More Accurate Beacon Locating Using AI Machine Learning

There’s new research in the Bulletin of Electrical Engineering and Informatics on Bluetooth beacons based indoor positioning in a shopping malls using machine learning. Researchers from Algeria and Italy improved the accuracy of RSSI locating by using AI machine learning techniques. They used extra-trees classifier (ETC) and a k-neighbours classifier to achieve greater than 90% accuracy.

A smartphone app was used to receive beacon RSSI and send it to an indoor positioning system’s data collection module. RSSI data was also filtered by a data processing module to limit the error range. KNN, RFC, extra trees classifiers (ETC), SVM, gradient boosting classifiers (GBC) and decision trees (DT) algorithms were evaluated.

The ETC model gave the best accuracy. ETC is an algorithm that uses a group of decision trees to classify data. It is similar to a random forest classifier but uses a different method to construct the decision trees. ETC fits a number of randomised decision trees on sub-samples of the dataset and uses averaging to improve the predictive accuracy and control over-fitting. ETC is a good choice for applications where accuracy is important but the data is noisy and where computational efficiency is important.

Using AI Machine Learning to Improve Ranging Accuracy

There’s new research from Oregon State University, USA and Peking University, Beijing, China on A Machine Learning Approach to Improve Ranging Accuracy with AoA and RSSI.

System Workflow

Machine learning was used to determine the line-of-sight distance in a multipath (reflective) environment. Due to the multipath effect, acquired signals indoors have complex mathematical models. A machine learning Artificial Neural Networks (ANN) is the most efficient way to process these signals.

The system achieved accuracy where 75% of the errors were less than 0.1 m with a median error of 0.037 m and a mean error of 0.092 m. This reduced ranging errors to under 10cm. The researchers were able to achieve high-precision indoor ranging without the need for a wide signal bandwidth nor synchronisation. The system was also simple and low cost to deploy due to low complexity of the equipment.

Using AI Machine Learning with Bluetooth Angle of Arrival (AoA)

There’s new research from Universities in Piraeus, Greece and Berlin, Germany, together with U-Blox AG in Switzerland who create Bluetooth Angle of Arrival prototyping boards on Deep Learning-Based Indoor Localization Using Multi-View BLE Signal.

Processing of Bluetooth Angle of Arrival usually requires radiogoniometry spectral analysis of radio in-phase and quadrature-phase (IQ) signals in order to then determine location by triangulation. Instead, this paper proposes machine learning of IQ and signal strength (RSSI) data from multiple anchor points to determine location. AoA processing also uses distributed processing across the anchors to improve performance.

The developed machine learning models were found to be robust against modifications of room furniture configurations and materials and it’s therefore expected that they have high re-usability (machine learning generalisation) potential. The system achieved a localization accuracy of 70cm.

Read about PrecisionRTLS™

Processing iBeacon RSSI Using AI Machine Learning

There’s new research from China on Regional Double-Layer, High-Precision Indoor Positioning System Based on iBeacon Network.

The project used extended Gaussian filtering to delete and filter significant abnormal data values caused by multipath radio noise indoors. A deep neural network was also used to fingerprint data.

The system resulted in a maximum error positional error of only 1.02m.

Probabilistic vs Neural Network iBeacon Positioning

There’s new research by ITMO University, Russia on the Implementation of Indoor Positioning Methods: Virtual Hospital Case. The paper describes how positioning can be used to discover typical pathways, queues and bottlenecks in healthcare scenarios. The researchers implemented and compared two ways to mitigate noise in Bluetooth beacon RSSI data.

The probabilistic and neural network methods both use past recorded data to compare with new data. This is known as fingerprinting. The neural network method is less complex when there’s need to scale to locating many objects. The researchers tested the methods at the outpatient department of the cardio medical unit of Almazov National Medical Research Centre.

Comparison of the methods showed they give approximately the same error of between 0.96m and 2.11m. However, the neural network-based approach significantly increased performance.

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.

Using Bluetooth Sensor Beacons for AI Machine Learning

Sensor beacons provide a quick and easy way to obtain data for AI machine learning. They provide a way of measuring physical processes to provide for detection and prediction.

Beacon Temperature Sensor

Beacons detect movement (accelerometer), movement (started/stopped moving), button press, temperature, humidity, air pressure, light level, open/closed (magnetic hall effect), proximity (PIR), proximity (cm range), fall detection, smoke and natural gas. The open/closed (magnetic hall effect) is particularly useful as it can be used on a multitude of physical things for scenarios that require digitising counts, presence and physical status.

The data is sent via Bluetooth rather than via cables which means there’s no soldering or physical construction. The Bluetooth data can be read by smartphones, gateways or any devices that have Bluetooth LE. From there it can be stored in files for reading into machine learning.

Such data is often complex and it’s difficult for a human to devise a conventional programming algorithm to extract insights. This is where AI machine learning excels. In simple terms, it reads in recorded data to find patterns in the data. The result of this learning is a model. The model is then used during inference to classify or predict situations based on new incoming data.

The above shows some output from accelerometer data fed into one of our models. The numbers are distinct features found over the time series as opposed to a single x,y,z sample. For example ’54’ might be a peak and ’61’ a trough. More complex features are also detectable such as ‘120’ being the movement of the acceleration sensor in a circle. This is the basis for machine learning classification and detection.

It’s also possible to perform prediction. Performing additional machine learning (yes, machine learning on machine learning!) on the features to produce a new model tells us what usually happens after what. When we feed in new data to this model we can predict what is about to happen.

The problem with sensor data is there can be a lot of it. It’s inefficient and slow to detect events when this processing at the server. We create so called Edge solutions that do this processing closer to the place of detection.

Read more about SensorCognition

Understanding Sensor Beacon Accelerometer Data

In this post we will take a look at data from the INGICS iGS01RG beacon.

The x axis is time. You can see the x, y and z values, every 100ms, over time. The y axis is normalised between -1 and -1 for use in our SensorCognition Edge device. The chart is for when the beacon has been moving, followed by a stationary period. Notice how the orange line continues to show acceleration even though the beacon isn’t moving. This is caused by gravity.

In this chart the beacon has been flipped over and the orange line now shows a constant negative acceleration.

A good thing about the presence of a constant offset in one of the x y z inputs is that it can be used to help determine the orientation of the beacon. The less desirable aspect is that the offset significantly complicates using the x y z to determine types of movement such as human gestures.

Such complex data problems are more easily solved using AI machine learning than trying to write a traditional algorithm to make sense of the data.

Here’s an example of output from a SensorCognition Edge device trained with up and down movement and left and right movement. In this case, the output 227 is showing the beacon is moving left and right.

Read about SensorCognition

The State of AI in 2019

Beacons provide a great way of providing new data for AI machine learning. They allow you to measure things that aren’t currently being quantified, create new data that isn’t silo’d by protectionist staff or departments and allow you to pre-process data in-place making it suitable for learning and inference.

There’s a new free State of AI Report 2019 in the form of a 136 page presentation. It covers aspects such as research, talent, industry and geopolitical areas such as China and Politics.

Read more about AI Machine Learning with Beacons

The Crux of Machine Learning is Realistic Expectations

Venturebeat has an article, based on IDC research, titled For 1 in 4 companies, half of all AI projects fail.

“Firms blamed the cost of AI solutions, a lack of qualified workers, and biased data as the principal blockers impeding AI adoption internally. Respondents identified skills shortages and unrealistic expectations as the top two reasons for failure, in fact, with a full quarter reporting up to 50% failure rate.”

We believe a key part of this is ‘unrealistic expectations’. Half of all AI projects failing for 1 in 4 companies isn’t unreasonable. AI and machine learning should be viewed as a research rather than a development activity in that it’s often the case that it’s not known if the goal is achievable until you try.

Another unrealistic expectation of machine learning is often to have 100% accuracy. The use of an accuracy % in assessing machine learning models focuses stakeholders minds too much on the perceived need for a very high accuracy. In reality, human-assessed, non-machine learning, processes such as medical diagnosis tend to have much less than 100% accuracy and sometimes have undetermined accuracy but these are reasonably seen as being acceptable.

In summary, there has to be upfront realistic expectations of both the possible outcome and the accuracy of the outcome for projects to correctly determine if AI activities are an unexpected failure.

Read about AI Machine Learning with Beacons