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 AKMW-iB005N-SMA 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.

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.

Improving Indoor Locating Using Kalman Filtering and a Particle Filter

There’s recent research from Korea on Particle Filtering-Based Indoor Positioning System for Beacon Tag Tracking. The paper looks into how to improve positioning accuracy, reduce system complexity and reduce deployment cost through the use of a Particle Filter-based Indoor Positioning System (PFIPS).

A Kalman Filter is used to preprocess collected Received Signal Strength Indication (RSSI) data followed by a Particle Filter (PF) to approximate the location of a tag which improves the location certainties.

Simulations and experiments showed the system outperformed the legacy indoor positioning systems in terms of location accuracy by 24.1% and achieved median accuracy of 1.16 m.

Read Using Beacons, iBeacons for Real-time Locating Systems (RTLS)

Improving iBeacon Location Accuracy

There are lots of ways of processing Bluetooth signal strength (RSSI) to determine location. Being based on radio, RSSI suffers from fluctuations, over time, even when the sender and receiver don’t move.

The College of Surveying and GeoInformatics, Tongji University, Shanghai , China has new research on iBeacon-based method by integrating a trilateration algorithm with a specific fingerprinting method to resist RSS fluctuations.

Trilateration and fingerprinting are common techniques to improve location accuracy based on RSSI. The paper improves on these by using analysis based on Kalman filtering of segments delimited by turns. This is used to derive locations based on pedestrian dead reckoning.

The researchers achieved a positioning accuracy of 2.75m.

Read about Determining Location Using Bluetooth Beacons

Read about Using Beacons, iBeacons for Real-time Locating Systems (RTLS)

Sensor Placement Optimisation Research

There’s interesting new research into Sensor Placement Optimization for Critical-grid Coverage Problem of Indoor Positioning (PDF).

This research looked into optimising the location of sensors as opposed to the more usual methods of filtering signals to improve accuracy. The aim was to reduce deployment costs by deploying more sensors in critical areas that were identified as needing greater positioning accuracy.

The critical-grid coverage scheme and NSGA-II algorithm were used to optimise the placement of iBeacon nodes in underground parking lots.

Read about Using Beacons, iBeacons for Real-time Locating Systems (RTLS)

Occupancy Detection Using BLE Beacons

The Covid pandemic has resulted in many organisations looking to quantify occupancy. This is especially so in education where government guidelines tend to be based on occupancy as well as social distancing.

Occupancy isn’t just relevant to pandemics. It’s also a factor in, for example, building emergency management when determining the optimal plan of action, for example, when allocating emergency personnel. Similar situations exist in police and military settings where, additionally, it’s advantageous to know the real time location of assets, people and casualties.

Past research on Occupancy Detection for Building Emergency Management Using BLE Beacons investigated use of a system made up of Bluetooth beacons installed in rooms and an app installed on occupants’ smartphones.

The research system used Raspberry Pis as iBeacons and Android phones as Bluetooth detectors. Fingerprinting was used to to produce data that fed into a multi-class SVM classification with classes being different room areas. The system was able to provide high occupancy accuracy and identify occupant movement patterns.

There are many problems with using such a system in real life. The Raspberry Pi beacons are fragile and have long term reliability problems due to the use of Micro SD storage. Systems based on fingerprinting rarely work long term because wireless signals change when there are changes in the physical environment such as more people or change in furniture. Using smartphones as detectors also isn’t always reliable because people fiddle with apps, change permissions and real time use implies a larger battery drain.

Instead, it’s necessary to turn the system around and have beacons on people and use dedicated devices, gateways, as detectors. In the simplest case, the gateways send detections to a server to be processed. More sophisticated systems such as our BeaconRTLS™ provide intelligent processing, mapping, alerts and reporting such as occupancy per zone.

Read about Using Beacons, iBeacons for Real-time Locating Systems (RTLS)

iBeacon RSSI Anomaly Detection for Indoor Positioning

There’s new research on iBeacon Indoor Positioning Method Combined with Real-Time Anomaly Rate to Determine Weight Matrix that uses a weighted Levenberg-Marquadt (LM) algorithm to determine the location of ibeacons.

The solution processes the received signal strength (RSSI) to determine anomaly rates of beacons and hence filter out abnormal signals. This helps to overcome the problems of unreliable signal strength in indoor locations due to reflections and obstacles.

The system achieves an average positioning error of 1.5m.

Read about Using Beacons, iBeacons for Real-time Locating Systems (RTLS)

Why Real Time Locating is Becoming More Popular

The recent Nordic Semiconductor wireless quarter magazine contained an article on positioning and real time locating systems (RTLS). RTLS is experiencing growth:

RTLS detects the position of people and assets in real time. Tags are attached to people or assets and the radio signals from the tag allow the location to be determined. The real time aspect is important because it provides the current position automatically, unlike barcode scans and and NRF tags that are only as up to date as the last successful scan. With older, manual, systems, people are lazy and forget to scan.

A complete RTLS system comprises of readers, tag/sensors, application software and communications/network infrastructure.

Asset tracking is being used in industry verticals such as healthcare, defence, education and manufacturing. It commonly tracks tools, equipment, pallets, sub-assemblies, jobs and completed goods.

People tracking has tended to be used more in education and health where the security of individuals is more important than privacy concerns related to tracking people.

RTLS growth is being driven by the benefit of real time tracking allowing processes to be much more efficient. Effort and time is saved when things and people can be found quickly. Alerts notify abnormal conditions to provide for proactive actions. Reports track long term trends to allow identification of patterns that can be used to change processes to improve efficiency.

Bluetooth is popular for use with RTLS because tags and readers are inexpensive compared to other technologies. Bluetooth also works indoors where GPS fails. Unlike other technologies, Bluetooth LE tags have a long battery life of up to several years. There are also tags that perform sensing and Bluetooth LE is suitable for use in electrically noisy environments. Bluetooth also integrates with Bluetooth LE devices such as smartphones, tablets, laptops and desktops.

At Beaconzone we are seeing two new trends in use of RTLS. The first is using RTLS for multiple purposes. Customers often come to us wanting to solve a particular problem but later find the RTLS has a multitude of uses and benefits. This is where a closed solution offering, for example, a lone worker solution, won’t be so flexible.

Established real-time location system market players are shifting from closed solution offerings to including best-in-breed components in application layer

Allied Market Research

The second trend, brought on by Covid, is the tracking of office workers. What might have used to be seen as an invasion of privacy is now being seen as an essential way to monitor room occupancy and determine who has been in the same room as someone else when a person tests positive for Covid.

Read about BeaconRTLS

iBeacon Deployment Parameters for Locating

Researchers from the The Hong Kong Polytechnic University have a new paper on Performance Evaluation of iBeacon Deployment for Location-Based Services in Physical Learning Spaces (pdf) that tests environmental and deployment factors, indoors and outdoors, related to using ibeacons for locating. It provides recommendations for iBeacon deployment in terms of location, density, transmission interval, fingerprint space interval and collection time.

iBeacon deployment

The paper provides a great introduction to positioning using beacon received signal strength (RSSI). It describes trilateration and fingerprinting methods for determining location.

Key insights are:

  • High temperature, strong wind and blocking by pedestrians degraded the signal strength.
  • Pedestrians traffic blocking the line of sight caused the most signal attenuation and variation.
  • High air temperature caused significant increase of packet loss that affected the RSSI.
  • Strong wind reduced the signal strength but didn’t affect the stability of signals.
  • Trees and nearby vehicle traffic didn’t have any negative effects on signals.
  • Lower error rates were observed when beacons were deployed on the ceiling as opposed to on the wall.
  • Positioning accuracy improved with ceiling placement due to the reduction of obstructions.
  • If ceilings are too high or ceiling deployment is impracticable wall mounted iBeacons should be placed as high as possible.
  • For fingerprinting, sample at 2m grid intervals for 6s to 10s at each point. Avoid having too many beacons as this won’t improve the positioning accuracy. A transmission interval of 100ms is detrimental to the positioning accuracy. 417ms is better.
  • For fingerprinting, positioning accuracy varies greatly according to the what is in the room.

The paper mentions that beacon UUID, major and minor are used to uniquely identify beacons. While this is true in the context of detecting using apps, most locating systems use gateways. Gateways use the Bluetooth MAC address to uniquely identify beacons and the advertising type, iBeacon, Eddystone or other, is irrelevant. Using gateways as receivers is also a solution to the problem of variability in receiving capability across smartphones.

The study only considered one beacon type and two receiving smartphones. At Beaconzone, we recommend experimenting with the actual hardware in the actual environment as, being wireless radio, optimum settings and can vary considerably.

Read about location accuracy

Read about Using Beacons, iBeacons for Real-time Locating Systems (RTLS)

Measuring Occupancy for Social Distancing

Governments are increasingly mandating workplace indoor occupancy limits due to the Coronavirus pandemic. This is especially so in education where the risk of reduced social distancing is being mitigated with occupancy limits.

Occupancy is the number of people that are currently inside a building, room or zone. Measuring occupancy manually requires significant effort, additional staff, is error prone and is difficult to achieve, especially when there are multiple entrances and exits.

It’s for this reason, we are seeing organisations starting to use automated approaches. Real time locating systems (RTLS) such as our BeaconRTLS™ use Bluetooth beacons on people and gateways in rooms/zones to track who is where. The resultant data provides for accurate current and historical occupancy.

Once you have a system in place it has lots of other uses:

  • Finding people
  • Locating staff for safety and evacuation
  • Finding expensive assets shared amongst staff
  • Providing alerts if things move when they shouldn’t
  • Detecting when collisions occur between vehicles/racking
  • Tracing of parts, sub-assemblies and physical orders
  • Supporting IoT sensing including light, temperature, humidity, water leak, gas
  • Creating big data for use with AI to provide insights using patterns the data

Read more about BeaconRTLS™