Researchers at the Skolkovo Institute of Science and Technology, Moscow Institute of Physics and Technology (MIPT), and the State University of Aerospace Instrumentation (SUAI) claim to have discovered a method for gauging a player's skill at competitive computer games - by monitoring how they sit in their chair.
The easiest way to tell the difference between someone who is good at games and someone who isn't is, of course, to have them play a game and see how they do. A team of researchers from the Skolkovo Institute of Science and Technology, Moscow Institute of Physics and Technology (MIPT), and the State University of Aerospace Instrumentation (SUAI) claim to have another method, however: monitoring how the player sits.
'We assumed that there could be a link between a player's body movements and skill level,' explains lead author and Skolkovo Institute student Anton Smerdov. 'Also, it was interesting to look at the players' response to various game events, such as kills, deaths or shootings. We suspected that professional players and beginners would react differently to the same event.'
To put the idea to the test, the team took nine professional players and 10 amateurs and had them play popular e-sports title Counter-Strike: Global Offensive (CS:GO) for between 30 and 60 minutes. In the chair used for each gaming session was a gyroscope and accelerometer, which gathered information about the player's seated movements during the play session. 'We then cut the data into three-minute sessions,' Smerdov explains, 'assuming that three minutes were enough to understand the player's behaviour and obtain a sample big enough for algorithm learning.'
Having identified 31 movement patterns distilled down to eight key features, the team ran the data through a machine learning algorithm which spat out its best guess for each player's skill level. The result: An accurate estimation of player skill in 77 percent of cases.
The study found that professional players, in contrast to the amateurs with fewer lifetime game hours on the clock, moved around both more often and more intensively in general; this, however, reversed during shooting and other in-game actions requiring concentration and fine motor control, when the professionals became absolutely still.
The team's paper, Understanding Cyber Athletes Behaviour Through a Smart Chair, was published as part of the IEEE 5th World Forum on Internet of Things conference.
March 25 2020 | 14:00