A Robust GNSS LOS/Multipath Signal Classifier based on the Fusion of Information and Machine Learning for Intelligent Transportation Systems

Guermah, Bassma; Ghazi, Hassan El; Sadiki, Tayeb; Guermah, Hatim

doi:10.1109/itmc.2018.8691272

Cited by 31 publications

(20 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, various researches have been investigated to improve the performance of GNSS systems based on this tool for different problems as NLOS/multipath signal detection, detection of GNSS ionospheric, spoofing attacks and jammer classification. Most of the solutions for features extraction are based on one or even two of GNSS signal observations such as elevation angle [29], SNR (Signal to Noise Ratio) [30] or a combination of both [31], CN/0 (Carrier-to-Noise Ratio) [32], DOP (Dilution Of Precision) [33], as they can be considered as indicators of the performance of a measurement. Nevertheless, if the combination of these different features allows to provide reliable measurements and a prior knowledge of the current situation, the logic of combining more than three features becomes complex and difficult to apprehend.…”

Section: Inputs Identificationmentioning

confidence: 99%

Navigation Context Adaptive Fault Detection and Exclusion Strategy based On Deep Learning & Information Theory: Application to a GNSS/IMU Integration

Harbaoui¹,

Tmazirte²,

Makkawi³

et al. 2021

Proceedings of the 34th International Technical Meeting of the Satellite Division of the Institute of Navigation (ION GNSS+ 202

View full text Add to dashboard Cite

His research interests include multi-sensor fault tolerant fusion for localization and integrity assessment. Khoder Makkawi Lecturer at Polytech Lille and Researcher at CRIStAL laboratory. Received the Ph.D. degree in 2020, in collaboration between Lille University and Lebanese University. He is a member of the TOSyMA (Tolérance aux fautes des Systèmes Mobiles Autonomes) team of the CRIStAL laboratory UMR CNRS 9189.

show abstract

Section: Inputs Identificationmentioning

confidence: 99%

Navigation Context Adaptive Fault Detection and Exclusion Strategy based On Deep Learning & Information Theory: Application to a GNSS/IMU Integration

Harbaoui¹,

Tmazirte²,

Makkawi³

et al. 2021

Proceedings of the 34th International Technical Meeting of the Satellite Division of the Institute of Navigation (ION GNSS+ 202

View full text Add to dashboard Cite

show abstract

“…Various machine learning techniques have been used for classifying GNSS signal reception conditions, and their multipath detection performances were better than those of traditional methods [56]- [58]. The performance of a machine learning technique is greatly influenced by the features that are used, and the algorithms that are applied to it.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based GPS Multipath Detection Method Using Dual Antennas

Kim,

Byun,

Park

2022

Preprint

View full text Add to dashboard Cite

In urban areas, global navigation satellite system (GNSS) signals are often reflected or blocked by buildings, thus resulting in large positioning errors. In this study, we proposed a machine learning approach for global positioning system (GPS) multipath detection that uses dual antennas. A machine learning model that could classify GPS signal reception conditions was trained with several GPS measurements selected as suggested features. We applied five features for machine learning, including a feature obtained from the dual antennas, and evaluated the classification performance of the model, after applying four machine learning algorithms: gradient boosting decision tree (GBDT), random forest, decision tree, and K-nearest neighbor (KNN). It was found that a classification accuracy of 82%-96% was achieved when the test data set was collected at the same locations as those of the training data set. However, when the test data set was collected at locations different from those of the training data, a classification accuracy of 44%-77% was obtained.

show abstract

“…The rules extracted from the corresponding input and output variables are applied to newly collected GNSS data to predict the signal reception classifications. The position is then calculated by excluding the predicted NLOS/multipath signals (Yozevitch et al 2016;Guermah et al 2018;Quan et al 2018;Sun et al 2019Sun et al , 2020. The positioning accuracy achievable through this approach is constrained, however, since the classification accuracy is affected by errors introduced from the offline labeling process needed for the machine learning algorithms (e.g., a 3D city model or camera-assisted labeling).…”

Section: Introductionmentioning

confidence: 99%

Pseudorange error prediction for adaptive tightly coupled GNSS/IMU navigation in urban areas

et al. 2021

View full text Add to dashboard Cite

The integration of global navigation satellite systems (GNSS) and inertial measurement unit (IMU) with the Kalman filter is widely used to enhance the availability of positioning in urban areas for many intelligent transport system (ITS) applications. In the traditional Kalman filter, the GNSS measurement noise is fixed based on factors determined a priori, instead of reflecting the impact of the surrounding environment on the received GNSS signal. This has the effect of degrading position accuracy and the a posteriori quality indicators. To address this issue, we propose a new measurement noise covariance update scheme, with the adaptive indicator generated from pseudorange error prediction results, for a tightly coupled GNSS/ IMU navigation system in urban areas. Specifically, the pseudorange errors are predicted by means of an ensemble bagged regression tree model accounting for signal strength, satellite elevation angle and coordinate information. The urban experimental results show that the proposed algorithm provides a 3D accuracy of 9.21 m, with an improvement of 55% and 15%, respectively, over the traditional fixed covariance extended Kalman filter (EKF)-based fusion and EKF-based fusion with pseudorange error correction.

show abstract

A Robust GNSS LOS/Multipath Signal Classifier based on the Fusion of Information and Machine Learning for Intelligent Transportation Systems

Cited by 31 publications

References 11 publications

Navigation Context Adaptive Fault Detection and Exclusion Strategy based On Deep Learning & Information Theory: Application to a GNSS/IMU Integration

Navigation Context Adaptive Fault Detection and Exclusion Strategy based On Deep Learning & Information Theory: Application to a GNSS/IMU Integration

Machine Learning-Based GPS Multipath Detection Method Using Dual Antennas

Pseudorange error prediction for adaptive tightly coupled GNSS/IMU navigation in urban areas

Contact Info

Product

Resources

About