Deep Learning-Based Indoor Localization Using Multi-View BLE Signal

Abstract

In this paper, we present a novel Deep Neural Network-based indoor localization method that estimates the position of a Bluetooth Low Energy (BLE) transmitter (tag) by using the received signals’ characteristics at multiple Anchor Points (APs). We use the received signal strength indicator (RSSI) value and the in-phase and quadrature-phase (IQ) components of the received BLE signals at a single time instance to simultaneously estimate the angle of arrival (AoA) at all APs. Through supervised learning on simulated data, various machine learning (ML) architectures are trained to perform AoA estimation using varying subsets of anchor points. In the final stage of the system, the estimated AoA values are fed to a positioning engine which uses the least squares (LS) algorithm to estimate the position of the tag. The proposed architectures are trained and rigorously tested on several simulated room scenarios and are shown to achieve a localization accuracy of 70 cm. Moreover, the proposed systems possess generalization capabilities by being robust to modifications in the room’s content or anchors’ configuration. Additionally, some of the proposed architectures have the ability to distribute the computational load over the APs.

Advances in Indoor Positioning and Indoor Navigation

“…AI is nowadays being applied in many situations, and indoor positioning is one of them. Koutris et al [ 9 ] propose a deep-neural-network-based indoor localization method. They use the received signal strength indicator (RSSI) and the in-phase and quadrature-phase (IQ) from Bluetooth Low-Energy (BLE) Anchor Points (APs) to estimate the angle of arrival (AoA) at all APs.…”

Deep-Learning-Based Antenna Alignment Prediction for Mobile Indoor Communication

“…The most-significant difference is that our solution does not care where the UE is located or in which room it can be found, only where the antenna beam should be directed. However, the procedures and considerations highlighted in [ 8 ] may be also advantageous, where various Neural Network (NN) solutions were applied to Bluetooth Low Energy signals for angle-of-arrival-based position determination. Their best performing solution is based on a convolutional NN, which requires intensive data preparation.…”

Deep Learning‐Based Bluetooth Low‐Energy 5.1 Multianchor Indoor Positioning with Attentional Data Filtering

“…While deep neural networks are successfully applied to different application domains, it is no surprise that they are also used in IPS design. [9][10][11] Recently, some efforts have been made to develop deep learning (DL)-based models for BLE 5.1 IPS such as using the convolutional neural network (CNN) [11] and recurrent neural network. [10] These approaches often use the fingerprint-based method such that object positioning is converted into a classification problem of the I/Q sample fingerprints.…”