Abstract: Researchers have developed an AI model that can recognize the emotional states of tennis players with high accuracy by analyzing their body language during matches. AI, trained on real-life footage, can detect positive and negative emotions, although it is more adept at recognizing negative ones. The technology has potential applications in sports training, healthcare and other fields, but raises ethical concerns about privacy and data misuse.
Important facts:
- The AI model accurately identifies the emotions of tennis players based on body language.
- Both AI and humans are better at recognizing negative emotions.
- Potential applications in sports, healthcare, etc., but ethical concerns need to be addressed.
Source: cut
For their study, “Recognizing affective states from expressive behavior of tennis players using convolutional neural networks,” researchers in sports science, software development and computer science from KIT and the University of Duisburg-Essen developed a special AI model. prepared.
They used pattern recognition programs to analyze video of tennis players recorded during actual games.
Success rate 68.9 percent
“Our model can identify impressive states with an accuracy of up to 68.9 percent, compared to assessments made by both human observers and previously automated methods,” said Professor Darko Jackau of KIT's Institute of Sports and Sports Science. Comparable and sometimes superior.”
An important and unique feature of the study is the project team's use of real-life scenarios rather than simulated or simulated situations to train their AI system. The researchers recorded video sequences of 15 tennis players in a specific setting, focusing on the body language displayed when a point was won or lost.
Videos show players with signs such as heads bowed, arms raised in joy, rackets dangling, or variations in walking speed; These cues can be used to identify affective states of players.
After being fed this data, the AI learned to associate body language signals with different affective reactions and determine whether a point was won (positive body language) or lost (negative body language). .
“Training in natural contexts is an important advance for identifying real emotional states, and it makes predictions possible in real scenarios,” said Jackauk.
Humans and machines recognize negative emotions better than positive emotions.
Not only does the research show that AI algorithms may surpass human observers in their ability to identify emotions in the future, it also reveals another interesting aspect: Both humans and AI are better at recognizing negative emotions. are
“This may be because negative emotions are easier to identify because they are expressed in more obvious ways,” Jakauk said.
“Psychological theories suggest that people are evolutionarily better adapted to understand negative emotional expressions, for example because quickly ending conflict situations is important for social cohesion.”
Ethical aspects need clarification before they can be used.
The study envisions several sports applications for identifying trusting emotions, such as training methods, improving team dynamics and performance, and preventing burnout. Other fields, including healthcare, education, customer service and automotive safety, could also benefit from reliable early detection of emotional states.
“While this technology offers the potential for significant benefits, the potential risks associated with it must also be taken into account, particularly related to privacy and data misuse,” said Jackauk.
“Our study strictly adheres to current ethical guidelines and data protection regulations. And given the future application of such technology in practice, it will be important to clarify ethical and legal issues ahead of time.
About this AI and emotion research news
the author: Margaret Lehney
Source: cut
contact: Margaret Lehney – KIT
Image: This image is credited to Neuroscience News.
Original research: Open access.
“Identifying affective states from expressive behavior of tennis players using relational neural networks” by Justice Hartlib et al. Knowledge based systems
Abstract
Recognizing affective states from expressive behavior of tennis players using convolutional neural networks
This study describes an AI model leveraging advanced Convolutional Neural Networks (CNNs) to recognize affective states in real-world sports settings, specifically tennis matches.
In contrast to previous studies that mainly used data obtained from actors and primitive statistical methods, the present research emphasizes the analysis of bodily expressions in real-life contexts for a more naturalistic representation of human emotions.
Our CNN-based models demonstrate an accuracy rate of up to 68.9%, outperforming or matching human observers in many instances. Interestingly, both machine learning models and human observers showed a common tendency to more effectively identify negative affective states, which may be attributed to the more intense and straightforward expression of these states. .
These findings not only advance the state of the art in affective state recognition, but also pave the way for broader applications, including in the fields of healthcare and automotive safety, thereby enabling sophisticated and universally applicable emotion recognition. There is an important development in the development of the system.