A Bluetooth Indoor Positioning System Based on Deep Learning with RSSI and AoA

Traditional received signal strength indicator (RSSI)-based and angle of arrival (AoA)-based positioning methods are highly susceptible to multipath effects, signal attenuation, and noise interference in complex indoor environments, which significantly degrade positioning accuracy. To mitigate the i...

Full description

Saved in:
Bibliographic Details
Main Authors: Yongjie Yang, Hao Yang, Fandi Meng
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/9/2834
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850135677070475264
author Yongjie Yang
Hao Yang
Fandi Meng
author_facet Yongjie Yang
Hao Yang
Fandi Meng
author_sort Yongjie Yang
collection DOAJ
description Traditional received signal strength indicator (RSSI)-based and angle of arrival (AoA)-based positioning methods are highly susceptible to multipath effects, signal attenuation, and noise interference in complex indoor environments, which significantly degrade positioning accuracy. To mitigate the impact of the above deterioration, we propose a deep learning-based Bluetooth indoor positioning system, which employs a Kalman filter (KF) to reduce the angular error in AoA measurements and utilizes a median filter (MF) and moving average filter (MAF) to mitigate fluctuations in RSSI-based distance measurements. In the deep learning network architecture, we propose a convolutional neural network (CNN)–multi-head attention (MHA) model. During the training process, the backpropagation (BP) algorithm is used to compute the gradient of the loss function and update the parameters of the entire network, gradually optimizing the model’s performance. Experimental results demonstrate that our proposed indoor positioning method achieves an average error of 0.29 m, which represents a significant improvement compared to traditional RSSI and AoA methods. Additionally, it displays superior positioning accuracy when contrasted with numerous emerging indoor positioning methodologies.
format Article
id doaj-art-4c11240d36f048379a00a55fb6247da3
institution OA Journals
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-4c11240d36f048379a00a55fb6247da32025-08-20T02:31:20ZengMDPI AGSensors1424-82202025-04-01259283410.3390/s25092834A Bluetooth Indoor Positioning System Based on Deep Learning with RSSI and AoAYongjie Yang0Hao Yang1Fandi Meng2School of Information Science and Technology, Nantong University, Nantong 226019, ChinaSchool of Information Science and Technology, Nantong University, Nantong 226019, ChinaSchool of Information Science and Technology, Nantong University, Nantong 226019, ChinaTraditional received signal strength indicator (RSSI)-based and angle of arrival (AoA)-based positioning methods are highly susceptible to multipath effects, signal attenuation, and noise interference in complex indoor environments, which significantly degrade positioning accuracy. To mitigate the impact of the above deterioration, we propose a deep learning-based Bluetooth indoor positioning system, which employs a Kalman filter (KF) to reduce the angular error in AoA measurements and utilizes a median filter (MF) and moving average filter (MAF) to mitigate fluctuations in RSSI-based distance measurements. In the deep learning network architecture, we propose a convolutional neural network (CNN)–multi-head attention (MHA) model. During the training process, the backpropagation (BP) algorithm is used to compute the gradient of the loss function and update the parameters of the entire network, gradually optimizing the model’s performance. Experimental results demonstrate that our proposed indoor positioning method achieves an average error of 0.29 m, which represents a significant improvement compared to traditional RSSI and AoA methods. Additionally, it displays superior positioning accuracy when contrasted with numerous emerging indoor positioning methodologies.https://www.mdpi.com/1424-8220/25/9/2834AoA positioningRSSI positioningdeep learningmulti-head attentionconvolutional neural networkbackpropagation
spellingShingle Yongjie Yang
Hao Yang
Fandi Meng
A Bluetooth Indoor Positioning System Based on Deep Learning with RSSI and AoA
Sensors
AoA positioning
RSSI positioning
deep learning
multi-head attention
convolutional neural network
backpropagation
title A Bluetooth Indoor Positioning System Based on Deep Learning with RSSI and AoA
title_full A Bluetooth Indoor Positioning System Based on Deep Learning with RSSI and AoA
title_fullStr A Bluetooth Indoor Positioning System Based on Deep Learning with RSSI and AoA
title_full_unstemmed A Bluetooth Indoor Positioning System Based on Deep Learning with RSSI and AoA
title_short A Bluetooth Indoor Positioning System Based on Deep Learning with RSSI and AoA
title_sort bluetooth indoor positioning system based on deep learning with rssi and aoa
topic AoA positioning
RSSI positioning
deep learning
multi-head attention
convolutional neural network
backpropagation
url https://www.mdpi.com/1424-8220/25/9/2834
work_keys_str_mv AT yongjieyang abluetoothindoorpositioningsystembasedondeeplearningwithrssiandaoa
AT haoyang abluetoothindoorpositioningsystembasedondeeplearningwithrssiandaoa
AT fandimeng abluetoothindoorpositioningsystembasedondeeplearningwithrssiandaoa
AT yongjieyang bluetoothindoorpositioningsystembasedondeeplearningwithrssiandaoa
AT haoyang bluetoothindoorpositioningsystembasedondeeplearningwithrssiandaoa
AT fandimeng bluetoothindoorpositioningsystembasedondeeplearningwithrssiandaoa