12:00 am to 12:00 am
Bio: Dr Stuart Morgan trained originally in sensory neuroscience, with
an interest in how the human visual system copes with dynamic and
uncertain visual environments. This work translated easily into high
performance sport, and Dr Morgan has worked in that domain for more
than 10 years. His novel contributions to sport science include
pioneering a stereoscopic video training tool, non-invasive eye
movement measurement techniques, and some of the earliest work in
spatial pattern recognition in team sports. Dr Morgan is currently
leads the Data Analytics Group at the Australian Institute of Sport,
and is responsible for developing leading edge technologies to improve
sports performance.
Abstract: “Successful football coach, Bernd Schröder, once said “there
is no science in football”. Performance analysis and computer science
in sport has made considerable progress in recent years, yet
Schröder’s statement remains representative of the perceptions of many
coaches. This statement illustrates two of the most significant
questions for computer science in sport: what are the barriers that
prevent coaches from embracing sports and computer science, and, how
can data be presented in more meaningful ways such that coach
expertise is enabled (rather than threatened) by science?
It is proposed that coaches develop expertise using primary modes of
game feedback, such as direct visual observation, video review, basic
game statistics, input from other first hand observers such as
assistant coaches, and crude insights from match outcomes such as the
progressive score line. It is from these sources that coaches build
and test decision making schemas. Certainly, it is not until much
later in their careers that coaches become exposed to empirical data,
often derived by specialist sports scientists, who provide the them
with a potentially bewildering array of game and performance data. It
may often be that coaches do not possess the knowledge frameworks to
absorb or exploit these sources of information, and that empirical
data presented by scientists does not therefore influence their
coaching decisions. It is proposed that consideration needs to be
given to the problem of data visualizations, and in particular,
matching data presentation techniques to the learning styles, decision
making schemas, and game perception frameworks that coaches have
otherwise used throughout their careers. This presentation open
discussions about how advances in computer science may amplify coach
expertise, rather than attempting to supplant it.”