Club using GPS to track players movements 1

[GarethCollins]

This is good news. I'm all for the appliance of science in order to give us that extra few percentage point advantage over other teams at this level.

Usually these devices include a state of the art GPS receiver that measures the speed and position of each player up to 10 times per second, giving extremely accurate position, speed and direction measurements. Usually the devices also contain inertial sensors including an accelerometer, gyroscope and magnetometer that measures detailed movement and tackle impacts of a player up to 400 times per second. Some of them also include a heart rate monitor.

From the collected data (usually uploaded to a computer via USB) individual player metrics can then be calculated like players' average and top speeds, distance covered, number and intensity of sprints (acceleration and deceleration), changes in direction (linear motion and angular and rotational motion), calories burned, and average metabolic power etc.

The analysis for each player (and the team as a whole) is then viewable from a pre-built dashboard a bit like this one (and the data can be compared with previous sessions):
GameTraka | Powered by SPT

If you want to do your own bespoke analysis of the data, rather than using a pre-built dashboard with its pre-built analysis, then you could build your own custom dashboard with your own custom calculations using a free solution like Microsoft Power BI.

https://blogs.microsoft.com/blog/201...thletes-teams/

And talking of the appliance of science, some software companies in the field of computer vision are now working on software that can analyze a team and players' performances by feeding it a video of the match.

Here's a short demo clip of some computer software tracking players from one team on the pitch in real-time.



It uses the same convolutional neural network algorithms that power the computer vision systems of driverless cars.

[Teifi Red]

On the Mixlr commentary during the game last night it was mentioned the gps system can also give early warning of a potential injury and fatigue levels of the players.
Not sure if correct but could be important with the small squad set up.

[waxcrayon]

Originally Posted by Alan Attack

Will it pick up Carrington? Tends to go missing for large parts of games!

Brilliant

[bigJ]

If we did sign Rhead we would need to get an extension belt like they do for seat belts on fat people on planes.
Posted via mobile theme

[Old Paddock Man]

Was Tom Taylor wearing one?

[GarethCollins]

Originally Posted by Teifi Red

On the Mixlr commentary during the game last night it was mentioned the gps system can also give early warning of a potential injury and fatigue levels of the players.
Not sure if correct but could be important with the small squad set up.

Yes, I believe the training data can be used in a number of different ways to help prevent injuries. For example, a player could be favouring one leg over the other when jumping, due perhaps to an old injury that never properly healed or muscular weakness never addressed. Some data collection and analysis systems can measure that difference, perhaps undetectable to the eye, helping trainers uncover an injury waiting to happen.

In addition, American sports have recently started hoovering up gigabytes of training data for their particular sport so that data scientists can construct machine learning models that can predict the likelihood of a specific injury occurring before it happens based on a number of different input variables, including the player's training workload, the player's training performance data, the player's previous injury history, their age, their biometrics, and also an injury correlation matrix that statistically weights the different injury types by the relationship between them. So by keeping a running count of which injuries lead to other injuries they're able to statistically weight the probability of an injury reoccurring or causing another type of injury based on that player's input data.

Of course it can't predict accidental injuries. It just gives a percentage risk.

Some research scientists from the University of Pisa in Italy published their methodology for this in their paper "Effective injury prediction in professional soccer with GPS data and machine learning".

https://www.researchgate.net/publica...chine_learning

Abstract:

"Injuries have a great impact on professional soccer, due to their large influence on team performance and the considerable costs of rehabilitation for players. Existing studies in the literature provide just a preliminary understanding of which factors mostly affect injury risk, while an evaluation of the potential of statistical models in forecasting injuries is still missing. In this paper, we propose a multidimensional approach to injury prediction in professional soccer which is based on GPS measurements and machine learning. By using GPS tracking technology, we collect data describing the training workload of players in a professional soccer club during a season. We show that our injury predictors are both accurate and interpretable by providing a set of case studies of interest to soccer practitioners. Our approach opens a novel perspective on injury prevention, providing a set of simple and practical rules for evaluating and interpreting the complex relations between injury risk and training performance in professional soccer."

[ugarte007]

If we dont do well this season Im out of ideas !

[ozzy red]

Some Chester fan will place a bug in the programme
I foresee a new era of espionage in the National League

[Always The Kop]

A lot of thanks has to go to our fantastic supporters groups, with their contributions to financing these, they were not cheap. Hopefully they will prove to be worth their weight in gold. Lets hope it's another thing that gives us that little edge to get some extra points through the season.