Nordic Semiconductor announced that, further to entering into a partnership with Edge Impulse, a leading provider of what’s termed ‘tiny machine learning’ or ‘TinyML’ tools designed to run on resource constrained semiconductor devices, all its nRF52 and nRF53 Series Bluetooth Low Energy (LE) chips will now be able to benefit from easy-to-use AI and machine learning features as standard. This is a first for the Bluetooth semiconductor industry.
“What AI and machine learning on resource-constrained chips does – which Nordic will now collectively refer to as TinyML – is take the application potential of wireless IoT technologies such as Bluetooth to a whole new level in terms of environmental awareness and autonomous decision making,” commented Kjetil Holstad, Nordic’s director of product management.
“Although we have had customers build and run TinyML applications on Nordic’s Bluetooth chips in the past, before now this required quite a high level of mathematical and computer programming expertise using professional science and academia software like MATLAB.”
One example of the above is two successful projects in the Hackster.io and Smart Parks-backed ‘ElephantEdge’ wildlife tracker challenge that employed Nordic’s nRF52840 System-on-Chip (SoC). These included an award-winning design by Dhruv Sheth called ‘EleTect’, a TinyML and IoT smart wildlife tracker employing the nRF52840 SoC as well as an accelerometer, camera and microphone.
Sheth’s different TinyML models included: camera vision models to monitor the risk of poaching and predators or to monitor elephant movements; accelerometer data models to predict and classify common elephant behaviours; and audio data models to detect and classify elephant musth data and mood swings (a periodic condition in male elephants characterised by highly aggressive behaviour that can place them in conflict with humans). These models were made ready for deployment in three forms including a C++ library, Arduino library and OpenMV library, all available on GitHub.
Holstad says prime engineering areas for TinyML include, but are not limited to, audio and vibration, where it can be used to establish normal operating patterns and rapidly detect anomalies. Example applications include anti-poaching (listening for gun shots), predictive and preventive maintenance (listening for tell-tale changes in the vibration signature of a public escalator or lift), and utilities (power line failure detection after a storm). But Holstad says all Nordic customer applications stand to benefit from TinyML, from asset tracking to wearables.
The Nordic Edge Impulse partnership will centre around Edge Impulse’s Edge Optimized Neural (EON) compiler that is said to optimise computer processing and memory use by up to fifty percent when running TinyML on resource-constrained semiconductor devices.
| Tel: | +27 21 555 8400 |
| Email: | [email protected] |
| www: | www.rfdesign.co.za |
| Articles: | More information and articles about RF Design |
© Technews Publishing (Pty) Ltd | All Rights Reserved
printer friendly version