Earlier this year, the Edge Impulse team created a crowdsourced project that enables the Nordic Semiconductor Thingy:91 to detect the device’s surrounding environmental conditions using its onboard sensors, including a temperature, pressure, humidity, and a gas result reading. The project enabled the Thingy:91 to detect whether the device was physically indoors or outdoors (or inside/outside).
By collecting data from a large number of varying environments, from multiple locations around the world from our various team members, the Nordic Thingy:91 is a powerful device for machine learning inference results for physical world sensor data. The ML predictions generated by the Edge Impulse SDK can also be wirelessly sent over Bluetooth connection to a results dashboard to rapidly view changes in the device’s environmental state, whether inside a building, outside or more!
The Nordic Thingy:91 is an easy-to-use battery-operated prototyping platform for cellular IoT using LTE-M, NB-IoT, and GPS. It is ideal for creating proof of concepts, demos, and initial prototypes in your cIoT development phase. The Thingy:91 is built around the nRF9160 SiP and is certified for a broad range of LTE bands globally, meaning the Nordic Thingy:91 can be used just about anywhere in the world. There is an nRF52840 multiprotocol SoC on the Thingy:91. This offers the option of adding Bluetooth Low Energy connectivity to your project.
Read the How can I get started? sectionHow can I get started?
- Sign up for an Edge Impulse account and create a new project.
- Follow along with the getting started guide to set up your Nordic Thingy:91 with Edge Impulse.
- If you’re collecting data with your team or colleagues, check out our blog post on utilizing the power of the crowd and your peer network with their own Nordic Thingy:91’s.
- Or, clone the project the Edge Impulse team has already created into your own Edge Impulse account.
- Once you have collected your data and trained your machine learning model (or Impulse), following along with the Nordic Thingy:91 deployment guide to retrieve model inferencing results in real-time!