Full Text Views
49
Magnetic fields are often utilized for position sensing of mobile devices. In typical sensing systems, multiple sensors are used to detect magnetic fields generated by target devices. To determine the positions of the devices, magnetic-field data detected by the sensors must be converted to device-position data. The data conversion is not trivial because it is a nonlinear inverse problem. In this study, we propose a machine-learning approach suitable for data conversion required in the magnetic-field-based position sensing of target devices. In our approach, two different sets of training data are used. One of the training datasets is composed of raw data of magnetic fields to be detected by sensors. The other set is composed of logarithmically represented data of the fields. We can obtain two different predictor functions by learning with these training datasets. Results show that the prediction accuracy of the target position improves when the two different predictor functions are used. Based on our simulation, the error of the target position estimated with the predictor functions is within 10cm in a 2m × 2m × 2m cubic space for 87% of all the cases of the target device states. The computational time required for predicting the positions of the target device is 4ms. As the prediction method is accurate and rapid, it can be utilized for the real-time tracking of moving objects and people.
Ai-ichiro SASAKI
Kindai University
Ken FUKUSHIMA
the Kansai Transmission and Distribution, Inc.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Ai-ichiro SASAKI, Ken FUKUSHIMA, "Machine-Learning Approach for Solving Inverse Problems in Magnetic-Field-Based Positioning" in IEICE TRANSACTIONS on Fundamentals,
vol. E105-A, no. 6, pp. 994-1005, June 2022, doi: 10.1587/transfun.2021EAP1063.
Abstract: Magnetic fields are often utilized for position sensing of mobile devices. In typical sensing systems, multiple sensors are used to detect magnetic fields generated by target devices. To determine the positions of the devices, magnetic-field data detected by the sensors must be converted to device-position data. The data conversion is not trivial because it is a nonlinear inverse problem. In this study, we propose a machine-learning approach suitable for data conversion required in the magnetic-field-based position sensing of target devices. In our approach, two different sets of training data are used. One of the training datasets is composed of raw data of magnetic fields to be detected by sensors. The other set is composed of logarithmically represented data of the fields. We can obtain two different predictor functions by learning with these training datasets. Results show that the prediction accuracy of the target position improves when the two different predictor functions are used. Based on our simulation, the error of the target position estimated with the predictor functions is within 10cm in a 2m × 2m × 2m cubic space for 87% of all the cases of the target device states. The computational time required for predicting the positions of the target device is 4ms. As the prediction method is accurate and rapid, it can be utilized for the real-time tracking of moving objects and people.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2021EAP1063/_p
Copy
@ARTICLE{e105-a_6_994,
author={Ai-ichiro SASAKI, Ken FUKUSHIMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Machine-Learning Approach for Solving Inverse Problems in Magnetic-Field-Based Positioning},
year={2022},
volume={E105-A},
number={6},
pages={994-1005},
abstract={Magnetic fields are often utilized for position sensing of mobile devices. In typical sensing systems, multiple sensors are used to detect magnetic fields generated by target devices. To determine the positions of the devices, magnetic-field data detected by the sensors must be converted to device-position data. The data conversion is not trivial because it is a nonlinear inverse problem. In this study, we propose a machine-learning approach suitable for data conversion required in the magnetic-field-based position sensing of target devices. In our approach, two different sets of training data are used. One of the training datasets is composed of raw data of magnetic fields to be detected by sensors. The other set is composed of logarithmically represented data of the fields. We can obtain two different predictor functions by learning with these training datasets. Results show that the prediction accuracy of the target position improves when the two different predictor functions are used. Based on our simulation, the error of the target position estimated with the predictor functions is within 10cm in a 2m × 2m × 2m cubic space for 87% of all the cases of the target device states. The computational time required for predicting the positions of the target device is 4ms. As the prediction method is accurate and rapid, it can be utilized for the real-time tracking of moving objects and people.},
keywords={},
doi={10.1587/transfun.2021EAP1063},
ISSN={1745-1337},
month={June},}
Copy
TY - JOUR
TI - Machine-Learning Approach for Solving Inverse Problems in Magnetic-Field-Based Positioning
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 994
EP - 1005
AU - Ai-ichiro SASAKI
AU - Ken FUKUSHIMA
PY - 2022
DO - 10.1587/transfun.2021EAP1063
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E105-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2022
AB - Magnetic fields are often utilized for position sensing of mobile devices. In typical sensing systems, multiple sensors are used to detect magnetic fields generated by target devices. To determine the positions of the devices, magnetic-field data detected by the sensors must be converted to device-position data. The data conversion is not trivial because it is a nonlinear inverse problem. In this study, we propose a machine-learning approach suitable for data conversion required in the magnetic-field-based position sensing of target devices. In our approach, two different sets of training data are used. One of the training datasets is composed of raw data of magnetic fields to be detected by sensors. The other set is composed of logarithmically represented data of the fields. We can obtain two different predictor functions by learning with these training datasets. Results show that the prediction accuracy of the target position improves when the two different predictor functions are used. Based on our simulation, the error of the target position estimated with the predictor functions is within 10cm in a 2m × 2m × 2m cubic space for 87% of all the cases of the target device states. The computational time required for predicting the positions of the target device is 4ms. As the prediction method is accurate and rapid, it can be utilized for the real-time tracking of moving objects and people.
ER -