The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Kebangkitan sistem logistik generasi akan datang yang menampilkan kenderaan autonomi dan dron telah mendedahkan masalah teruk pemalsuan data lokasi sistem satelit navigasi Global (GNSS). Walaupun teknik anti-penipuan berasaskan isyarat telah dikaji, teknik ini mungkin mencabar untuk digunakan pada modul GNSS komersil semasa dalam banyak kes. Dalam kajian ini, kami meneroka menggunakan pelbagai peranti penderiaan dan teknik pembelajaran mesin seperti pengelas pokok keputusan dan rangkaian Memori jangka pendek (LSTM) panjang untuk mengesan pemalsuan data lokasi GNSS. Kami memperoleh data penderiaan daripada enam trajektori dan menjana data pemalsuan berdasarkan tingkah laku radio yang ditentukan Perisian (SDR) untuk penilaian. Kami mentakrifkan berbilang ciri menggunakan data GNSS, suar dan unit ukuran Inersia (IMU) dan membangunkan model untuk mengesan penipuan. Keputusan percubaan kami menunjukkan bahawa rangkaian LSTM menggunakan data lalu sepuluh urutan mempamerkan prestasi yang lebih tinggi, dengan ketepatan skor F1 melebihi 0.92 menggunakan ciri yang sesuai termasuk suar dan keupayaan generalisasi untuk data ujian yang tidak terlatih. Selain itu, keputusan kami mencadangkan bahawa jarak dari suar ialah metrik yang berharga untuk mengesan penipuan GNSS dan menunjukkan potensi untuk pemasangan suar di sepanjang lebuh raya dron masa hadapan.
Xin QI
Waseda University
Toshio SATO
Waseda University
Zheng WEN
Waseda University
Yutaka KATSUYAMA
Waseda University
Kazuhiko TAMESUE
Waseda University
Takuro SATO
Waseda University
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.
Salinan
Xin QI, Toshio SATO, Zheng WEN, Yutaka KATSUYAMA, Kazuhiko TAMESUE, Takuro SATO, "GNSS Spoofing Detection Using Multiple Sensing Devices and LSTM Networks" in IEICE TRANSACTIONS on Communications,
vol. E106-B, no. 12, pp. 1372-1379, December 2023, doi: 10.1587/transcom.2023CEP0008.
Abstract: The rise of next-generation logistics systems featuring autonomous vehicles and drones has brought to light the severe problem of Global navigation satellite system (GNSS) location data spoofing. While signal-based anti-spoofing techniques have been studied, they can be challenging to apply to current commercial GNSS modules in many cases. In this study, we explore using multiple sensing devices and machine learning techniques such as decision tree classifiers and Long short-term memory (LSTM) networks for detecting GNSS location data spoofing. We acquire sensing data from six trajectories and generate spoofing data based on the Software-defined radio (SDR) behavior for evaluation. We define multiple features using GNSS, beacons, and Inertial measurement unit (IMU) data and develop models to detect spoofing. Our experimental results indicate that LSTM networks using ten-sequential past data exhibit higher performance, with the accuracy F1 scores above 0.92 using appropriate features including beacons and generalization ability for untrained test data. Additionally, our results suggest that distance from beacons is a valuable metric for detecting GNSS spoofing and demonstrate the potential for beacon installation along future drone highways.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2023CEP0008/_p
Salinan
@ARTICLE{e106-b_12_1372,
author={Xin QI, Toshio SATO, Zheng WEN, Yutaka KATSUYAMA, Kazuhiko TAMESUE, Takuro SATO, },
journal={IEICE TRANSACTIONS on Communications},
title={GNSS Spoofing Detection Using Multiple Sensing Devices and LSTM Networks},
year={2023},
volume={E106-B},
number={12},
pages={1372-1379},
abstract={The rise of next-generation logistics systems featuring autonomous vehicles and drones has brought to light the severe problem of Global navigation satellite system (GNSS) location data spoofing. While signal-based anti-spoofing techniques have been studied, they can be challenging to apply to current commercial GNSS modules in many cases. In this study, we explore using multiple sensing devices and machine learning techniques such as decision tree classifiers and Long short-term memory (LSTM) networks for detecting GNSS location data spoofing. We acquire sensing data from six trajectories and generate spoofing data based on the Software-defined radio (SDR) behavior for evaluation. We define multiple features using GNSS, beacons, and Inertial measurement unit (IMU) data and develop models to detect spoofing. Our experimental results indicate that LSTM networks using ten-sequential past data exhibit higher performance, with the accuracy F1 scores above 0.92 using appropriate features including beacons and generalization ability for untrained test data. Additionally, our results suggest that distance from beacons is a valuable metric for detecting GNSS spoofing and demonstrate the potential for beacon installation along future drone highways.},
keywords={},
doi={10.1587/transcom.2023CEP0008},
ISSN={1745-1345},
month={December},}
Salinan
TY - JOUR
TI - GNSS Spoofing Detection Using Multiple Sensing Devices and LSTM Networks
T2 - IEICE TRANSACTIONS on Communications
SP - 1372
EP - 1379
AU - Xin QI
AU - Toshio SATO
AU - Zheng WEN
AU - Yutaka KATSUYAMA
AU - Kazuhiko TAMESUE
AU - Takuro SATO
PY - 2023
DO - 10.1587/transcom.2023CEP0008
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E106-B
IS - 12
JA - IEICE TRANSACTIONS on Communications
Y1 - December 2023
AB - The rise of next-generation logistics systems featuring autonomous vehicles and drones has brought to light the severe problem of Global navigation satellite system (GNSS) location data spoofing. While signal-based anti-spoofing techniques have been studied, they can be challenging to apply to current commercial GNSS modules in many cases. In this study, we explore using multiple sensing devices and machine learning techniques such as decision tree classifiers and Long short-term memory (LSTM) networks for detecting GNSS location data spoofing. We acquire sensing data from six trajectories and generate spoofing data based on the Software-defined radio (SDR) behavior for evaluation. We define multiple features using GNSS, beacons, and Inertial measurement unit (IMU) data and develop models to detect spoofing. Our experimental results indicate that LSTM networks using ten-sequential past data exhibit higher performance, with the accuracy F1 scores above 0.92 using appropriate features including beacons and generalization ability for untrained test data. Additionally, our results suggest that distance from beacons is a valuable metric for detecting GNSS spoofing and demonstrate the potential for beacon installation along future drone highways.
ER -