NeuroSense

Ultra-low Power Tiny AI Chip for Wearables

NeuroSense, the Tiny AI chip based on Neuromorphic Analog Signal Processing, eliminates  the most annoying disadvantages of mass-market wearables: high power consumption, low accuracy of heart rate measurements, connectivity and data security issues

Mass market wearables could be smarter!

People need them always-on, low-power, accurate and cloudless

To support modern Neural Networks’ capabilities, a wearable’s hardware consumes a lot of power, because AI requires compute resources and cloud connection. That’s why mass market wearables, such as fitness trackers, smartwatches, health monitoring devices, and remote care wearables for seniors have short battery life and low tracking accuracy.

Is underperformance annoying? Sure! And it can be even dangerous...

1Heart rate calculations, while in motion, have low accuracy due to inconsistent noise factors

2Heart rate and PPG calculations are resource-hungry

3Human activity learning requires loads of raw data transferred to cloud

Problems solved by NeuroSense !

1Three times better heart rate accuracy than algorithm-based calculations

2Ultra-low power consumption below 100µW

3Human activity recognition on sensor level, cloudless operation

1 sec:  ECG reference, NeuroSense 

5 min average: Algorithm, ECG reference, NeuroSense

Heart rate measurement accuracy by NeuroSense is more than twice better than algorithm-based calculations.

NeuroSense ADVANTAGES

Neuromorphic Module instead of the sensor MCU

Longer battery life due to ultra-low power consumption

Small IC footprint

Low manufacturing costs

More parameters to measure

Oxygen saturation, arrhythmia, steps counter, sleep tracking, stress monitoring

Any human activity learning and recognition

Tunable for any application

Providing short time-to-market

Neuromorphic
Analog
Signal
Processing
NO FEAR of DATA TSUNAMI
Technology