“The machine-learning core and finite state machine enable product designers to implement simple decision trees for neural processing on the chip,” according to the company. “ST1VAFE3BX provides opportunities to extend wearable applications beyond the wrist to other locations on the body, such as intelligent patches for lifestyle or medical monitoring purposes.”
The single bio-potential channel has a programmable gain amplifier and access to the shared 12bit ADC sampling at up to 3.2kHz – suitable to quantify heart, brain and muscular activity, said ST. The accelerometer can be programmed for full-scale between ±2 and ±16g.
Associated tool include MEMS Studio for the accelerometer and Edge AI Suite for the processor. There is also a tool to configuring decision trees.
Power is 50µA from 1.62 to 3.6V, and there is a 2.2µA power-saving mode.
Packaging is 2 x 2mm 12lead LGA.
See the IC in Hall C3 on stand 101 at Electronica (Munich, 12-15 November) or check out its web page here.