An AI Machine Learning Beacon-Based Indoor Location System

There’s a recent paper by researchers at DeustoTech Institute of Technology, Bilbao, Spain and Department of Engineering for Innovation, University of Salento, Lecce, Italy on Behavior Modeling for a Beacon-Based Indoor Location System.

The research compares two different approaches to track a person indoors using Bluetooth LE technology with a smartphone and a smartwatch used as monitoring devices.

The beacons were iB005N supplied by us and it’s the first time we have been referenced in a research paper.

The research is novel in that it uses AI machine learning to attempt location prediction.

The researchers were able to predict the user’s next location with 67% accuracy.

Location prediction has some interesting and useful applications. For example, you might stop a vulnerable person going outside a defined area or in an industrial setting stop a worker going into a dangerous area.

Bluetooth LE Learning Resources

Bluetooth LE development is getting very popular with an increasing number of learning resources. Here are some that have appeared recently:

Erik Hellman, a developer, has two useful articles Bluetooth LE for modern Android Development part1 and part2. He covers Android versions, Bluetooth GATT, PHY, Android Device Manager, pairing and bonding.

Litum have a new article What is Bluetooth Low Energy (BLE)? How does BLE work? that’s higher level and less technical covering Bluetooth LE device discovery, differences to Classic Bluetooth, how positioning works, Bluetooth range , usecases and industries.

Zephyr, the embedded systems OS have also recently updated their Bluetooth documentation.

A Comparison of Beacon Locating Methods in a Retail Store

There’s a recent paper by researchers at the Department of Management Science and Technology, Athens University of Economics and Business on An Ensemble Filter for Indoor Positioning in a Retail Store Using Bluetooth Low Energy Beacons.

The paper starts with an overview of indoor positioning techniques including trilateration, fingerprinting, dead reckoning and AI machine learning. It also provides a synposis of different technologies such as RFID, WiFi and Bluetooth.

The paper explains that while fingerprinting is widely used, it faces limitations when used in dynamically changing environments. Fingerprinting requires ongoing maintenance and updating of the reference fingerprinting map that’s manually intensive and time-consuming. Fingerprinting also requires a large number of beacon reference points to perform accurate locating.

The researchers looked into positioning within a two floor (grocery) retail store. Retail stores are of of the more challenging environments as there are shoppers moving about that can affect indoor localisation

Several indoor positioning techniques were considered including fingerprinting and trilateration. The researchers implemented fingerprinting and compared it to seven established classifiers. The random forest algorithm worked the best and inspired the authors to build an ensemble classification filter with lower absolute mean and root mean squared errors.

Beacons Aid Accessibility in Toronto

Mohari Hospitality and SH Hotels & Resorts have just opened the re-designed 1 Hotel Toronto as part of downtown Toronto’s urban regeneration.

1 Hotel Toronto

Beacons have been placed in the communal indoor and outdoor spaces as part of CNIB’s Accessible Neighbourhoods Project. The project improves access to city areas by making them more accessible.

Improving accessibility in Toronto

The BlindSquare Beacon Positioning System (BPS) broadcasts a unique ID that’s received by smartphones. The ID is used to look up the information linked to the beacon that’s presented to the user.

BPS App

There’s more detailed information on the BPS in the user guide.

Can You Provide iBeacons That Pop Up Smartphone Notifications?

You might have read that beacons can be used to pop up notifications. Such a mechanism, called Google Nearby Notifications, existed prior to October 2018 after which it was discontinued.

Today, there are two ways to cause beacons to trigger notifications:

Nordic Semiconductor Wireless Quarter Magazine Published

Nordic Semiconductor, the manufacturer of the System on a Chip (SoC) used in many beacons, has published the latest online issue of Wireless Quarter Magazine. It showcases the many uses of Nordic SoCs.

Highlights include:

  • Nordic Semiconductor has launched an Apple Find My network compatible SDK
  • A new Bluetooth device that could help vapers quit
  • A Bluetooth LE smart pen that monitors aesthetic levels during surgery

There’s an in-depth article ‘Evolving Intelligence’ that covers AI machine learning. It explains how bandwidth limitations, latency demands and privacy concerns are dictating that machine learning move from the Cloud to edge devices. Battery powered IoT modules are able to perform machine learning inference in real-time allowing decision making near to where sensor data is generated and used.

Learn about Beaconzone SensorCognition™

What’s the Best iBeacon?

We often get asked what’s the best iBeacon? Unfortunately, there is no one best beacon for all scenarios. It depends on your particular project and business requirements. Having said this we have some favourites based on specific characteristics:

Best for Price: FSC-BP103 – Inexpensive beacon that transmits up to 10 channels simultaneously:

Best for Features: M52-SA Plus – Large easy replaceable battery, long range, temperature, humidity, accelerometer:

iBeacon

Best for Battery Life: SmartBeacon-AA Pro (no longer available) – Allows use of 4x AA batteries. Use lithium AA batteries for 7+ year battery life (also depends on settings).

Best for Setup App: Minew range – Minew’s latest BeaconPlus range (those supporting both iBeacon and Eddystone) provides the best in class app.

View our complete range.

IoT Projects with Bluetooth Low Energy

Our article on Beacon Proximity and Sensing for the Internet of Things (IoT) provides short summary how to use Bluetooth for IoT.

If you need a more rigorous description take a look at the book IoT Projects with Bluetooth Low Energy. It covers the fundamental aspects of Bluetooth Low Energy scanning, services, and characteristics. It goes on to describe examples of how to monitor health data, perform indoor navigation and use the Raspberry Pi for Bluetooth solutions. The book’s code is also available on GitHub.

View Sensor Beacons