According to ScienceDaily17 , researchers at the Karlsruhe Institute of Technology and the University of Duisburg-Essen accurately identified a new type of neural network with the help of a computer-assisted neural network.basketballsportsmenEmotions expressed in body language during the game.
The team trained this AI-based model for the first time using actual game data, and the results were published in the latest issue of Knowledge Systems, an academic journal in the field of artificial intelligence:https://www.sciencedirect.com/science/article/pii/S0950705124004908
Sports science, software development and computer science researchers at the two schools are said to have developed a special AI model thatRecognizing Tennis Players' Emotional States Using Convolutional Neural Networks, and used a pattern recognition program to analyze videos of tennis players in actual matches.
Professor Darko Jekauc of the Institute of Sport and Exercise Science at the Karlsruhe Institute of Technology said, "Our model is able to recognize emotional states thatAccuracy up to 68.9%that compare favorably with human observers and early automated methods, if at all."
Image source: Pexels
The project team trained its AI system using real scenarios rather than simulated or artificial ones, an "important and unique" feature of the study. The researchers recorded video sequences of 15 tennis players in specific scenarios, focusing onBody language displayed when scoring or losing points. The video shows that the players' clues includeHead down, arms up in celebration, racket dropping or change of paceThey can be used to recognize the emotional state of the players.
After acquiring the above data, the AI will "learn" to associate body language signals with different emotional responses, and then use this data to create an AI that can be used as the basis for a new AI.Positive or negative body languageto determine whether to take a point or lose a point.
In terms of specific applications, the team says this research could subsequently be used toImproving training methods, team motivation and performance, and preventing burnoutetc., but also in other areas - includingHealthcare, education, customer service and automotive safetywait.