Jianguo Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jianguo Liu has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Junwei Wang
College of Artificial Intelligence and Automation, Hohai University, Changzhou, China
6 shared publications - Xiyuan Chen
Southeast University
6 shared publications - Teng Li
School of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan 430048, China
3 shared publications - Yi Mou
School of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan 430048, China
3 shared publications - Xuefen Zhu
School of Instrument Science and Engineering, Southeast University, Nanjing, China
2 shared publications - Ang Li
Key Laboratory of Micro-Inertial Instrument and Advanced Navigation Technology, School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China
1 shared publication
Latest Publications
- Open Access
A Dual-Domain Wavelet-Based Spatiotemporal Attention Network for 24-h Global Ionospheric TEC Prediction
To address the challenges associated with the complex spatiotemporal variations of global ionospheric total electron content (TEC), this study proposes a Dual-domain Filtered-label Wavelet-based Spatiotemporal Attention Network (DFL-WT-STANet) for global TEC forecasting. The proposed framework integrates wavelet-based multi-scale feature extraction, ConvLSTM-based spatiotemporal modeling, and decoupled temporal and spatial Transformer branches to capture local and global dependencies in TEC variations. A dual-domain optimization strategy is further introduced to jointly constrain prediction errors in the time and frequency domains, enhancing the representation of temporal variations and disturbance-related characteristics. Kp, Dst, F10.7, and SSN are incorporated as auxiliary solar and geomagnetic activity features. The global TEC data from 2003 to 2024 were used for experimental evaluation, with 2015, 2019, and 2024 selected as representative test years under different solar activity conditions. DFL-WT-STANet achieves RMSE values of 2.96 and 4.81 TECU in the high-solar-activity years of 2015 and 2024, respectively, while the RMSE decreases to 1.15 TECU in the low-solar-activity year of 2019. Compared with the CODE 1-day-ahead prediction product (C1PG), DFL-WT-STANet reduces the RMSE by 26.75%, 22.06%, and 25.29% in 2015, 2019, and 2024, respectively. During a severe geomagnetic storm with a minimum Dst of nT, the proposed model further reduces the storm-day RMSE and MAE by 8.93% and 11.32%, respectively, compared with WT-STANet. Monthly and latitude-dependent evaluations further show that the forecasting advantage is consistently maintained across different months and a broad range of latitude regions. These results demonstrate that DFL-WT-STANet provides accurate and robust global TEC forecasting under different solar and geomagnetic activity conditions, with particular advantages during pronounced ionospheric disturbances.Open AccessA Dual-Domain Wavelet-Based Spatiotemporal Attention Network for 24-h Global Ionospheric TEC Prediction
To address the challenges associated with the complex spatiotemporal variations of global ionospheric total electron content (TEC), this study proposes a Dual-domain Filtered-label Wavelet-based Spatiotemporal Attention Network (DFL-WT-STANet) for global TEC forecasting. The proposed framework integrates wavelet-based multi-scale feature extraction, ConvLSTM-based spatiotemporal modeling, and decoupled temporal and spatial Transformer branches to capture local and global dependencies in TEC variations. A dual-domain optimization strategy is further introduced to jointly constrain prediction errors in the time and frequency domains, enhancing the representation of temporal variations and disturbance-related characteristics. Kp, Dst, F10.7, and SSN are incorporated as auxiliary solar and geomagnetic activity features. The global TEC data from 2003 to 2024 were used for experimental evaluation, with 2015, 2019, and 2024 selected as representative test years under different solar activity conditions. DFL-WT-STANet achieves RMSE values of 2.96 and 4.81 TECU in the high-solar-activity years of 2015 and 2024, respectively, while the RMSE decreases to 1.15 TECU in the low-solar-activity year of 2019. Compared with the CODE 1-day-ahead prediction product (C1PG), DFL-WT-STANet reduces the RMSE by 26.75%, 22.06%, and 25.29% in 2015, 2019, and 2024, respectively. During a severe geomagnetic storm with a minimum Dst of nT, the proposed model further reduces the storm-day RMSE and MAE by 8.93% and 11.32%, respectively, compared with WT-STANet. Monthly and latitude-dependent evaluations further show that the forecasting advantage is consistently maintained across different months and a broad range of latitude regions. These results demonstrate that DFL-WT-STANet provides accurate and robust global TEC forecasting under different solar and geomagnetic activity conditions, with particular advantages during pronounced ionospheric disturbances. - 12 October 2026
- Published by Elsevier in Ocean Engineering
- Vol. 369
Adaptive robust UKF based on IMM for single-axis rotation-INS/GNSS integration system
- 12 October 2026
- Published by Elsevier in Ocean Engineering
- Vol. 369
Adaptive robust UKF based on IMM for single-axis rotation-INS/GNSS integration system
- 27 June 2026
- Published by Elsevier in Engineering Structures
- Vol. 365
A spring-suspended sectional model system with actively tunable damping: Concept, design, and performance validation
- 27 June 2026
- Published by Elsevier in Engineering Structures
- Vol. 365
A spring-suspended sectional model system with actively tunable damping: Concept, design, and performance validation
- Open Access
- 30 April 2026
- Published by MDPI AG in Micromachines
- Vol. 17 (5) , 557
Single-Axis Rotational Inertial Navigation Systems for USVs: A Review of Key Technologies
In complex marine environments, achieving low-cost, highly reliable, and continuous navigation is crucial for the intelligent and autonomous operation of unmanned surface vehicles (USVs). Currently, the integrated Global Navigation Satellite System and Strapdown Inertial Navigation System (GNSS/SINS) serves as the primary navigation architecture for USVs. While the cost of high-performance GNSS receivers has steadily decreased, high-precision SINS remains prohibitively expensive. Consequently, micro-electromechanical system (MEMS)-based SINS has emerged as a preferred alternative due to its favorable balance of cost, power consumption, and size. However, significant inertial sensor errors make it difficult to maintain high-precision positioning during GNSS outages. To address this limitation, the single-axis rotational inertial navigation system (SRINS) has been introduced. Nevertheless, constrained by the single-axis mechanical structure and complex sea state disturbances, the system still struggles to effectively modulate random errors and azimuth gyroscope drift, rendering it insufficient for highly demanding navigation tasks. To overcome these bottlenecks, this article systematically reviews four core technologies: (1) Comprehensive denoising and temperature drift compensation techniques for MEMS gyroscopes; (2) rapid moving-base initial alignment models under high sea state disturbances; (3) fast online calibration methods for azimuth gyroscope drift; and (4) adaptive and robust GNSS/SINS integration architectures capable of accommodating high-dynamic conditions and non-Gaussian interference. Finally, this article discusses the engineering conflict between deploying high-precision algorithms and the limited onboard computational capacity of USVs. It concludes by highlighting a highly promising navigation paradigm for future research: the integration of factor graph optimization with physics-informed deep learning.
- 30 April 2026
- Published by MDPI AG in Micromachines
- Vol. 17 (5) , 557
Open AccessSingle-Axis Rotational Inertial Navigation Systems for USVs: A Review of Key Technologies
In complex marine environments, achieving low-cost, highly reliable, and continuous navigation is crucial for the intelligent and autonomous operation of unmanned surface vehicles (USVs). Currently, the integrated Global Navigation Satellite System and Strapdown Inertial Navigation System (GNSS/SINS) serves as the primary navigation architecture for USVs. While the cost of high-performance GNSS receivers has steadily decreased, high-precision SINS remains prohibitively expensive. Consequently, micro-electromechanical system (MEMS)-based SINS has emerged as a preferred alternative due to its favorable balance of cost, power consumption, and size. However, significant inertial sensor errors make it difficult to maintain high-precision positioning during GNSS outages. To address this limitation, the single-axis rotational inertial navigation system (SRINS) has been introduced. Nevertheless, constrained by the single-axis mechanical structure and complex sea state disturbances, the system still struggles to effectively modulate random errors and azimuth gyroscope drift, rendering it insufficient for highly demanding navigation tasks. To overcome these bottlenecks, this article systematically reviews four core technologies: (1) Comprehensive denoising and temperature drift compensation techniques for MEMS gyroscopes; (2) rapid moving-base initial alignment models under high sea state disturbances; (3) fast online calibration methods for azimuth gyroscope drift; and (4) adaptive and robust GNSS/SINS integration architectures capable of accommodating high-dynamic conditions and non-Gaussian interference. Finally, this article discusses the engineering conflict between deploying high-precision algorithms and the limited onboard computational capacity of USVs. It concludes by highlighting a highly promising navigation paradigm for future research: the integration of factor graph optimization with physics-informed deep learning.
- 21 August 2025
- Published by Elsevier in Measurement
- Vol. 257
An adaptive robust method for azimuth gyro drift calibration in single-axis rotation MEMS-SINS
- 21 August 2025
- Published by Elsevier in Measurement
- Vol. 257
An adaptive robust method for azimuth gyro drift calibration in single-axis rotation MEMS-SINS
- Open Access
- 9 July 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (7) , 424
Filter Learning-Based Partial Least Squares Regression and Its Application in Infrared Spectral Analysis
Partial Least Squares (PLS) regression has been widely used to model the relationship between predictors and responses. However, PLS may be limited in its capacity to handle complex spectral data contaminated with significant noise and interferences. In this paper, we propose a novel filter learning-based PLS (FPLS) model that integrates an adaptive filter into the PLS framework. The FPLS model is designed to maximize the covariance between the filtered spectral data and the response. This modification enables FPLS to dynamically adapt to the characteristics of the data, thereby enhancing its feature extraction and noise suppression capabilities. We have developed an efficient algorithm to solve the FPLS optimization problem and provided theoretical analyses regarding the convergence of the model, the prediction variance, and the relationships among the objective functions of FPLS, PLS, and the filter length. Furthermore, we have derived bounds for the Root Mean Squared Error of Prediction (RMSEP) and the Cosine Similarity (CS) to evaluate model performance. Experimental results using spectral datasets from Corn, Octane, Mango, and Soil Nitrogen show that the FPLS model outperforms PLS, OSCPLS, VCPLS, PoPLS, LoPLS, DOSC, OPLS, MSC, SNV, SGFilter, and Lasso in terms of prediction accuracy. The theoretical analyses align with the experimental results, emphasizing the effectiveness and robustness of the FPLS model in managing complex spectral data.
- 9 July 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (7) , 424
Open AccessFilter Learning-Based Partial Least Squares Regression and Its Application in Infrared Spectral Analysis
Partial Least Squares (PLS) regression has been widely used to model the relationship between predictors and responses. However, PLS may be limited in its capacity to handle complex spectral data contaminated with significant noise and interferences. In this paper, we propose a novel filter learning-based PLS (FPLS) model that integrates an adaptive filter into the PLS framework. The FPLS model is designed to maximize the covariance between the filtered spectral data and the response. This modification enables FPLS to dynamically adapt to the characteristics of the data, thereby enhancing its feature extraction and noise suppression capabilities. We have developed an efficient algorithm to solve the FPLS optimization problem and provided theoretical analyses regarding the convergence of the model, the prediction variance, and the relationships among the objective functions of FPLS, PLS, and the filter length. Furthermore, we have derived bounds for the Root Mean Squared Error of Prediction (RMSEP) and the Cosine Similarity (CS) to evaluate model performance. Experimental results using spectral datasets from Corn, Octane, Mango, and Soil Nitrogen show that the FPLS model outperforms PLS, OSCPLS, VCPLS, PoPLS, LoPLS, DOSC, OPLS, MSC, SNV, SGFilter, and Lasso in terms of prediction accuracy. The theoretical analyses align with the experimental results, emphasizing the effectiveness and robustness of the FPLS model in managing complex spectral data.
- 18 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-17
Robust M-Estimation-Based ICKF for GNSS Outlier Mitigation in GNSS/SINS Navigation Applications
The accuracy and robustness of tightly coupled GNSS/SINS integrated navigation parameter estimation are hindered by outliers caused by GNSS measurements under multipath interference and non-line-of-sight (NLOS) conditions. To address the limitations of robust estimation and the mismatch of state posterior PDF approximation, a novel M-estimation-based robust iterated cubature kalman filter (ICKF) is developed to minimize the impact of GNSS outliers while improving the correction effect of high-quality LOS GNSS measurement in this paper. The nonlinear weighted least squares regression model and objective function are established for outlier mitigation, including a sigma-point iterative filtering framework and an M-estimation method of down-weighting GNSS measurements. Specifically, the maximum a posteriori (MAP) estimation idea is used to design the sigma-point iterated filtering framework, which makes the posteriori probability density function (PDF) constantly close to the high likelihood confidence interval to obtain excellent nonlinear approximation effects. Furthermore, to avoid the inherent non-convexity of the traditional M-estimation method, the relaxation compensation scheme based on the adaptive control factor is introduced into the robust loss function to accelerate the convergence of the penalty weight of GNSS outliers. The availability of the proposed method for GNSS outlier mitigation is proved by vehicle field tests under multipath interference and NLOS conditions.
- 18 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-17
Robust M-Estimation-Based ICKF for GNSS Outlier Mitigation in GNSS/SINS Navigation Applications
The accuracy and robustness of tightly coupled GNSS/SINS integrated navigation parameter estimation are hindered by outliers caused by GNSS measurements under multipath interference and non-line-of-sight (NLOS) conditions. To address the limitations of robust estimation and the mismatch of state posterior PDF approximation, a novel M-estimation-based robust iterated cubature kalman filter (ICKF) is developed to minimize the impact of GNSS outliers while improving the correction effect of high-quality LOS GNSS measurement in this paper. The nonlinear weighted least squares regression model and objective function are established for outlier mitigation, including a sigma-point iterative filtering framework and an M-estimation method of down-weighting GNSS measurements. Specifically, the maximum a posteriori (MAP) estimation idea is used to design the sigma-point iterated filtering framework, which makes the posteriori probability density function (PDF) constantly close to the high likelihood confidence interval to obtain excellent nonlinear approximation effects. Furthermore, to avoid the inherent non-convexity of the traditional M-estimation method, the relaxation compensation scheme based on the adaptive control factor is introduced into the robust loss function to accelerate the convergence of the penalty weight of GNSS outliers. The availability of the proposed method for GNSS outlier mitigation is proved by vehicle field tests under multipath interference and NLOS conditions.
- 12 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 70 (8) , 8334-8343
Strong Tracking UKF-Based Hybrid Algorithm and Its Application to Initial Alignment of Rotating SINS With Large Misalignment Angles
In this article, the fast and precise initial alignment of the low-cost rotary strapdown inertial navigation system under mooring conditions is investigated. The unscented Kalman filter (UKF) is used to address model nonlinearity and to achieve fast alignment for large misalignment angles. A generalized multifading strong tracking UKF (GSTUKF) is proposed to effectively compensate for the kinematic model errors caused by mooring and rotary motions. The performance of the standard strong tracking UKF cannot be optimal because only a portion of the fading factors associated with the directly observable state variables can be obtained approximately using the analytical method. By contrast, using the iteration method to calculate the full-dimensional fading factors precisely, the GSTUKF has greater robustness and adaptability. To find out the optimal fading factors in real time, the multivariate nonlinear optimization model is first designed, and then the iteration approach based on a hybrid algorithm consisting of particle swarm optimization and beetle antennae search is developed, which has no risk of falling into a local minimum. Simulations and experiments are conducted to validate the GSTUKF's effectiveness. The experiments demonstrate that the proposed method reduces the yaw error by 47.2% compared with the standard strong tracking UKF.
- 12 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 70 (8) , 8334-8343
Strong Tracking UKF-Based Hybrid Algorithm and Its Application to Initial Alignment of Rotating SINS With Large Misalignment Angles
In this article, the fast and precise initial alignment of the low-cost rotary strapdown inertial navigation system under mooring conditions is investigated. The unscented Kalman filter (UKF) is used to address model nonlinearity and to achieve fast alignment for large misalignment angles. A generalized multifading strong tracking UKF (GSTUKF) is proposed to effectively compensate for the kinematic model errors caused by mooring and rotary motions. The performance of the standard strong tracking UKF cannot be optimal because only a portion of the fading factors associated with the directly observable state variables can be obtained approximately using the analytical method. By contrast, using the iteration method to calculate the full-dimensional fading factors precisely, the GSTUKF has greater robustness and adaptability. To find out the optimal fading factors in real time, the multivariate nonlinear optimization model is first designed, and then the iteration approach based on a hybrid algorithm consisting of particle swarm optimization and beetle antennae search is developed, which has no risk of falling into a local minimum. Simulations and experiments are conducted to validate the GSTUKF's effectiveness. The experiments demonstrate that the proposed method reduces the yaw error by 47.2% compared with the standard strong tracking UKF.
- 14 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-17
A Robust Backtracking CKF Based on Krein Space Theory for In-Motion Alignment Process
The large misalignment angle errors generated by coarse alignment and the uncertainty time-varying calibration errors generated by the inertial measurement unit reduce the alignment accuracy, increase the alignment time, and ultimately limit the application of backtracking Kalman filters into In-motion fine alignment scene. This paper proposes a robust backtracking cubature Kalman filter (CKF) approach based on Krein space theory to overcome these issues. Specifically, considering the effect of dynamic model uncertainties of the alignment process, a linear robust filter and the existence conditions of optimal estimation are constructed to restrain the uncertainty interference according to Krein space theory. Meanwhile, an adaptive window adjustment algorithm is designed to intelligently determine the backtracking interval in different backtracking filtering stages and cross-scene motion environments, which is founded on the innovation variance gradient detection. Furthermore, using the statistical linearization scheme, the quasi-linear CKF model is derived to assist in resolving the nonlinear large misalignment angle within the Krein linear space framework for In-motion alignment. Experimental verification results from a vehicle In-motion alignment test illustrate that the proposed Krein backtracking CKF approach is effective in improving the alignment accuracy and shortening the alignment time simultaneously.
- 14 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-17
A Robust Backtracking CKF Based on Krein Space Theory for In-Motion Alignment Process
The large misalignment angle errors generated by coarse alignment and the uncertainty time-varying calibration errors generated by the inertial measurement unit reduce the alignment accuracy, increase the alignment time, and ultimately limit the application of backtracking Kalman filters into In-motion fine alignment scene. This paper proposes a robust backtracking cubature Kalman filter (CKF) approach based on Krein space theory to overcome these issues. Specifically, considering the effect of dynamic model uncertainties of the alignment process, a linear robust filter and the existence conditions of optimal estimation are constructed to restrain the uncertainty interference according to Krein space theory. Meanwhile, an adaptive window adjustment algorithm is designed to intelligently determine the backtracking interval in different backtracking filtering stages and cross-scene motion environments, which is founded on the innovation variance gradient detection. Furthermore, using the statistical linearization scheme, the quasi-linear CKF model is derived to assist in resolving the nonlinear large misalignment angle within the Krein linear space framework for In-motion alignment. Experimental verification results from a vehicle In-motion alignment test illustrate that the proposed Krein backtracking CKF approach is effective in improving the alignment accuracy and shortening the alignment time simultaneously.
- 18 April 2022
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering
- Vol. 236 (15) , 3281-3292
Adaptive Kalman filter based on multiple fading factors for fast in-motion initial alignment with rotation modulation technique
In this paper, a novel fast fine alignment method is proposed on the basis of micro electro mechanical systems (MEMS) for unmanned aerial vehicle (UAV) under mooring conditions. Firstly, the model of single-axis rotation modulation with extended angular rate measurement is built to improve the speed of convergence, especially the azimuth misalignment angle and the constant error of gyroscope along the rotation axis. Both model mismatch and noise uncertainty of the extended measurement will arise for the difficulty to obtain the exact angular velocity of the carrier without auxiliary sensors. To address this problem, the adaptive Kalman filter based on multiple fading factors is proposed. Besides, the meta-heuristic beetle antennae search (BAS) algorithm is applied for the first time to optimize the fading factors in real time. Then, the effectiveness of the proposed method is verified by means of singular value decomposition and error covariance matrix analysis. Finally, the result of comparative simulations and experiments show that the observability degree and convergence speed of misalignment angles improve significantly compared to those conventional methods and the estimated values can satisfy the requirements of fine alignment. More importantly, the constant error of gyroscope along the rotation axis is estimated accurately and can be compensated in the subsequent navigation process.
- 18 April 2022
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering
- Vol. 236 (15) , 3281-3292
Adaptive Kalman filter based on multiple fading factors for fast in-motion initial alignment with rotation modulation technique
In this paper, a novel fast fine alignment method is proposed on the basis of micro electro mechanical systems (MEMS) for unmanned aerial vehicle (UAV) under mooring conditions. Firstly, the model of single-axis rotation modulation with extended angular rate measurement is built to improve the speed of convergence, especially the azimuth misalignment angle and the constant error of gyroscope along the rotation axis. Both model mismatch and noise uncertainty of the extended measurement will arise for the difficulty to obtain the exact angular velocity of the carrier without auxiliary sensors. To address this problem, the adaptive Kalman filter based on multiple fading factors is proposed. Besides, the meta-heuristic beetle antennae search (BAS) algorithm is applied for the first time to optimize the fading factors in real time. Then, the effectiveness of the proposed method is verified by means of singular value decomposition and error covariance matrix analysis. Finally, the result of comparative simulations and experiments show that the observability degree and convergence speed of misalignment angles improve significantly compared to those conventional methods and the estimated values can satisfy the requirements of fine alignment. More importantly, the constant error of gyroscope along the rotation axis is estimated accurately and can be compensated in the subsequent navigation process.