Page 35 - EngineerIt January 2021

INDUSTRY AND TECHNOLOGY

Data and analytics can model a football match

By Dean Evans, Technology Writer Intel

ootball is big business and mistakes can cost
Fclubs millions. How do teams make the best of
their resources and identify areas for
improvement? The secret to improving
performance on the pitch starts with
understanding the gap between a team’s current
level of effectiveness and the level they want to
reach. Teams monitor their own players via
wearable sensors like the Catapult Sports
OptimEye S5 and analyse their opponents using
statistical data from InStat, Opta and Prozone.
When Liverpool FC’s Philippe Coutinho scored
a free kick against Brighton in December 2017 by
firing his shot underneath the jumping defensive
wall, Jurgen Klopp credited his analysts for pointing
out the opportunity. Data was also instrumental database every month and the company employs 500 people in its Production and Data Centre to analyse
when Hearts ended Celtic’s 69 game unbeaten run and document every sprint, kick, dribble, challenge and pass. While InStat data can prove vital in areas such
last year. Hearts Manager Craig Levein revealed as opposition analysis, match preparation, scouting and player recruitment, clubs also assess the
that Anderlecht's 1-0 victory over Celtic in the performance of their own players using wearable sensors and analytics.
Champions League had pointed the way. A typical Catapult Sports wearable vest with an embedded OptimEye S5 device, for example, can collect
"The analysis of the Anderlecht game," up to 1,000 data points per second. It can measure fitness and skill levels, response to specific training
revealed the BBC, “showed that the Belgians techniques, tactical performance, and risk of injury.
played a pressing 4-3-3 and that the three With measurable objectives to aim for, a football club could then assess its own resources and see how
midfielders and three attacking players covered much of a gap there is between where they are today and where they want to be tomorrow. If a team isn’t
an average of 11.8 km per man when hustling creating enough goal-scoring opportunities, for example, can that be improved by a change of formation or a
and harrying Celtic out of possession." new striker with a higher shots percentage?
Thanks to their own club analytics, Levein and Of course, with so many variables in the average football match, analytics isn’t a magic bullet. Statistical
his coaching staff knew that they had players who predictions can be upended by simple human error – a missed shot, a poor pass, a clever dive or a
could cover that sort of distance. So the strategy contentious refereeing decision. Or they can just as easily be defined by a moment of brilliance from a world
was to "hit the 11.8 km average, frustrate Celtic, class player.
press them high up the pitch, cut out the passing But, used intelligently, analytics technology can give teams an edge over their rivals. Sensor data from
route to their most dangerous players, refuse to let training sessions -- along with what players eat and how much they sleep – can be combined with cloud-
them settle and force some errors." hosted, instant-access statistics from the likes of Opta, InStat and Scout7 to help identify in-form players,
Football has become increasingly data-driven define personalised training regimes and improve physical performance.
and Hearts drew upon InStat’s vast database of A football match seems impossible to model - 22 players (with their own strengths and weaknesses),
football statistics to help mastermind their victory. three officials (ditto), contrasting formations, luck, randomness, pitch conditions, weather effects, crowd
More than 1,500 clubs and national teams noise, the cumulative behind-the-scenes impact of coaches, doctors, physiotherapists, masseurs, kit
use the system, which features information on managers, nutritionists, analysts and sport scientists. But with a combination of cloud computing and big
more than 400,000 players. According to InStat data analytics, teams are beginning to understand the probability of success and, more importantly, what
over 6,000 new video records are added to the they can do to improve it. n

5G and Edge: Computing optimised for business value

and edge add speed, reliability and flexibility to enterprise Why 5G and Edge computing?
5Gapplications by bringing compute closer to its source or where it Distributed computing gives businesses the flexibility to process application
delivers the greatest business impact. data in the location that delivers the most value. In many data-rich and
Not all enterprise applications have the same requirements. When time-sensitive use cases, that may not require a remote data centre. 5G
computing extends across cloud, network, and edge with 5G, businesses connectivity makes the division of computing resources along the cloud-
will have choices around where and how to handle each application. One network-edge continuum possible, and its ultra-reliable low-latency
option, the cloud data centre, provides high-volume processing and storage. capabilities make the shorter connection between the device and the edge
On the other hand, the edge—which processes data closer to its source and even more efficient. In fact, Gartner predicts that 75% of enterprise data will
the point of service delivery—provides ultra-low latency to help boost be created and processed outside the cloud by 2025 when 5G networks will
efficiency, improve service quality, and generate actionable insights faster. be fully deployed. n

EngineerIT | December 2020 / January 2021 | 33