NLOS multipath detection by using machine learning in urban environments

Taro Suzuki, Yusuke Nakano, Yoshiharu Aman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In global navigation satellite system (GNSS) positioning, GNSS satellites are often obstructed by buildings, leading to reflected and diffracted signals, which are known as non-line-of-sight (NLOS) signals. These cause major positioning (also known as "NLOS multipath") errors in GNSS positioning. This paper proposes a novel NLOS multipath detection technique that uses a machine-learning technique to improve positioning accuracy in urban environments. The key idea behind this technique is to construct a classifier that discriminates NLOS multipath signals from the output of the multiple GNSS signal correlators of a software GNSS receiver. In the code-tracking process within GNSS receivers, the code correlation peak is determined and tracked using the outputs of the signal correlators. In the case of an NLOS signal, there are no direct signals; the first reflected signal has low power compared to the direct signal. Hence, the correlation function is expected to be more distorted in the case of NLOS signal correlation. We use this phenomenon to detect NLOS signals. For realizing machine learning, we extract the features of the NLOS signal from the shape of the NLOS correlation function, using an actual dataset, to construct an NLOS classifier. To evaluate the proposed technique, we conduct NLOS classification experiments using signal correlation data acquired at different locations in the Shinjuku area of Japan. We propose to construct an NLOS classifier based on a support vector machine. From the experiments, 87% of the LOS signals and 99% of the NLOS signals are correctly discriminated.

Original languageEnglish
Title of host publication30th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS 2017
PublisherInstitute of Navigation
Pages3958-3967
Number of pages10
Volume6
ISBN (Electronic)9781510853317
Publication statusPublished - 2017 Jan 1
Event30th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS 2017 - Portland, United States
Duration: 2017 Sep 252017 Sep 29

Other

Other30th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS 2017
CountryUnited States
CityPortland
Period17/9/2517/9/29

Fingerprint

Learning systems
Satellites
Navigation
Classifiers
Correlators
Signal systems
Support vector machines
Global positioning system
Experiments

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Suzuki, T., Nakano, Y., & Aman, Y. (2017). NLOS multipath detection by using machine learning in urban environments. In 30th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS 2017 (Vol. 6, pp. 3958-3967). Institute of Navigation.

NLOS multipath detection by using machine learning in urban environments. / Suzuki, Taro; Nakano, Yusuke; Aman, Yoshiharu.

30th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS 2017. Vol. 6 Institute of Navigation, 2017. p. 3958-3967.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Suzuki, T, Nakano, Y & Aman, Y 2017, NLOS multipath detection by using machine learning in urban environments. in 30th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS 2017. vol. 6, Institute of Navigation, pp. 3958-3967, 30th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS 2017, Portland, United States, 17/9/25.
Suzuki T, Nakano Y, Aman Y. NLOS multipath detection by using machine learning in urban environments. In 30th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS 2017. Vol. 6. Institute of Navigation. 2017. p. 3958-3967
Suzuki, Taro ; Nakano, Yusuke ; Aman, Yoshiharu. / NLOS multipath detection by using machine learning in urban environments. 30th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS 2017. Vol. 6 Institute of Navigation, 2017. pp. 3958-3967
@inproceedings{77e28168be9d4439b52b14f97d2412f4,
title = "NLOS multipath detection by using machine learning in urban environments",
abstract = "In global navigation satellite system (GNSS) positioning, GNSS satellites are often obstructed by buildings, leading to reflected and diffracted signals, which are known as non-line-of-sight (NLOS) signals. These cause major positioning (also known as {"}NLOS multipath{"}) errors in GNSS positioning. This paper proposes a novel NLOS multipath detection technique that uses a machine-learning technique to improve positioning accuracy in urban environments. The key idea behind this technique is to construct a classifier that discriminates NLOS multipath signals from the output of the multiple GNSS signal correlators of a software GNSS receiver. In the code-tracking process within GNSS receivers, the code correlation peak is determined and tracked using the outputs of the signal correlators. In the case of an NLOS signal, there are no direct signals; the first reflected signal has low power compared to the direct signal. Hence, the correlation function is expected to be more distorted in the case of NLOS signal correlation. We use this phenomenon to detect NLOS signals. For realizing machine learning, we extract the features of the NLOS signal from the shape of the NLOS correlation function, using an actual dataset, to construct an NLOS classifier. To evaluate the proposed technique, we conduct NLOS classification experiments using signal correlation data acquired at different locations in the Shinjuku area of Japan. We propose to construct an NLOS classifier based on a support vector machine. From the experiments, 87{\%} of the LOS signals and 99{\%} of the NLOS signals are correctly discriminated.",
author = "Taro Suzuki and Yusuke Nakano and Yoshiharu Aman",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "6",
pages = "3958--3967",
booktitle = "30th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS 2017",
publisher = "Institute of Navigation",

}

TY - GEN

T1 - NLOS multipath detection by using machine learning in urban environments

AU - Suzuki, Taro

AU - Nakano, Yusuke

AU - Aman, Yoshiharu

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In global navigation satellite system (GNSS) positioning, GNSS satellites are often obstructed by buildings, leading to reflected and diffracted signals, which are known as non-line-of-sight (NLOS) signals. These cause major positioning (also known as "NLOS multipath") errors in GNSS positioning. This paper proposes a novel NLOS multipath detection technique that uses a machine-learning technique to improve positioning accuracy in urban environments. The key idea behind this technique is to construct a classifier that discriminates NLOS multipath signals from the output of the multiple GNSS signal correlators of a software GNSS receiver. In the code-tracking process within GNSS receivers, the code correlation peak is determined and tracked using the outputs of the signal correlators. In the case of an NLOS signal, there are no direct signals; the first reflected signal has low power compared to the direct signal. Hence, the correlation function is expected to be more distorted in the case of NLOS signal correlation. We use this phenomenon to detect NLOS signals. For realizing machine learning, we extract the features of the NLOS signal from the shape of the NLOS correlation function, using an actual dataset, to construct an NLOS classifier. To evaluate the proposed technique, we conduct NLOS classification experiments using signal correlation data acquired at different locations in the Shinjuku area of Japan. We propose to construct an NLOS classifier based on a support vector machine. From the experiments, 87% of the LOS signals and 99% of the NLOS signals are correctly discriminated.

AB - In global navigation satellite system (GNSS) positioning, GNSS satellites are often obstructed by buildings, leading to reflected and diffracted signals, which are known as non-line-of-sight (NLOS) signals. These cause major positioning (also known as "NLOS multipath") errors in GNSS positioning. This paper proposes a novel NLOS multipath detection technique that uses a machine-learning technique to improve positioning accuracy in urban environments. The key idea behind this technique is to construct a classifier that discriminates NLOS multipath signals from the output of the multiple GNSS signal correlators of a software GNSS receiver. In the code-tracking process within GNSS receivers, the code correlation peak is determined and tracked using the outputs of the signal correlators. In the case of an NLOS signal, there are no direct signals; the first reflected signal has low power compared to the direct signal. Hence, the correlation function is expected to be more distorted in the case of NLOS signal correlation. We use this phenomenon to detect NLOS signals. For realizing machine learning, we extract the features of the NLOS signal from the shape of the NLOS correlation function, using an actual dataset, to construct an NLOS classifier. To evaluate the proposed technique, we conduct NLOS classification experiments using signal correlation data acquired at different locations in the Shinjuku area of Japan. We propose to construct an NLOS classifier based on a support vector machine. From the experiments, 87% of the LOS signals and 99% of the NLOS signals are correctly discriminated.

UR - http://www.scopus.com/inward/record.url?scp=85047967255&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047967255&partnerID=8YFLogxK

M3 - Conference contribution

VL - 6

SP - 3958

EP - 3967

BT - 30th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS 2017

PB - Institute of Navigation

ER -