Guoan Bi
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
Guoan Bi has a total of 318 co-authors. Here are the top co-authors by number of shared publications:
Lu Wang
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798
30 shared publicationsLifan Zhao
Nanyang Technological University
26 shared publications- Lei Yang
Civil Aviation University of China
24 shared publications - Xiumei Li
School of Information Science and Technology, Hangzhou Normal University, Hangzhou 311121, China
17 shared publications Haijian Zhang
16 shared publications- Yonghong Zeng
Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore
16 shared publications
Latest Publications
- 17 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (1) , 748-753
Guest Editorial Introduction to the Special Issue on Advanced Signal Processing and AI Technologies for Transportation Big Data and Their Applications in COVID-19 Scenario and Beyond
Compared with the traditional transportation data, the transportation big data (TBD) is under the background of “Internet + traffic.” It is a great challenge for analyzing and processing TBD because of its complex and unstructured characteristics, such as sequence, strong relevance, accuracy, and closed loop. This Special Issue provides high-quality and up-to-date technology related to the application of SP and AI into TBD and their applications in the COVID-19 scenario and beyond and serves as a forum for researchers all over the world to discuss their works and recent advancements in the field, especially for defensing COVID-19 in public transportation.
- 17 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (1) , 748-753
Guest Editorial Introduction to the Special Issue on Advanced Signal Processing and AI Technologies for Transportation Big Data and Their Applications in COVID-19 Scenario and Beyond
Compared with the traditional transportation data, the transportation big data (TBD) is under the background of “Internet + traffic.” It is a great challenge for analyzing and processing TBD because of its complex and unstructured characteristics, such as sequence, strong relevance, accuracy, and closed loop. This Special Issue provides high-quality and up-to-date technology related to the application of SP and AI into TBD and their applications in the COVID-19 scenario and beyond and serves as a forum for researchers all over the world to discuss their works and recent advancements in the field, especially for defensing COVID-19 in public transportation.
- 24 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 17 (5) , 3379-3381
Guest Editorial: Special Section on Advanced Signal Processing and AI Technologies for Industrial Big Data
The papers in this special section focus on advanced signal processing and artificial intelligence (AI) technologies for industrial Big Data (IBD) powered by Industry 4.0. Modern industry has evolved from the traditional manufacturing industry to digital and intelligent industry. Huge amount of complex real-time data are generated from the thousands of industrial sensors in physical and man-made environments. Industrial big data (IBD) afford us an unprecedented opportunity to obtain an in-depth understanding of Internet of Things and facilitate data-driven approaches for industrial optimization and scheduling. The papers in this section collect the latest ideas and research on advanced signal processing and artificial intelligence (AI) technologies for IBD.
- 24 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 17 (5) , 3379-3381
Guest Editorial: Special Section on Advanced Signal Processing and AI Technologies for Industrial Big Data
The papers in this special section focus on advanced signal processing and artificial intelligence (AI) technologies for industrial Big Data (IBD) powered by Industry 4.0. Modern industry has evolved from the traditional manufacturing industry to digital and intelligent industry. Huge amount of complex real-time data are generated from the thousands of industrial sensors in physical and man-made environments. Industrial big data (IBD) afford us an unprecedented opportunity to obtain an in-depth understanding of Internet of Things and facilitate data-driven approaches for industrial optimization and scheduling. The papers in this section collect the latest ideas and research on advanced signal processing and artificial intelligence (AI) technologies for IBD.
- 21 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-14
Super-Resolution ISAR Imaging for Maneuvering Target Based on Deep-Learning-Assisted Time–Frequency Analysis
Traditional range-instantaneous Doppler (RID) methods for maneuvering target imaging suffer from the problems of low resolution and poor noise suppression. We propose a new super-resolution inverse synthetic aperture radar (ISAR) imaging method based on deep-learning-assisted time–frequency analysis (TFA). Our deep neural network resembles the basic structure of a U-net with two additional convolutional-upsampling layers and $l_{1}$ -norm loss function for super-resolution generation and noise suppression. The neural network is trained in advance to learn the mapping function between the low-resolution time–frequency spectrum inputs and their high-resolution references. Then, the linear TFA assisted by the pretrained network is integrated into the RID-based ISAR imaging system and is found to achieve sharply focused and denoised target image with super-resolution. Both the simulated and real radar data are used to evaluate the performance of the proposed method. Numerical experimental results demonstrate the superiority of the proposed ISAR imaging method over traditional ones.
- 21 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-14
Super-Resolution ISAR Imaging for Maneuvering Target Based on Deep-Learning-Assisted Time–Frequency Analysis
Traditional range-instantaneous Doppler (RID) methods for maneuvering target imaging suffer from the problems of low resolution and poor noise suppression. We propose a new super-resolution inverse synthetic aperture radar (ISAR) imaging method based on deep-learning-assisted time–frequency analysis (TFA). Our deep neural network resembles the basic structure of a U-net with two additional convolutional-upsampling layers and $l_{1}$ -norm loss function for super-resolution generation and noise suppression. The neural network is trained in advance to learn the mapping function between the low-resolution time–frequency spectrum inputs and their high-resolution references. Then, the linear TFA assisted by the pretrained network is integrated into the RID-based ISAR imaging system and is found to achieve sharply focused and denoised target image with super-resolution. Both the simulated and real radar data are used to evaluate the performance of the proposed method. Numerical experimental results demonstrate the superiority of the proposed ISAR imaging method over traditional ones.
- 1 November 2020
- Published by Elsevier in Signal Processing
- Vol. 176
Distributed compressive sensing via LSTM-Aided sparse Bayesian learning
- 1 November 2020
- Published by Elsevier in Signal Processing
- Vol. 176
Distributed compressive sensing via LSTM-Aided sparse Bayesian learning
- Open Access
- 18 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 13 (19391404) , 4825-4835
FMCW SAR Sparse Imaging Based on Approximated Observation: An Overview on Current Technologies
Sparsity-driven synthetic aperture radar (SAR) imaging technique for frequency modulation continuous-wave (FMCW) has already shown the superiority in terms of performance improvement in imaging and recovery from down-sampled data. However, restricted by the computational cost, conventional FMCW SAR sparse imaging method based on observation matrix is not able to achieve the large-scale scene reconstruction, not to mention real-time processing. To solve this problem, the FMCW SAR sparse imaging theory based on approximated observation is proposed by using an echo simulation operator to replace typical observation matrix, and recovering the scene via two-dimensional (2-D) regularization operation. This new technology can achieve high-resolution sparse imaging of the scene with a computational cost close to that of traditional matched filtering (MF) algorithms, which makes several applications, such as early-warning and battlefield monitoring, possible by using FMCW SAR sparse imaging system. In this paper, we present the recent research progress on approximated observation based FMCW SAR sparse imaging to deal with a few key issues for practical radar systems. In particular, we describe 1) Lq-norm regularization based imaging technique that makes sparse reconstruction of large-scale scene possible; 2) L2,q-norm regularization based imaging technique that minimizes the azimuth ambiguities in high-resolution sparse imaging; 3) a sparse imaging technique that supports real-time applications of FMCW SAR imaging.
- 18 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 13 (19391404) , 4825-4835
Open AccessFMCW SAR Sparse Imaging Based on Approximated Observation: An Overview on Current Technologies
Sparsity-driven synthetic aperture radar (SAR) imaging technique for frequency modulation continuous-wave (FMCW) has already shown the superiority in terms of performance improvement in imaging and recovery from down-sampled data. However, restricted by the computational cost, conventional FMCW SAR sparse imaging method based on observation matrix is not able to achieve the large-scale scene reconstruction, not to mention real-time processing. To solve this problem, the FMCW SAR sparse imaging theory based on approximated observation is proposed by using an echo simulation operator to replace typical observation matrix, and recovering the scene via two-dimensional (2-D) regularization operation. This new technology can achieve high-resolution sparse imaging of the scene with a computational cost close to that of traditional matched filtering (MF) algorithms, which makes several applications, such as early-warning and battlefield monitoring, possible by using FMCW SAR sparse imaging system. In this paper, we present the recent research progress on approximated observation based FMCW SAR sparse imaging to deal with a few key issues for practical radar systems. In particular, we describe 1) Lq-norm regularization based imaging technique that makes sparse reconstruction of large-scale scene possible; 2) L2,q-norm regularization based imaging technique that minimizes the azimuth ambiguities in high-resolution sparse imaging; 3) a sparse imaging technique that supports real-time applications of FMCW SAR imaging.
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Joint sparsity-inducing DOA estimation for strictly noncircular sources with unknown mutual coupling
In this paper, a joint sparsity-inducing DOA estimation method is proposed for strictly noncircular sources with unknown mutual coupling. In the proposed method, two block-sparse recovery models are firstly formulated via parameterizing the steering vector without losing the array aperture. Then, taking the noncircularity of sources into account, a joint sparsity-inducing framework combined with reweighted l 1 - norm optimization is constructed to estimate DOA, where the weighted matrix is structured by the noncircular MUSIC-like (NC MUSIC-like) spectrum function to strengthen the sparsity. Finally, DOA estimation can be realized via screening the position of nonzero blocks of the recovered block sparse matrix. Some simulations are implemented to demonstrate that the proposed method shows the effectiveness and superiority with unknown mutual coupling.
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Joint sparsity-inducing DOA estimation for strictly noncircular sources with unknown mutual coupling
In this paper, a joint sparsity-inducing DOA estimation method is proposed for strictly noncircular sources with unknown mutual coupling. In the proposed method, two block-sparse recovery models are firstly formulated via parameterizing the steering vector without losing the array aperture. Then, taking the noncircularity of sources into account, a joint sparsity-inducing framework combined with reweighted l 1 - norm optimization is constructed to estimate DOA, where the weighted matrix is structured by the noncircular MUSIC-like (NC MUSIC-like) spectrum function to strengthen the sparsity. Finally, DOA estimation can be realized via screening the position of nonzero blocks of the recovered block sparse matrix. Some simulations are implemented to demonstrate that the proposed method shows the effectiveness and superiority with unknown mutual coupling.
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 18 (7) , 1224-1228
Airborne FMCW SAR Sparse Data Processing via Frequency-Scaling Algorithm
Using the continuous-wave technology to replace the conventional pulse-mode, frequency-modulation continuous-wave (FMCW) synthetic aperture radar (SAR) has shown good potentials of reducing the weight of the system and the sensors' peak transmission power. In order to relax the requirements of data bandwidth and storage, and increase the swath, the SAR system will collect the downsampled data, which makes the traditional matched filtering (MF)-based method unable to recover the considered scene, leading to failed reconstruction. To solve this problem, this letter presents an FMCW SAR sparse imaging method based on the frequency-scaling algorithm (FSA). Experimental results on the real data show that compared with the MF-based FMCW SAR imaging algorithms, the proposed method can improve the recovered image performance effectively. For the sparse surveillance region, it can achieve accurate recovery even from the downsampled data. Because the computational complexity of the proposed method is in the same order as that of MF, the sparse imaging of large-scale scenes can also be realized in the FMCW SAR.
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 18 (7) , 1224-1228
Airborne FMCW SAR Sparse Data Processing via Frequency-Scaling Algorithm
Using the continuous-wave technology to replace the conventional pulse-mode, frequency-modulation continuous-wave (FMCW) synthetic aperture radar (SAR) has shown good potentials of reducing the weight of the system and the sensors' peak transmission power. In order to relax the requirements of data bandwidth and storage, and increase the swath, the SAR system will collect the downsampled data, which makes the traditional matched filtering (MF)-based method unable to recover the considered scene, leading to failed reconstruction. To solve this problem, this letter presents an FMCW SAR sparse imaging method based on the frequency-scaling algorithm (FSA). Experimental results on the real data show that compared with the MF-based FMCW SAR imaging algorithms, the proposed method can improve the recovered image performance effectively. For the sparse surveillance region, it can achieve accurate recovery even from the downsampled data. Because the computational complexity of the proposed method is in the same order as that of MF, the sparse imaging of large-scale scenes can also be realized in the FMCW SAR.
- 4 April 2020
- Published by Springer Nature
- p. 739-748
Flexible Sparse Representation Based Inverse Synthetic Aperture Radar Imaging
- 4 April 2020
- Published by Springer Nature
- p. 739-748
Flexible Sparse Representation Based Inverse Synthetic Aperture Radar Imaging
- 4 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 58 (9) , 6197-6209
Target Localization in High-Coherence Multipath Environment Based on Low-Rank Decomposition and Sparse Representation
In a multipath propagation environment, prevalent target localization methods are mainly based on the classical two-ray propagation model without considering other reflected waves. Because the received target echoes are considerably corrupted by multipath reflections in the case of complex terrain, these prevalent methods might fail to work or achieve poor performance. To solve this problem, we first consider a practical multipath propagation scenario to reveal the dynamic structural relationship of the spatial paths based on the spherical earth model. Subsequently, a target localization algorithm based on low-rank decomposition (LRD) and sparse representation (SR) framework is proposed. The proposed algorithm can effectively mitigate the effects of complex multipath interference without using any prior knowledge on the illuminated terrain and the reflecting paths. Experiments on synthetic data and real data validate the effectiveness of the proposed algorithm.
- 4 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 58 (9) , 6197-6209
Target Localization in High-Coherence Multipath Environment Based on Low-Rank Decomposition and Sparse Representation
In a multipath propagation environment, prevalent target localization methods are mainly based on the classical two-ray propagation model without considering other reflected waves. Because the received target echoes are considerably corrupted by multipath reflections in the case of complex terrain, these prevalent methods might fail to work or achieve poor performance. To solve this problem, we first consider a practical multipath propagation scenario to reveal the dynamic structural relationship of the spatial paths based on the spherical earth model. Subsequently, a target localization algorithm based on low-rank decomposition (LRD) and sparse representation (SR) framework is proposed. The proposed algorithm can effectively mitigate the effects of complex multipath interference without using any prior knowledge on the illuminated terrain and the reflecting paths. Experiments on synthetic data and real data validate the effectiveness of the proposed algorithm.
- 1 January 2020
- Published by Elsevier in Signal Processing
- Vol. 166
Structured Bayesian learning for recovery of clustered sparse signal
- 1 January 2020
- Published by Elsevier in Signal Processing
- Vol. 166
Structured Bayesian learning for recovery of clustered sparse signal