A High-Precision Magnetic-Assisted Heading Angle Calculation Method Based on a 1D Convolutional Neural Network (CNN) in a Complicated Magnetic Environment
Due to its widespread presence and independence from artificial signals, the application of geomagnetic field information in indoor pedestrian navigation systems has attracted extensive attention from researchers. However, for indoors environments, geomagnetic field signals can be severely disturbed...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-06-01
|
Series: | Micromachines |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-666X/11/7/642 |
id |
doaj-106b353f61b44c82b9a5ea02359435ed |
---|---|
record_format |
Article |
spelling |
doaj-106b353f61b44c82b9a5ea02359435ed2020-11-25T03:38:30ZengMDPI AGMicromachines2072-666X2020-06-011164264210.3390/mi11070642A High-Precision Magnetic-Assisted Heading Angle Calculation Method Based on a 1D Convolutional Neural Network (CNN) in a Complicated Magnetic EnvironmentGuanghui Hu0Hong Wan1Xinxin Li2State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, ChinaState Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, ChinaState Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, ChinaDue to its widespread presence and independence from artificial signals, the application of geomagnetic field information in indoor pedestrian navigation systems has attracted extensive attention from researchers. However, for indoors environments, geomagnetic field signals can be severely disturbed by the complicated magnetic, leading to reduced positioning accuracy of magnetic-assisted navigation systems. Therefore, there is an urgent need for methods which screen out undisturbed geomagnetic field data for realizing the high accuracy pedestrian inertial navigation indoors. In this paper, we propose an algorithm based on a one-dimensional convolutional neural network (1D CNN) to screen magnetic field data. By encoding the magnetic data within a certain time window to a time series, a 1D CNN with two convolutional layers is designed to extract data features. In order to avoid errors arising from artificial labels, the feature vectors will be clustered in the feature space to classify the magnetic data using unsupervised methods. Our experimental results show that this method can distinguish the geomagnetic field data from indoors disturbed magnetic data well and further significantly improve the calculation accuracy of the heading angle. Our work provides a possible technical path for the realization of high-precision indoor pedestrian navigation systems.https://www.mdpi.com/2072-666X/11/7/642magnetic-assistedone-dimensional convolutional neural network (1D CNN)magnetic anomaly detectionpedestrian inertial navigation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Guanghui Hu Hong Wan Xinxin Li |
spellingShingle |
Guanghui Hu Hong Wan Xinxin Li A High-Precision Magnetic-Assisted Heading Angle Calculation Method Based on a 1D Convolutional Neural Network (CNN) in a Complicated Magnetic Environment Micromachines magnetic-assisted one-dimensional convolutional neural network (1D CNN) magnetic anomaly detection pedestrian inertial navigation |
author_facet |
Guanghui Hu Hong Wan Xinxin Li |
author_sort |
Guanghui Hu |
title |
A High-Precision Magnetic-Assisted Heading Angle Calculation Method Based on a 1D Convolutional Neural Network (CNN) in a Complicated Magnetic Environment |
title_short |
A High-Precision Magnetic-Assisted Heading Angle Calculation Method Based on a 1D Convolutional Neural Network (CNN) in a Complicated Magnetic Environment |
title_full |
A High-Precision Magnetic-Assisted Heading Angle Calculation Method Based on a 1D Convolutional Neural Network (CNN) in a Complicated Magnetic Environment |
title_fullStr |
A High-Precision Magnetic-Assisted Heading Angle Calculation Method Based on a 1D Convolutional Neural Network (CNN) in a Complicated Magnetic Environment |
title_full_unstemmed |
A High-Precision Magnetic-Assisted Heading Angle Calculation Method Based on a 1D Convolutional Neural Network (CNN) in a Complicated Magnetic Environment |
title_sort |
high-precision magnetic-assisted heading angle calculation method based on a 1d convolutional neural network (cnn) in a complicated magnetic environment |
publisher |
MDPI AG |
series |
Micromachines |
issn |
2072-666X |
publishDate |
2020-06-01 |
description |
Due to its widespread presence and independence from artificial signals, the application of geomagnetic field information in indoor pedestrian navigation systems has attracted extensive attention from researchers. However, for indoors environments, geomagnetic field signals can be severely disturbed by the complicated magnetic, leading to reduced positioning accuracy of magnetic-assisted navigation systems. Therefore, there is an urgent need for methods which screen out undisturbed geomagnetic field data for realizing the high accuracy pedestrian inertial navigation indoors. In this paper, we propose an algorithm based on a one-dimensional convolutional neural network (1D CNN) to screen magnetic field data. By encoding the magnetic data within a certain time window to a time series, a 1D CNN with two convolutional layers is designed to extract data features. In order to avoid errors arising from artificial labels, the feature vectors will be clustered in the feature space to classify the magnetic data using unsupervised methods. Our experimental results show that this method can distinguish the geomagnetic field data from indoors disturbed magnetic data well and further significantly improve the calculation accuracy of the heading angle. Our work provides a possible technical path for the realization of high-precision indoor pedestrian navigation systems. |
topic |
magnetic-assisted one-dimensional convolutional neural network (1D CNN) magnetic anomaly detection pedestrian inertial navigation |
url |
https://www.mdpi.com/2072-666X/11/7/642 |
work_keys_str_mv |
AT guanghuihu ahighprecisionmagneticassistedheadinganglecalculationmethodbasedona1dconvolutionalneuralnetworkcnninacomplicatedmagneticenvironment AT hongwan ahighprecisionmagneticassistedheadinganglecalculationmethodbasedona1dconvolutionalneuralnetworkcnninacomplicatedmagneticenvironment AT xinxinli ahighprecisionmagneticassistedheadinganglecalculationmethodbasedona1dconvolutionalneuralnetworkcnninacomplicatedmagneticenvironment AT guanghuihu highprecisionmagneticassistedheadinganglecalculationmethodbasedona1dconvolutionalneuralnetworkcnninacomplicatedmagneticenvironment AT hongwan highprecisionmagneticassistedheadinganglecalculationmethodbasedona1dconvolutionalneuralnetworkcnninacomplicatedmagneticenvironment AT xinxinli highprecisionmagneticassistedheadinganglecalculationmethodbasedona1dconvolutionalneuralnetworkcnninacomplicatedmagneticenvironment |
_version_ |
1724542034331566080 |