By networking multiple such fibres into a distributed computational textile, they achieved human activity recognition accuracy of 95% —a dramatic leap from the 67% achieved by single-fibre systems.

By using a two-dimensional acoustic array with 256 receivers and four ultrasonic transmitters, the researchers were able to gather data related to four different human activities -- sitting ...

Researchers have long been able to use information from smartwatches to identify physical movement, such as sitting or walking, that wearers are performing in a controlled lab setting.

Balls of human brain cells linked to a computer have been used to perform a very basic form of speech recognition. The hope is that such systems will use far less energy for AI tasks than silicon ...