In this blog, we’ll discuss how users of Edge Impulse and Nordic can actuate and stream classification results over BLE using Nordic’s UART Service (NUS). This makes it easy to integrate embedded machine learning into your next generation IoT applications. Seamless integration with nRF Cloud is also possible since nRF Cloud has native support for a BLE terminal. 

We’ve extended the Edge Impulse example functionality already available for the nRF52840 DK and nRF5340 DK by adding the abilities to actuate and stream classification outputs. The extended example is available for download on github, and offers a uniform experience on both hardware platforms. 

Using nRF Toolbox 

After following the instructions in the example’s readme, download the nRF Toolbox mobile application (available on both iOS and Android) and connect to the nRF52840 DK or the nRF5340 DK that will be discovered as “Edge Impulse”. Once connected, set up the interface as follows so that you can get information about the device, available sensors, and start/stop the inferencing process. Save the preset configuration so that you can load it again for future use. Fill out the text of the various commands to use the same convention as what is used for the Edge Impulse AT command set. For example, sending AT+RUNIMPULSE starts the inferencing process on the device. 

Figure 1. Setting up the Edge Impulse AT Command set

Once the appropriate AT command set mapping to an icon has been done, hit the appropriate icon. Hitting the ‘play’ button cause the device to start acquiring data and perform inference every couple of seconds. The results can be viewed in the “Logs” menu as shown below.

Figure 2. Classification Output over BLE in the Logs View

Using nRF Cloud

Using the nRF Connect for Cloud mobile app for iOS and Android, you can turn your smartphone into a BLE gateway. This allows users to easily connect their BLE NUS devices running Edge Impulse to the nRF Cloud as an easy way to send the inferencing conclusions to the cloud. It’s as easy as setting up the BLE gateway through the app, connecting to the “Edge Impulse” device and watching the same results being displayed in the “Terminal over BLE” window shown below!

Figure 3. Classification Output Shown in nRF Cloud

Summary

Edge Impulse is supercharging IoT with embedded machine learning and we’ve discussed a couple of ways you can easily send conclusions to either the smartphone or to the cloud by leveraging the Nordic UART Service. We look forward to seeing how you’ll leverage Edge Impulse, Nordic and BLE to create your next gen IoT application.  

Article originally written for the Edge Impulse blog by Zin Thein Kyaw, Senior User Success Engineer at Edge Impulse.

IoT technologies or "Internet of Things" collect and analyze information about the object, its movement, condition, and many other features. In the European Union alone there are currently more than 13.3 millions of active trackers that use this system, which is a significant growth compared to 0.7 of a million in 2016.

An object of observation will be tagged for tracking with a relatively small device that collects the necessary information and sends it to you via Wi-Fi. But how one should know which type of IoT solutions to choose?

IoT Tracking Technologies

1. RFID tags

RFID tags use radio frequency to identify the right element or track a certain "tag". In comes in two types:

• Passive RFID tag depends on the RFID reader to send a wave that they can use to reply. For example, to see who passes through the reader bars in the store with an unpaid product.
• Active RFID tags have an identifier along with a battery inside, which allows it to communicate with a reader on a larger distance.

2. BLE beacons

BLE beacons rely on Bluetooth Low Energy so they can communicate, often used inside mobile phones. They can send multiple types of signals and detect many devices around them.

Beacons come in different forms and devices:

• Parent beacons process and collect received data, communicate with child-beacons.
• USB beacons
• Router-sized beacons
• Small portable beacons

3. NFC chips

Near Field Communication is one of IoT technologies that rely on the electromagnetic field when are very close to each other (5-20 centimeters). NFC devices interact similar to RFID, can also be active and passive:

• Active NFC sends and receives data (for example, it's being used on smartphones)
• Passive NFC only sends information

4. Zigbee hardware

Zigbee was invented for more complicated communication. They create a small network in a limited area, powered by a small radio.

Zigbee chips are widely used in radios and USB interfaces among other IoT solutions. It's also famous for its low cost and power expenses.

5. LTE advanced

Long-Term Evolution is a wireless communication technology that was developed for faster internet, bigger storage and data processing. It's mostly used by mobile phones but sadly has different regions depending on the country where the phone was produced, with no support for a different frequency.

6. LiFi

Visible Light Communication based Light Fidelity uses diodes to communicate at the speed of light without a chance for a human to notice the signal. The signal is then received by a photodetector.

LiFi is known to be the biggest rival of WiFi, though it's limited to the reach of the light that can be stopped by an obstacle.

7. GPS

Everyone who owns a phone is familiar with Global Positioning System, which provides geolocation at a certain time to all GPS receiving devices. While still haven't beat by its accuracy in tracking, GPS is known to be quite power-consuming because it determines an object's location in non-stop mode.

8. LPWAN

Low Power Wide Area Networks is created for long-distance communication and uses a low bit rate. It also allows to create a private wireless network.

Here some of the LPWAN based technologies:

• NB-IoT uses a wide range in cellular services and devices
• LoRaWAN uses a chirp spectrum radio module along with LPWAN technology
• DASH7 is a firmware standard with low-latency, used over LPWAN

How IoT tracking helps in your business

Which of the IoT technologies is the best suited for your business?

Commercial Organization

• A commercial organization may track their assets using RFID tags, such as Amazon keeps track of products in their vendor places
• BLE beacons can help understand the customers, how much time they spend in the store, which aisles they visit and how they move across them
• NFC technologies allow your customers to pay faster with their wireless credit cards
• Zigbee is a necessity for those who develop smart home devices
• LiFi help you set up shop displays and show advertisements to the customers

Industrial Business

• BLE beacons help organize the inner industrial process, track equipment, monitor assets, prevent human errors and incidents
• NFC takes care of security and access control
• Zigbee helps with remote monitoring in a company with a large facility. However the cost rise drastically when operating between the facilities, so it's not used
• LTE Advanced can instantly notify of a security breach and needed maintenance, write reports, draw a map of assets real-time movement
• LPWAN optimizes costs and energy losses and power outrage. It monitors liquid levels, energy installations, optimizes solar plants performance

Healthcare Facility

• RFID helps manage medical equipment and monitor the room's condition. It also helps with identification badges
• BLE beacons help with indoor navigation
• NFC tracks the patient's location, their time of treatment and health at home
• Zigbee can monitor patients in real-time at low-cost
• GPS tracks down the location of an emergency case
• Li-Fi can lag when the light is interrupted. Otherwise, it's a perfect tool since it doesn't mess with another equipment
• LTE has a personal network for enterprises. It's a large and secure network at a hospital

Logistics

• RFID identifies a vehicle, person, baggage and therefore is helpful at railroad, airports, and roads
• NFC helps scan tickets and trains passes fast
• GPS helps to locate fleet vehicles and contact them
• Modified with LED bulbs, LiFi cars help to prevent a collision in advance
• Paired with other technologies, LTE Advanced can monitor the flight in real-time and communicate in long-distance
• LPWAN can trace objects in real-time, optimize routes, detect and resolve faults, road threats, and maintenance

Agriculture and Food

• RFID is helpful with tagging and locating cattle and food
• GPS allows to plow and place crops precisely, map and monitor the field and save costs from farming
• LPWAN is useful for measuring the soil moisture, water levels, cattle hygiene, and gate security

A wide range of IoT object tracking technologies is created to serve different purposes. Decide among the best of IoT solutions for yourself or read more in our blog to help determine which option is the best for you.