Watch our Demonstration Video

Reality AI can recognize subtle signatures in acceleration and vibration, even in high variation applications and noisy environments. Typical applications are wearables, and machine health / predictive maintenance.

Typical sample rates when working with accelerometers and vibration sensors

You'll get your best results with Reality AI when you use time waveforms as your input data and you select an appropriate sample rate. If time waveform isn't practical, we can also work with FFT as input - though we prefer as much frequency and time resolution as possible. In some cases our tools can get good results with Peak-to-Peak, RMS and similar values, but the more information the tools can get in the frequency and time domains, the better.

Reality AI Starter Kit using Bosch XDK

Try Reality AI Starter Kit

Includes Bosch XDK sensor modules 

+ 2 months access to Reality AI Tools™

> Collect accelerometer and vibration data 

> Detect anomalies, or create labeled classes

> Create detectors for specific events and conditions

> Explore relationship between sample rate, detection window,
computational complexity, and detection accuracy

> Determine hardware requirements for embedded AI solutions

Learn more with our Technical Whitepaper

Explore the technical details behind the Reality AI approach to machine learning with signals

  • Why signals require a different approach than other machine learning problems

  • The importance of "features" to effective machine learning

  • Why the FFT probably isn't good enough, and what other options are better

  • The difference between Reality AI and Deep Learning