Researchers at Singapore’s Nanyang Technological University (NTU) have developed MaskFi, a technique for utilizing Wi-Fi signals to track people’s movements and activities in metaverse environments.
TakeAway Points:
- Singaporean research scientists have developed a technique for tracking activities in the metaverse.
- The research aims to address the limitations faced by current tracking modalities.
- MaskFi allows for more accurate whole-body tracking, deeper avatar control, and enhanced interactions with the environment, all of which improve metaverse experiences.
MaskFi Technique
According to the findings, the research seeks to overcome limitations faced by current tracking modalities that rely on body-worn sensors or external cameras. These methods struggle with obstacles and poor lighting conditions and only provide data from specific points on the body.
Related articlesYou may also like
The researchers pioneered an unsupervised learning technique named “MaskFi” to meet the need for large labeled datasets to train the AI models.
MaskFi allows models to be trained using less data, and they can be improved iteratively until they achieve extremely high accuracy. During testing, the system’s accuracy in pertinent studies was about 97%.
“The experiments are conducted in the real world, and extensive results on our data and public dataset show that our approach achieves 97.61% accuracy on WV-Lab and 96.82% accuracy on MM-Fi regarding the HAR task, which demonstrates the effectiveness of our framework in practice.”
the findings stated.
Meanwhile, the NTU team’s solution affects the range and sensitivity of Wi-Fi signals to minute motions through walls. The AI then uses the data to analyze the signals and model the movements and activities of the entire body.
Though the requirement for sizable labeled datasets to train the AI models posed a significant challenge for earlier attempts, the researchers invented “MaskFi,” an unsupervised learning method, to address this.
MasFi Use Cases
According to the report, this technology created by NTU researchers allows for more accurate whole-body tracking, deeper avatar control, and enhanced interactions with the environment, to improve metaverse experiences.
In addition, this development has potential applications in elder care, security surveillance, and health monitoring, in addition to gaming and social media. It also protects privacy. Their work pioneers easy, interoperable tracking modalities by utilizing Wi-Fi infrastructure and AI, with potential benefits across a range of industries, including entertainment and healthcare.
