric strength and imbalances between limbs. Asymmetries and deficits in hamstring strength between legs are commonly assessed and used as screening methods to prevent injuries which can only be proven effective if hamstring strength measures are reliable over time. We conducted a repeated-measures reliability study with 25 male Rugby Union players. Nordic eccentric strength and bilateral strength balance was assessed. Three testing sessions were undertaken over three consecutive weeks. Intrasession and intersession reliabilities were assessed using typical errors (TE), coefficient of variations (CV), and intraclass correlation coefficients (ICC). Our results showed good intrasession reliability (ICC = 0.79–0.90, TE = 26.8 N to 28.9 N, CV = 5.5% to 6.7%), whilst intersession reliability was fair for mean and the max (ICC = 0.52–0.64, TE = 44.1 N to 55.9 N, CV from 7.4% to 12.5%). Regarding the bilateral strength balance ratios, our results showed good intrasession reliability (ICC = 0.62–0.89, TE = 0.5, CV = 4.4% to 7.2%), whilst the intersession reliability for mean and max values was fair (ICC = 0.52–0.54) with a good absolute intersession reliability CV ranging from 8.2% to 9.6%. Assessing the Nordic eccentric hamstring strength and the bilateral strength balance in Rugby players using a load cell device is a feasible method to test, and demonstrated good intrasession and fair intersession reliability. Nordic eccentric strength assessment is a more practical and functional test than isokinetic; we provide data from Rugby Union players to inform clinicians, and to establish normative values in this cohort. Full article

(This article belongs to the Special Issue Sensors and Artificial Intelligence for Analyzing Human Behavior in Sports and Physical Activity)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Sensors and Artificial Intelligence for Analyzing Human Behavior in Sports and Physical Activity

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (6 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI