Telecoms, Datacoms, Wireless, IoT


Nordic partnership bonds AI to IoT

26 February 2021 Telecoms, Datacoms, Wireless, IoT

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.”

nRF52840 design kit.

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.


Credit(s)



Share this article:
Share via emailShare via LinkedInPrint this page

Further reading:

Industrial Ethernet time sensitive networking switch
RS South Africa Telecoms, Datacoms, Wireless, IoT
The ADIN3310 and ADIN6310 are 3-port and 6-port Gigabit Ethernet time sensitive networking (TSN) switches with integrated security primarily designed for industrial Ethernet applications.

Read more...
When it comes to long-term reliability of RF amplifier ICs, focus first on die junction temperature
Altron Arrow Editor's Choice Telecoms, Datacoms, Wireless, IoT
When considering the long-term reliability of integrated circuits, a common misconception is that high package or die thermal resistance is problematic. However, high or low thermal resistance, by itself, tells an incomplete story.

Read more...
Automotive-grade digital isolators
Telecoms, Datacoms, Wireless, IoT
The NSI83xx series of capacitive-based isolators from NOVOSENSE Microelectronics offer superior EOS resilience and minimal power noise susceptibility.

Read more...
Why bis means business for LTE Cat 1 IoT connections
NuVision Electronics Editor's Choice Telecoms, Datacoms, Wireless, IoT
Tomaž Petaros, product manager IoT EMEA at Quectel Wireless Solutions explains why the market for Cat 1bis IoT connections is getting busy.

Read more...
Wi-Fi in 2025: When is Wi-Fi 7 the answer?
Telecoms, Datacoms, Wireless, IoT
Wi-Fi 7 introduces multi-link operation and lower latency, a game-changing feature that allows devices to transmit and receive data across multiple frequency bands simultaneously to significantly reduce network congestion.

Read more...
Bluetooth Lite SoCs purpose built for IoT
NuVision Electronics Telecoms, Datacoms, Wireless, IoT
Whether it is enabling predictive maintenance on industrial equipment, tracking assets in dense environments, or running for years on a coin cell battery in ultra-low power sensors, developers need solutions that are lean, reliable, and ready to scale with emerging use cases.

Read more...
LTE Cat 1bis module
Otto Wireless Solutions Telecoms, Datacoms, Wireless, IoT
The A7673X LTE Cat 1bis module from SimCom is engineered to meet the growing demands of the IoT industry, offering exceptional performance and seamless integration.

Read more...
Track with precision
Telecoms, Datacoms, Wireless, IoT
KYOCERA AVX provides innovative antennas for cellular, LTE-M, NB-IoT, LoRa, GNSS, BLE, UWB, Wi-Fi, and future Satellite IoT.

Read more...
Wi-Fi 7 front-end module
RF Design Telecoms, Datacoms, Wireless, IoT
The Qorvo QPF4609 is an integrated front end module designed for 802.11be systems that has integrated matching, which minimises layout area.

Read more...
Multi-channel downconverter
Vepac Electronics Telecoms, Datacoms, Wireless, IoT
The Downconverter from Crane Aerospace is a converter that operates from 2 to 18 GHz and delivers a noise figure of 11 dB with an attenuation range of 25 dB.

Read more...