Reality AI Demo
Embedded AI using accelerometers and vibration
What you'll see
Leverage Reality AIʼs powerful signature extraction and recognition capabilities.
This demo shows detection using a 3-axis accelerometer and a Cortex M3 microcontroller, contained in a Bosch XDK.
How it works
The demo uses approximately 2-4 minutes of streaming accelerometer data recorded for each action and machine state using the Reality AI Starter Kit. Fan vibrations were also recorded on different surfaces and in different environments so that the AI could learn to screen out background variation.
We then used Reality AI Tools™ in the cloud to train classifiers that could recognize both the human activities and the machine states. Reality AI Tools can also be used for anomaly detection.
Detection code was then exported to the Bosch XDK development environment and loaded onto the chip. That classifier generates messages, which the XDK communicates to a listening app which displays results in a browser window.
See another demo using sound or image
Choose one of these demonstrations below to see other examples of Reality AI technology at work.
Become part of the Reality AI community and help shape the AI revolution