Cellulær IoT-platform udfører AI edge computing

Signetik lancerer præcertificeret batteriforsynet cellulær IoT-platform, der er baseret på off-the-shelf moduler og add-ons, hvilket reducerer designrisici og time-to-market (in english).

SigCell is designed to remove both the delay in time-to-market and commercial risk of developing a sensor-to-cloud IoT solution with both basic and big data AI analysis and machine learning capabilities. Signetik says the SigCell platform offers a vast range of environmental sensing and imaging processing capabilities that include (but are not limited to): temperature, humidity, movement, sound, light, rain, gun shot, and visual tracking. Typical battery-life is quoted at 2-5 years in most applications depending on duty cycle.

- Our cellular IoT platform is all about getting environmental sensing applications into production fast, explains Signetik's President, Steve Poulsen.
- And in a manufacturing environment, for example, this might include interfacing to older, PLC-based legacy equipment to make it IoT-enabled. Or in agriculture, it might include rain detection to avoid over-watering of crops, allied with taking still photos and using basic AI to spot any abnormalities in appearance or growth. 

Although The Signetik IoT platform includes an ecosystem of add-on boards with sensors for various applications, Poulsen stresses:
- And if we as a company don't yet have an add-on board for what you want to sense, give us a month or two and we'll develop one for you. 

The Signetik SigCell platform uses the Nordic nRF9160 SiP's 64MHz Arm Cortex-M33 processor supported by 1MB of Flash and 256KB of RAM memory to perform sensor data acquisition, edge computing, and even basic AI data analysis to avoid the financial and energy cost of sending large amounts of data to the cloud. Only if big data AI is required would collected IoT data be transferred.

- AI and the IoT go hand-in-hand because the IoT generates too much data for a human to reliably and quickly analyze, continues Steve Poulsen.
- At present we estimate around 20 percent of our customers use AI in their IoT applications, and based on current trends we see this rising to 50 percent within the next few years.

- But we've been working on IoT applications for over 20 years - since long before it was called IoT. What's changed is the commercially viability of powerful but low-cost sensors and low power wide area (LPWA) wireless technologies as a means to collect data from them. The latter now includes cellular IoT for long-distance LPWA gateway-free connectivity. And cellular IoT is by far the best LPWA wireless technology out there today, and the one we plan to standardize upon moving forwards. 

In addition to a wide range of IoT-targeted short- and long-range wireless module platforms and add-ons, Signetik offers a full range of embedded design services ranging from PCBs and RF antenna design, to smartphone and web application design, data server design, as well as server monitoring.

- Modules have long been an established way to remove development risk, adds Geir Langeland, Nordic Semiconductor Director of Sales & Marketing.
- And in the IoT world we are finding that a lot of companies are small and startup and don't need the added risk of developing an IoT application from scratch on their own.