Xiang Cui
Xiang Cui has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Ruimin Jin
China Research Institute of Radiowave Propagation, Qingdao 266107, China
4 shared publications - Weimin Zhen
China Research Institute of Radiowave Propagation, Qingdao 266107, China
4 shared publications - Guangwang Ji
China Research Institute of Radiowave Propagation, Qingdao 266107, China
3 shared publications - Huiyun Yang
China Research Institute of Radiowave Propagation, Qingdao 266107, China
3 shared publications - Longjiang Chen
China Research Institute of Radiowave Propagation, Qingdao 266107, China
3 shared publications - Mingyue Gu
China Research Institute of Radiowave Propagation, Qingdao 266107, China
3 shared publications
Latest Publications
- Open Access
- 8 September 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (18) , 3074
Machine-Learning-Based GNSS Signal Anomaly Classification Using COSMIC-2 POD Data
Ionospheric scintillation and radio frequency interference (RFI) affect Global Navigation Satellite System (GNSS) signals, making their distinction important for ionospheric monitoring and interference detection. This study identifies GNSS signal anomalies associated with scintillation and RFI using COSMIC-2 1 Hz precise orbit determination (POD) observations. Using 60 s per-satellite windows, dual-frequency time-series inputs and 16-dimensional statistical features were extracted, and weak labels for Normal, Scintillation, and RFI were generated from the amplitude scintillation index S4 and the RFI index. An InceptionTimeLite-FiLM-DeepSets joint multi-satellite model, where FiLM denotes feature-wise linear modulation, was trained and tested on 2024 data and directly applied to the full-year 2025 dataset. On the 2024 test set, recall for Normal, Scintillation, and RFI was 98.9%, 76.1%, and 58.5%, respectively, with a Macro-F1 of 0.8227 and a Matthews correlation coefficient of 0.7120. Predicted Scintillation occurrence rates were higher at low magnetic latitudes and during the postsunset premidnight period, whereas predicted RFI occurrence rates were concentrated over North Africa, the Middle East, South Asia, and Southeast Asia. These results show that, within the weak-label framework, COSMIC-2 1 Hz POD observations can support GNSS signal anomaly classification and spatiotemporal distribution analysis, providing a complementary approach for long-term anomaly analysis.
- 8 September 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (18) , 3074
Open AccessMachine-Learning-Based GNSS Signal Anomaly Classification Using COSMIC-2 POD Data
Ionospheric scintillation and radio frequency interference (RFI) affect Global Navigation Satellite System (GNSS) signals, making their distinction important for ionospheric monitoring and interference detection. This study identifies GNSS signal anomalies associated with scintillation and RFI using COSMIC-2 1 Hz precise orbit determination (POD) observations. Using 60 s per-satellite windows, dual-frequency time-series inputs and 16-dimensional statistical features were extracted, and weak labels for Normal, Scintillation, and RFI were generated from the amplitude scintillation index S4 and the RFI index. An InceptionTimeLite-FiLM-DeepSets joint multi-satellite model, where FiLM denotes feature-wise linear modulation, was trained and tested on 2024 data and directly applied to the full-year 2025 dataset. On the 2024 test set, recall for Normal, Scintillation, and RFI was 98.9%, 76.1%, and 58.5%, respectively, with a Macro-F1 of 0.8227 and a Matthews correlation coefficient of 0.7120. Predicted Scintillation occurrence rates were higher at low magnetic latitudes and during the postsunset premidnight period, whereas predicted RFI occurrence rates were concentrated over North Africa, the Middle East, South Asia, and Southeast Asia. These results show that, within the weak-label framework, COSMIC-2 1 Hz POD observations can support GNSS signal anomaly classification and spatiotemporal distribution analysis, providing a complementary approach for long-term anomaly analysis.
- Open Access
- 3 September 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (17) , 3073
Estimating Ionospheric Phase Scintillation Indices in the Polar Region from 1 Hz GNSS Observations Using Machine Learning
Ionospheric scintillation represents a disturbance phenomenon induced by irregular electron density variations, predominantly occurring in equatorial, auroral, and polar regions, thereby posing significant threats to Global Navigation Satellite Systems (GNSS) performance. Polar regions in particular confront distinctive challenges, including the sparse deployment of dedicated ionospheric scintillation monitoring receiver (ISMR) equipment, the limited availability of strong scintillation samples, severely imbalanced training datasets, and the insufficient sensitivity of conventional Deep Neural Networks (DNNs) to intense scintillation events. To address these challenges, this study proposes a modeling framework that integrates residual neural networks (ResNet) with the Synthetic Minority Over-sampling Technique for Regression with Gaussian Noise (SMOGN). The proposed model incorporates multi-source disturbance features to accurately estimate phase scintillation indices () in polar regions. The methodology was implemented and validated across multiple polar observation stations in Canada. Shapley Additive Explanations (SHAP) interpretability analysis reveals that the rate of total electron content index (ROTI) features contribute up to 64.09% of the predictive weight. The experimental results demonstrate a substantial performance enhancement compared with conventional DNN models, with root mean square error (RMSE) values ranging from 0.0078 to 0.038 for daytime samples in 2024, and an average coefficient of determination (R2) consistently exceeding 0.89. The coefficient of determination for the Pseudo-Random Noise (PRN) path estimation results can reach 0.91. The model has good estimation results at different latitudes and is able to accurately capture the distribution characteristics of the local strong scintillation structures and their evolution patterns.- 3 September 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (17) , 3073
Open AccessEstimating Ionospheric Phase Scintillation Indices in the Polar Region from 1 Hz GNSS Observations Using Machine Learning
Ionospheric scintillation represents a disturbance phenomenon induced by irregular electron density variations, predominantly occurring in equatorial, auroral, and polar regions, thereby posing significant threats to Global Navigation Satellite Systems (GNSS) performance. Polar regions in particular confront distinctive challenges, including the sparse deployment of dedicated ionospheric scintillation monitoring receiver (ISMR) equipment, the limited availability of strong scintillation samples, severely imbalanced training datasets, and the insufficient sensitivity of conventional Deep Neural Networks (DNNs) to intense scintillation events. To address these challenges, this study proposes a modeling framework that integrates residual neural networks (ResNet) with the Synthetic Minority Over-sampling Technique for Regression with Gaussian Noise (SMOGN). The proposed model incorporates multi-source disturbance features to accurately estimate phase scintillation indices () in polar regions. The methodology was implemented and validated across multiple polar observation stations in Canada. Shapley Additive Explanations (SHAP) interpretability analysis reveals that the rate of total electron content index (ROTI) features contribute up to 64.09% of the predictive weight. The experimental results demonstrate a substantial performance enhancement compared with conventional DNN models, with root mean square error (RMSE) values ranging from 0.0078 to 0.038 for daytime samples in 2024, and an average coefficient of determination (R2) consistently exceeding 0.89. The coefficient of determination for the Pseudo-Random Noise (PRN) path estimation results can reach 0.91. The model has good estimation results at different latitudes and is able to accurately capture the distribution characteristics of the local strong scintillation structures and their evolution patterns. - Open Access
- 28 February 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (5) , 864
A Spoofing Detection and Direction-Finding Approach for Global Navigation Satellite System Signals Using Off-the-Shelf Anti-Jamming Antennas
Global Navigation Satellite System (GNSS) spoofing induces the target receiver to obtain the wrong positioning and timing results, which is very harmful. It is necessary to develop high-precision GNSS spoofing detection and associated direction-finding methods. In order to achieve sensitive and high-precision direction-finding for GNSS spoofing, it is necessary to realize the spoofing signal detection in the capture phase. This paper first proposes a method of GNSS spoofing detection, based on machine learning, that extracts features in the capture phase, which realizes various types of spoofing detection such as matching power, carrier phase alignment, and frequency locking. Notably, existing spoofing-direction-finding methods are mainly based on dedicated antenna arrays, which incur high costs and are not conducive to large-scale deployments. The basis of the spoofing detection proposed by this paper consists of a differential phase-center correction method, which is proposed in the context of an off-the-shelf anti-jamming array antenna, which effectively reduces the impact of the phase-center jitter introduced by the mutual coupling between antenna arrays on the direction-finding. The publicly accessible Texas Spoofing Test Battery (TEXBAT) dataset and actual measured data are both used for test verification. The results demonstrate that the proposed spoofing detection method can achieve success rates of over 97% on the TEXBAT dataset and more than 96% on the measured dataset, and the accuracy of the proposed direction-finding method can reach 1°, which can realize the effective detection and direction-finding of GNSS spoofing.
- 28 February 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (5) , 864
Open AccessA Spoofing Detection and Direction-Finding Approach for Global Navigation Satellite System Signals Using Off-the-Shelf Anti-Jamming Antennas
Global Navigation Satellite System (GNSS) spoofing induces the target receiver to obtain the wrong positioning and timing results, which is very harmful. It is necessary to develop high-precision GNSS spoofing detection and associated direction-finding methods. In order to achieve sensitive and high-precision direction-finding for GNSS spoofing, it is necessary to realize the spoofing signal detection in the capture phase. This paper first proposes a method of GNSS spoofing detection, based on machine learning, that extracts features in the capture phase, which realizes various types of spoofing detection such as matching power, carrier phase alignment, and frequency locking. Notably, existing spoofing-direction-finding methods are mainly based on dedicated antenna arrays, which incur high costs and are not conducive to large-scale deployments. The basis of the spoofing detection proposed by this paper consists of a differential phase-center correction method, which is proposed in the context of an off-the-shelf anti-jamming array antenna, which effectively reduces the impact of the phase-center jitter introduced by the mutual coupling between antenna arrays on the direction-finding. The publicly accessible Texas Spoofing Test Battery (TEXBAT) dataset and actual measured data are both used for test verification. The results demonstrate that the proposed spoofing detection method can achieve success rates of over 97% on the TEXBAT dataset and more than 96% on the measured dataset, and the accuracy of the proposed direction-finding method can reach 1°, which can realize the effective detection and direction-finding of GNSS spoofing.
- Open Access
COSMIC-2 RFI Prediction Model Based on CNN-BiLSTM-Attention for Interference Detection and Location
As the application of the Global Navigation Satellite System (GNSS) continues to expand, its stability and safety issues are receiving more and more attention, especially the interference problem. Interference reduces the signal reception quality of ground terminals and may even lead to the paralysis of GNSS function in severe cases. In recent years, Low Earth Orbit (LEO) satellites have been highly emphasized for their unique advantages in GNSS interference detection, and related commercial and academic activities have increased rapidly. In this context, based on the signal-to-noise ratio (SNR) and radio-frequency interference (RFI) measurements data from COSMIC-2 satellites, this paper explores a method of predicting RFI measurements using SNR correlation variations in different GNSS signal channels for application to the detection and localization of civil terrestrial GNSS interference signals. Research shows that the SNR in different GNSS signal channels shows a correlated change under the influence of RFI. To this end, a CNN-BiLSTM-Attention model combining a convolutional neural network (CNN), bi-directional long and short-term memory network (BiLSTM), and attention mechanism is proposed in this paper, and the model takes the multi-channel SNR time series of the GNSS as the input and outputs the maximum measured value of RFI in the multi-channels. The experimental results show that compared with the traditional band-pass filtering inter-correlation method and other deep learning models, the model in this paper has a root mean square error (RMSE), mean absolute error (MAE), and correlation coefficient (R2) of 1.0185, 1.8567, and 0.9693, respectively, in RFI prediction, which demonstrates a higher RFI detection accuracy and a wide range of rough localization capabilities, showing significant competitiveness. Since the correlation changes in the SNR can be processed to decouple the signal strength, this model is also suitable for future GNSS-RO missions (such as COSMIC-1, CHAMP, GRACE, and Spire) for which no RFI measurements have yet been made.
Open AccessCOSMIC-2 RFI Prediction Model Based on CNN-BiLSTM-Attention for Interference Detection and Location
As the application of the Global Navigation Satellite System (GNSS) continues to expand, its stability and safety issues are receiving more and more attention, especially the interference problem. Interference reduces the signal reception quality of ground terminals and may even lead to the paralysis of GNSS function in severe cases. In recent years, Low Earth Orbit (LEO) satellites have been highly emphasized for their unique advantages in GNSS interference detection, and related commercial and academic activities have increased rapidly. In this context, based on the signal-to-noise ratio (SNR) and radio-frequency interference (RFI) measurements data from COSMIC-2 satellites, this paper explores a method of predicting RFI measurements using SNR correlation variations in different GNSS signal channels for application to the detection and localization of civil terrestrial GNSS interference signals. Research shows that the SNR in different GNSS signal channels shows a correlated change under the influence of RFI. To this end, a CNN-BiLSTM-Attention model combining a convolutional neural network (CNN), bi-directional long and short-term memory network (BiLSTM), and attention mechanism is proposed in this paper, and the model takes the multi-channel SNR time series of the GNSS as the input and outputs the maximum measured value of RFI in the multi-channels. The experimental results show that compared with the traditional band-pass filtering inter-correlation method and other deep learning models, the model in this paper has a root mean square error (RMSE), mean absolute error (MAE), and correlation coefficient (R2) of 1.0185, 1.8567, and 0.9693, respectively, in RFI prediction, which demonstrates a higher RFI detection accuracy and a wide range of rough localization capabilities, showing significant competitiveness. Since the correlation changes in the SNR can be processed to decouple the signal strength, this model is also suitable for future GNSS-RO missions (such as COSMIC-1, CHAMP, GRACE, and Spire) for which no RFI measurements have yet been made.
- 6 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (15) , 24070-24085
Small Delay GNSS Forwarding Spoofing Detection in a Multipath Environment Based on Convolutional Neural Network
Global navigation satellite systems (GNSS) are popular for navigation and timing applications due to their high accuracy, low cost and global availability. However, the open signal structure and extremely low signal power make them susceptible to various intentional and unintentional interferences. Spoofing can manipulate the navigation information of the victims, which is stealthier and more harmful. In practical environments, the received signals often contain multipath signals in addition to the direct path, which are caused by reflection or scattering from obstacles. Among them, both small delay multipath signals and small delay forwarding spoofing signals can distort the capture correlation peaks, leading to a high detection false alarm rate of existing spoofing detection methods based on the shape of correlation peaks. In this paper, we address this problem by analyzing the positional differences of the correlation peaks of different signals in the capture stage relative to the capture center based on the time delay and power characteristics. Subsequently, using a convolutional neural network (CNN) effectively detects small delay spoofing signals in the multipath environment. When the superimposed power of the multipath signals in the receiving environment is less than that of the genuine signal, the proposed method can effectively distinguish the multipath signal from the spoofing signal. Additionally, the spoofing detection accuracy of the CNN on the simulation dataset reaches 98.83%. Finally, the effectiveness of the proposed method is verified by building field experimental scenarios.
- 6 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (15) , 24070-24085
Small Delay GNSS Forwarding Spoofing Detection in a Multipath Environment Based on Convolutional Neural Network
Global navigation satellite systems (GNSS) are popular for navigation and timing applications due to their high accuracy, low cost and global availability. However, the open signal structure and extremely low signal power make them susceptible to various intentional and unintentional interferences. Spoofing can manipulate the navigation information of the victims, which is stealthier and more harmful. In practical environments, the received signals often contain multipath signals in addition to the direct path, which are caused by reflection or scattering from obstacles. Among them, both small delay multipath signals and small delay forwarding spoofing signals can distort the capture correlation peaks, leading to a high detection false alarm rate of existing spoofing detection methods based on the shape of correlation peaks. In this paper, we address this problem by analyzing the positional differences of the correlation peaks of different signals in the capture stage relative to the capture center based on the time delay and power characteristics. Subsequently, using a convolutional neural network (CNN) effectively detects small delay spoofing signals in the multipath environment. When the superimposed power of the multipath signals in the receiving environment is less than that of the genuine signal, the proposed method can effectively distinguish the multipath signal from the spoofing signal. Additionally, the spoofing detection accuracy of the CNN on the simulation dataset reaches 98.83%. Finally, the effectiveness of the proposed method is verified by building field experimental scenarios.
- Open Access
- 5 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 267-278
Make Data Reliable: An Explanation-powered Cleaning on Malware Dataset Against Backdoor Poisoning Attacks
Machine learning (ML) based Malware classification provides excellent performance and has been deployed in various real-world applications. Training for malware classification often relies on crowdsourced threat feeds, which exposes a natural attack injection point. Considering a real-world threat model for backdoor poisoning attacks on a malware dataset, because attackers are generally considered to have no control over the sample-labeling process, they conduct a clean-label attack, a more realistic scenario, by generating backdoored benign binaries that will be disseminated through threat intelligence platforms and poison the datasets for downstream malware classifiers. To avoid the threat of backdoor poisoned datasets, we propose an explanation-powered defense methodology called make data reliable (MDR), which is a general and effective mitigation to ensure the reliability of datasets by removing backdoored samples. We use a surrogate model and explanation tool Shapley Additive exPlanations (SHAP) to filter suspicious samples, then perform watermark identification based on the filtered suspicious samples, and finally remove samples with the identified watermark to construct a reliable dataset. We conduct extensive experiments on two typical datasets that were manually poisoned using different attack strategies. Experimental results show that the MDR achieves backdoored samples removal rate greater than 99.0% for different datasets and attack conditions, while maintaining an extremely low false positive rate of less than 0.1%. Furthermore, to confirm the generality of MDR, we use different models to perform a model-agnostic evaluation. The results show that, MDR is a general methodology that does not rely on any specific model.
- 5 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 267-278
Open AccessMake Data Reliable: An Explanation-powered Cleaning on Malware Dataset Against Backdoor Poisoning Attacks
Machine learning (ML) based Malware classification provides excellent performance and has been deployed in various real-world applications. Training for malware classification often relies on crowdsourced threat feeds, which exposes a natural attack injection point. Considering a real-world threat model for backdoor poisoning attacks on a malware dataset, because attackers are generally considered to have no control over the sample-labeling process, they conduct a clean-label attack, a more realistic scenario, by generating backdoored benign binaries that will be disseminated through threat intelligence platforms and poison the datasets for downstream malware classifiers. To avoid the threat of backdoor poisoned datasets, we propose an explanation-powered defense methodology called make data reliable (MDR), which is a general and effective mitigation to ensure the reliability of datasets by removing backdoored samples. We use a surrogate model and explanation tool Shapley Additive exPlanations (SHAP) to filter suspicious samples, then perform watermark identification based on the filtered suspicious samples, and finally remove samples with the identified watermark to construct a reliable dataset. We conduct extensive experiments on two typical datasets that were manually poisoned using different attack strategies. Experimental results show that the MDR achieves backdoored samples removal rate greater than 99.0% for different datasets and attack conditions, while maintaining an extremely low false positive rate of less than 0.1%. Furthermore, to confirm the generality of MDR, we use different models to perform a model-agnostic evaluation. The results show that, MDR is a general methodology that does not rely on any specific model.