Electronicdesign 26611 Ai Gettyimages 941054744
Electronicdesign 26611 Ai Gettyimages 941054744
Electronicdesign 26611 Ai Gettyimages 941054744
Electronicdesign 26611 Ai Gettyimages 941054744
Electronicdesign 26611 Ai Gettyimages 941054744

SmartEdge Agile Brings AI to the Edge

April 24, 2019
Technology Editor Bill Wong takes a hands-on look at the SmartEdge Agile sensor that supports the Brainium software stack.

Avnet, a global technology solutions provider, and Octonion, an IoT software provider, joined forces to deliver the SmartEdge Agile sensor (see figure) designed to highlight the Octonion’s Brainium software stack. I took the sensor and software for a short spin.

The sensor module is compact with a USB Type-C connection for charging. Bluetooth is used to link the module through the Brainium gateway software running on a Raspberry Pi, Android, or Apple IOs device to the cloud, where most of the heavy lifting is done. In that sense, the platform is very similar to other IoT systems and software stacks designed to make it easy to build cloud-based applications with input from remote sensors.

The SmartEdge Agile sensor is an IoT platform with its own sensor complement. It can be augmented with additional sensors or communication support.

The module is based on STMicroelectronics’ STM32 microcontroller. It includes Bluetooth LE 5.0 support along with a secure element that provides secure authentication support across the internet. Wired or wireless connectivity can be used to connect the module to the cloud. A lithium-polymer (LiPo) battery provides wireless operation.

The base module includes sensors for humidity and temperature, ambient light, proximity detection, a 3D accelerometer, a 3D gyro, a 3D magnetometer, a pressure sensor, and a microphone. The on-board sockets allow for other wireless communication options as well as additional sensors.

The sensor module comes with a six-month subscription to Microsoft’s Azure, which hosts the software in the cloud. Development of the cloud-based software is done using the Brainium portal.

Getting started with the system is relatively easy. Signing up for a Brainium account is first followed by the download and installation of the gateway. The software does a good job of linking everything up. Since the secure element is already known to the cloud support, secure communication is used from the start.

Project Modules

The project-based, cloud integrated development environment (IDE) pairs one or more modules with a project. This can start with basic capture of sensor information from the module. The more interesting work comes with using the data to train AI modules that can also be developed with the IDE.

A number of predictive models target motion recognition for the end goal of providing predictive maintenance. I didn’t get into depth in this area as one of the requirements for training a machine-learning (ML) module is lots of data. Strapping a module to a motor or carrying it around are ways of generating data for a device or person, but it helps to know what type of data will be useful as well as know the intended end goal. It might involve recognizing a gesture or motion while holding the sensor.

It’s possible to do some down-and-dirty coding, but most users will never do that even when dealing with the ML support. The one challenge with the system is that it’s relatively easy to get started and train models to recognize basic motions and environmental changes. This may be sufficient for some applications, but addressing ML training and using the results from the model to implement more complex functions or forecasts can be a challenge. SmartEdge Agile makes acquisition of the data and linking it to Brainium much easier than trying to do the same thing with a more basic IoT stack.

The solution takes much of the security, communication, and sensor acquisition details out of the equation. However, one must keep the cost in mind. You will need to work with Avnet to deploy and manage many devices. Avnet can also provide support for developing custom sensor platforms as well as developing solutions that can be built using Brainium ML support.

Overall, SmartEdge Agile is a good starting point to familiarize yourself with IoT and ML in combination with the cloud. Doing more at the sensor or gateway will be a major undertaking, but working in the cloud will be trivial by comparison. Likewise, developing models using sensor data from the module will be easy. However, turning that into a product or service will still require a major effort. Nonetheless, using SmartEdge Agile may get one to that goal much more quickly.

Sponsored Recommendations

Board-Mount DC/DC Converters in Medical Applications

March 27, 2024
AC/DC or board-mount DC/DC converters provide power for medical devices. This article explains why isolation might be needed and which safety standards apply.

Use Rugged Multiband Antennas to Solve the Mobile Connectivity Challenge

March 27, 2024
Selecting and using antennas for mobile applications requires attention to electrical, mechanical, and environmental characteristics: TE modules can help.

Out-of-the-box Cellular and Wi-Fi connectivity with AWS IoT ExpressLink

March 27, 2024
This demo shows how to enroll LTE-M and Wi-Fi evaluation boards with AWS IoT Core, set up a Connected Health Solution as well as AWS AT commands and AWS IoT ExpressLink security...

How to Quickly Leverage Bluetooth AoA and AoD for Indoor Logistics Tracking

March 27, 2024
Real-time asset tracking is an important aspect of Industry 4.0. Various technologies are available for deploying Real-Time Location.

Comments

To join the conversation, and become an exclusive member of Electronic Design, create an account today!