Football: when data is used to improve performance
Our society is becoming increasingly digitized thanks to the use of a wide range of digital technologies that generate large data flows, collectively referred to as big data. This is particularly true of sports-related data collected via smartwatches, smartphone apps, satellite tracking systems, and even smart textiles.
Stéphane Perrey, University of Montpellier; Gérard Dray, IMT Mines Alès – Institut Mines-Télécom and Jacky Montmain, IMT Mines Alès – Institut Mines-Télécom
This data would make it possible to identify key performance indicators as well as the movements of athletes on the field: the number and length of sprints and changes of direction, distance covered at certain speeds, changes in heart rate, and player trajectories.
They can therefore guide training strategy. From there, it is only a short step to becoming an essential tool for improving performance or preventing injuries. This type of information can therefore be of interest to a wide range of stakeholders: athletes, coaches, physical trainers, adapted physical activity instructors, doctors, and sports agents. These data, and the methodologies that accompany them, open up new perspectives for research in sports science and digital science.
Recent developments in wearable and connected sensors, cloud data storage, and artificial intelligence tools have been the cornerstones of a major shift in how sports-related data is analyzed. Over the past decade, sports science research has benefited from the reduction in the size of sensors and the consequent increase in the capacity to collect and analyze simultaneous measurements, driven by huge advances in wireless transmission.
Soccer is one of the most popular sports in the world, and over the years, more and more information has become available, which has increased data analysts' interest in the sport. Related professions, such as data scientist, have developed with specific skills in statistics and computer science in order to collect, process, analyze, and interpret big data... with the aim of finding information that is useful for decision-making.
In sports, we talk about Sports Data Analysts, and several think tanks, university schools, and thematic groups within research units (EuroMov Digital Health in Motion) bringing together multidisciplinary expertise have been set up. How can sports science and digital science, from data collection to predictive modeling of performance or injury, including data management, impact the field of sports?
The proliferation of movement data
Recent years have seen the rise of position detection systems to provide spatio-temporal tracking data on players on the field. Although semi-automatic camera systems have been used to track player positions in professional soccer matches, automatic tracking systems using satellite positioning systems (GNSS for geolocation and navigation by satellite system) or local positioning measurement systems are commonly adopted by professional organizations and teams in team sports (soccer, rugby, basketball, handball, and ice hockey). Some positioning systems have even equipped balls with integrated sensors.
One of the most visible advances in many sports disciplines is the introduction of autonomous inertial measurement units (IMUs), which measure linear acceleration (accelerometers), rotational speed (gyroscopes), and the Earth's magnetic field for orientation (magnetometers) at a three-dimensional point.
The fusion of these portable sensors (IMU-GNSS) is a constant trend in the development of human movement tracking and detection systems with applications in sports such as soccer to track players' motor actions. In general, movements (speed, distance, and derived measurements) are primarily quantified using GNSS data, while the detection and characterization of shocks/impacts is reserved for IMU data. Despite these advances, is it possible to free players from these sensors in the quantification of movement? It would appear so.
[Nearly 80,000 readers trust The Conversation newsletter to help them better understand the world's major issues. Subscribe today]
Markerless motion capture systems and algorithms have been continuously improved over the past five years to measure kinematics (i.e., the description of motion in terms of position, velocity, or acceleration) in sports. Modern computer vision algorithms using neural networks have been adapted to evaluate different forms of motor actions, providing practical means for faster data analysis with validity in real-world conditions, i.e., outside the restrictive environment of laboratories.
The classification of human locomotor activity types from a sports performance perspective can be improved when the acquired signals are used as inputs for machine learning algorithms. The ability of current algorithms to analyze and extract knowledge from such datasets can, for example, identify changes in direction, which are often decisive in a game. The use of deep learning algorithms (a subfield of machine learning that focuses on algorithms inspired by the structure and functioning of the brain, called artificial neural networks) on video images would make it possible to recognize different types of kicks in soccer with a high degree of accuracy.
Using multiple fused IMU-GNSS sensors and various machine learning algorithms, Reilly et al. developed an automated classification model to accurately identify players' movements with changes in direction during competitive matches. Improvements in classification models in sports such as soccer are still hampered by the variability of movement patterns, which has a direct impact on the quality and quantity of available datasets.
From data to predicting performance or injury status
So how could big data improve performance in high-level sports? The data collected by the aforementioned tools and equipment can be used to characterize movements in detail and then determine the athlete's physical training load. Widely used to monitor soccer players, physical demands can be determined using objective mechanical parameters calculated from GNSS-IMU signals coupled with heart rate signals, for example. The data collected from these wearable devices provides useful information for understanding a player's activity and performance in competition, and for preventing the risk of injury during training.
To do this, one approach is to perform descriptive analyses to characterize target exercise intensities in relation to physical performance over time and to identify interpretable analytical relationships. With sufficient information collected over several months or even years, predictive analyses can be deployed to estimate performance on the day of competition or to provide useful information to coaches, teams, or players in order to guide training protocols to optimize prescription (volume, intensity, and type of exercises) and thus performance.
Regarding individual physical performance in professional soccer players, researchers have presented an approach that predicts individual acceleration-velocity profiles based on GNSS data measurements in real game situations. These profiles can provide relevant information about the theoretical maximum strength of the hip extensors and the ability to generate significant horizontal force at high running speeds, both of which are key determinants of muscle injuries and sprint performance.
In the context of sports injuries, the ability to predict risk factors and assess an athlete's readiness after surgery or any other procedure is essential. The application of machine learning techniques appears to be able to provide information on the risk of non-contact injuries by taking into account changes in training doses over a week (short term) and a month (medium term) based on data collected by GNSS and IMU coupled with questionnaires. The results of a study conducted over the course of a sports season among professional soccer players in Ligue 2 show that, depending on the complexity of the predictive model, the classification performance for predicting injury risks can approach 100%, particularly over a one-month time horizon.
In addition, it appears that subjective variables (such as sleep quality, fitness, mood, satisfaction, and enjoyment) are important factors in predicting injury risk, as is distance traveled. This initial information can be used to guide individualized training programs in order to reduce the risk of injury.
Today, portable mobile devices provide the information needed to analyze players' performance in training and competition. In addition, new machine learning algorithms, including deep learning and data mining, enable players' progress to be assessed at all stages of their training.
However, it remains to be seen whether current technological and scientific advances are already mature enough to implement automated decision-making systems in real-life competition conditions and influence the outcome of the match.
Stéphane Perrey, University Professor of Exercise Physiology/Integrative Neuroscience, Director of the Research Digital Health in Motion Research Unit, University of Montpellier; Gérard Dray, Professor, IMT Mines Alès – Institut Mines-Télécom and Jacky Montmain, Professor – EuroMov Digital Health in Motion, IMT Mines Alès – Institut Mines-Télécom
This article is republished from The Conversation under a Creative Commons license. Readthe original article.