Article
Automation & Control Systems
Zhichao Sun, Hang Ren, Huarui Sun, Gary G. Yen, Junjie Wu, Jianyu Yang
Summary: This article investigates the terminal trajectory planning for synthetic aperture radar (SAR) imaging guidance. A chronological iterative search framework (CISF) is proposed to solve the trajectory planning problem by decomposing it into subproblems and utilizing the optimization results of preceding subproblems. Experimental studies show the effectiveness and superiority of CISF compared to other methods.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Wencheng Han, Hao Li, Maoguo Gong
Summary: In this paper, a change detection method based on evolutionary multiobjective optimization is proposed to automatically perform binary and ternary change detection of multitemporal SAR images. The method designs two objectives based on the log-likelihood function of the Gaussian mixture model and the Bhattacharyya distance. A novel measurement method based on Bhattacharyya distance is designed for the ternary change detection task. The proposed approach uses a multiobjective optimization method based on non-dominated sorting to optimize these two objectives simultaneously, and incorporates chromosome ranking, perturbation probability selection operators, and a one-step local search strategy to improve the algorithm's performance. Experimental results demonstrate the effectiveness and robustness of the proposed algorithm.
APPLIED SOFT COMPUTING
(2022)
Article
Geochemistry & Geophysics
Yijiang Nan, Xiaojing Huang, Y. Jay Guo
Summary: This article proposes a new panoramic SAR which combines linear and rotational SARs to reconstruct a large 360 degrees panoramic view of the observed scene. It introduces the system geometry, imaging process, resolution analysis, sampling criteria, and a novel dynamic piecewise compensation algorithm. A prototype of panoramic SAR is built based on an FMCW radar and a moving platform, and simulation and experimental results are provided to validate the proposed principle and algorithm.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Xinhua Mao, Tianyue Shi, Ronghui Zhan, Yu-Dong Zhang, Daiyin Zhu
Summary: This article presents a new interpretation of the polar format algorithm for general bistatic spotlight synthetic aperture radar imaging, analyzing the roles of range and azimuth resampling on residual 2-D phase error and proposing a structure-aided 2-D autofocus approach to improve accuracy. Experimental results demonstrate the effectiveness of the proposed approach.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Computer Science, Artificial Intelligence
Fangqing Gu, Haosen Liu, Yiu-ming Cheung, Hai -Lin Liu
Summary: This study proposes an adaptive constraint regulation method to balance the feasibility and convergence of solutions by adjusting the constraint violation of infeasible solutions. Experimental results demonstrate that the proposed method effectively achieves solution balance and improves solution diversity.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Environmental Sciences
Pietro Mastro, Guido Masiello, Carmine Serio, Antonio Pepe
Summary: This work aims to explore the potential of incoherent and coherent change detection approaches using sequences of synthetic aperture radar (SAR) images for detecting and monitoring ground surface changes. By comparing interferometric coherence maps and amplitude backscattered signal variations, additional information can be obtained. The research primarily focuses on the capability and interactions of different coherent/incoherent change detection indices for rapidly mapping changed areas. Experiments demonstrate the usefulness of artificial intelligence algorithms in handling information from different CDIs and rapidly assessing damage.
Article
Computer Science, Artificial Intelligence
Zeneng She, Wenjian Luo, Xin Lin, Yatong Chang, Yuhui Shi
Summary: This paper focuses on the study of multiparty multiobjective optimization problems (MPMOPs) and proposes a new algorithm OptMPNDS3 to solve these problems. Comparisons with other algorithms on a problem suite show that OptMPNDS3 performs strongly and similarly.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Guangyuan Liu, Yangyang Li, Licheng Jiao, Yanqiao Chen, Ronghua Shang
Summary: This study introduces a new approach using a multiobjective evolutionary algorithm assisted stacked autoencoder for PolSAR image classification, which can adaptively optimize parameters and hyperparameters to achieve competitive results.
SWARM AND EVOLUTIONARY COMPUTATION
(2021)
Article
Engineering, Aerospace
Michael Inggs
Summary: This document summarizes the achievements in synthetic aperture radar (SAR) technology during the 50-year existence of the Aerospace and Electronic Systems Society. Advances in radar technology, driven by the digital revolution, have led to the widespread application of SAR in various fields. The development of coherent radar during World War II enabled the formation of large synthetic apertures, resulting in microwave images with high resolution that are unaffected by time and weather. The article traces the history of SAR technology from airborne platforms to satellites and discusses its achievements. SAR technology has now entered the phase of commercial exploitation, with a significant increase in available systems.
IEEE AEROSPACE AND ELECTRONIC SYSTEMS MAGAZINE
(2023)
Article
Geochemistry & Geophysics
Hongyang An, Junjie Wu, Kah Chan Teh, Zhichao Sun, Zhongyu Li, Jianyu Yang
Summary: This article proposes an efficient video formation method for video SAR systems with reduced data, modeling the observed scene as a sum of low-rank and sparse tensors and using a tensor alternating direction method of multiplier. Compared to traditional imaging methods, the proposed approach greatly reduces the amount of data samples.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Yuxuan Luan, Junjiang He, Jingmin Yang, Xiaolong Lan, Geying Yang
Summary: This paper proposes a uniformity-comprehensive multiobjective optimization evolutionary algorithm based on machine learning to address the common challenge faced by many existing algorithms in solving real-world optimization problems. By employing strategies such as uniform initialization and self-organizing map, the algorithm improves the population diversity and uniformity. Comparative analysis with 13 other algorithms validates the superiority of the proposed algorithm in terms of uniformity and objective function balance.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Xin Zhang, Chunlei Huo, Nuo Xu, Hangzhi Jiang, Yong Cao, Lei Ni, Chunhong Pan
Summary: This study introduces a multitask learning-based object detector (MTL-Det) to improve ship detection performance in SAR images by modeling the problem as three cooperative tasks and utilizing auxiliary subtasks to enhance feature learning. The approach effectively addresses the challenges posed by speckle noise in SAR images and outperforms traditional single-task-based object detectors.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Computer Science, Artificial Intelligence
Qiuzhen Lin, Wu Lin, Zexuan Zhu, Maoguo Gong, Jianqiang Li, Carlos A. Coello Coello
Summary: This article proposes a multimodal multiobjective evolutionary algorithm with dual clustering in decision and objective spaces to maintain diversity in solutions. Experimental results validate the advantages of this approach in maintaining diversity in both objective and decision spaces.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2021)
Article
Engineering, Electrical & Electronic
Yuri Alvarez Lopez, Jaime Laviada, Ana Arboleya, Fernando Las-Heras
Summary: Synthetic aperture radar (SAR)-based microwave imaging systems are widely used in various applications. The scanning speed is a crucial factor in SAR imaging systems, and widening the distance between measurements can increase it. However, this causes the presence of grating lobes that degrade the quality of microwave SAR images. To address this issue, a novel methodology is proposed in this study, which incorporates the amplitude and phase of the field radiated by the transmitting and receiving antennas in the backpropagation imaging algorithm. This method exploits the directive pattern of the antennas to reduce the level of grating lobes in SAR images.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Environmental Sciences
Zhenguo Yan, Xin Song, Lei Yang, Yitao Wang
Summary: The study proposes a SAR image ship classification method based on multiple classifiers ensemble learning (MCEL) and AIS data transfer learning, which increases the ship classification accuracy with limited samples by training models on AIS data and transferring them to SAR images.
Article
Geochemistry & Geophysics
Tongfei Liu, Maoguo Gong, Fenlong Jiang, Yuanqiao Zhang, Hao Li
Summary: This letter proposes a novel landslide inventory mapping (LIM) approach based on adaptive histogram-mean distance (AHMD), which takes into account the spatial contextual information of different landslide regions to improve detection performance. Experimental results demonstrate the superiority of the AHMD approach compared to seven other methods.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Sijia Zhang, Maoguo Gong, Yu Xie, A. K. Qin, Hao Li, Yuan Gao, Yew-Soon Ong
Summary: This paper proposes an influence-aware attention mechanism to learn the representative attributes of the whole crowd in order to detect anomalies in videos. By dividing pedestrians into multiple flows and measuring the consistency of movement patterns within the same stream and the interactions between different streams, this method addresses the issue of detection bias and false alarms caused by crowd overlaps and low-resolution images. Experimental results demonstrate the effectiveness and robustness of the proposed method.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Maoguo Gong, Jialu Liu, Hao Li, Yu Xie, Zedong Tang
Summary: This article proposes a novel face deidentification method that achieves a balance between facial privacy protection and data utilities. The method disentangles identity-related and identity-independent factors to deidentify the face, and employs an image inpainting network to enhance facial details and blend the deidentified face seamlessly. Experimental results demonstrate that the proposed method effectively deidentifies the face while preserving identity-independent information.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Information Systems
Shuang Liang, Yun Zhu, Hao Li
Summary: The joint integrated probabilistic data association (JIPDA) algorithm is widely used for automatic tracking of multiple targets. However, it has the well-known problem of track coalescence. In this study, a novel evolutionary optimization based joint integrated probabilistic data association (EOJIPDA) filter is developed to overcome this problem. By minimizing the trace of the covariance matrix, the accuracy of target state estimation can be improved.
Article
Computer Science, Artificial Intelligence
Wencheng Han, Hao Li, Maoguo Gong
Summary: In this paper, a change detection method based on evolutionary multiobjective optimization is proposed to automatically perform binary and ternary change detection of multitemporal SAR images. The method designs two objectives based on the log-likelihood function of the Gaussian mixture model and the Bhattacharyya distance. A novel measurement method based on Bhattacharyya distance is designed for the ternary change detection task. The proposed approach uses a multiobjective optimization method based on non-dominated sorting to optimize these two objectives simultaneously, and incorporates chromosome ranking, perturbation probability selection operators, and a one-step local search strategy to improve the algorithm's performance. Experimental results demonstrate the effectiveness and robustness of the proposed algorithm.
APPLIED SOFT COMPUTING
(2022)
Article
Engineering, Electrical & Electronic
Kai-Yuan Feng, Xia Fei, Maoguo Gong, A. K. Qin, Hao Li, Yue Wu
Summary: This paper proposes a novel channel pruning scheme to remove task-irrelevant channels in a task-driven manner, reducing computation costs while maintaining performance.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Tianqi Gao, Hao Li, Maoguo Gong, Mingyang Zhang, Wenyuan Qiao
Summary: This paper proposes a novel efficient metaheuristic change detection procedure based on superpixel-based multiobjective optimization. The method improves the accuracy of change detection by modeling a multiobjective optimization problem and designing a new mutation operator. Experimental results on real SAR datasets demonstrate the effectiveness of the proposed method in change detection.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Wencheng Han, Hao Li, Maoguo Gong
Summary: In this paper, a multi-regularization based on multifactorial multiobjective optimization is proposed to solve the sparse reconstruction problem. The problem is first constructed as a multi-regularization model and then optimized using a multifactorial multiobjective optimization method. A preference-based selection method and a sparsity-oriented crossover operator are designed to handle the priority and sparsity characteristic of the problem. Experimental results demonstrate the effectiveness and practicality of the proposed algorithm.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Yue Wu, Yibo Liu, Maoguo Gong, Peiran Gong, Hao Li, Zedong Tang, Qiguang Miao, Wenping Ma
Summary: This article proposes a method that models the multi-view point cloud registration problem as multi-task optimization and introduces a bi-channel knowledge sharing mechanism to improve the efficiency and effectiveness of the problem solving.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Xiaolong Fan, Maoguo Gong, Yue Wu, Hao Li
Summary: This paper proposes a method for graph representation learning by maximizing mutual information between feature and topology views. The method constructs a feature graph and uses a cross-view representation learning module to capture graph information. Experimental results demonstrate the effectiveness of integrating feature and topology views.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Geochemistry & Geophysics
Maoguo Gong, Wenyuan Qiao, Hao Li, A. K. Qin, Tianqi Gao, Tianshi Luo, Lining Xing
Summary: Remote sensing image series classification plays an important role in land cover analysis, but manual annotations are expensive and time-consuming. Domain adaptation (DA) provides a solution to this problem. However, traditional DA methods often result in information loss, affecting the classification effect. To address this, a network called RAFNet is proposed, which aligns inter-domain representations and fine-tunes the model using an information-based loss function. Experimental studies show that RAFNet achieves considerable segmentation accuracy even without annotated information in the target domain.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Yuanqiao Zhang, Maoguo Gong, Yuan Gao, Hao Li, Lei Wang, Yixin Wang
Summary: Multi-party learning is a widely used distributed learning framework in the medical system and mobile data analysis. It protects data privacy by having individual devices update model parameters instead of sharing sensitive data. However, balancing model performance and computational costs during communication rounds is challenging. In this article, we propose a novel framework called Multi-objective Multi-Party Learning via Diverse Steps (MMPL). We treat multi-party learning as a multi-objective problem and employ evolutionary optimization for analysis. Our framework utilizes neural networks to connect evolutionary optimization with multi-party learning and introduces a novel strategy for complex encoding problems. Experimental results demonstrate that our method achieves better performance and partially alleviates the time-consuming issue compared to other algorithms.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Geochemistry & Geophysics
Mingyang Zhang, Hao Liu, Maoguo Gong, Hao Li, Yue Wu, Xiangming Jiang
Summary: This paper proposes a cross-domain self-taught network (CDSTN) for few-shot HSI classification. It combines domain adaptation (DA) and semi-supervised self-taught strategy to utilize labeled and unlabeled samples from source and target domains. Experimental results show that CDSTN achieves superior and stable performance with limited labeled samples.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Mingyang Zhang, Tianqi Gao, Maoguo Gong, Shengqi Zhu, Yue Wu, Hao Li
Summary: This article proposes a novel semi-supervised framework for high-resolution RS image change detection, which combines a small amount of labeled data and a large amount of unlabeled data to train the CD network. Experimental results demonstrate the effectiveness and superiority of the proposed method.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Zedong Tang, Maoguo Gong, Yu Xie, Hao Li, A. K. Qin
Summary: This study introduces a level-based inter-task learning strategy that categorizes particles into different levels and employs various inter-task learning methods. This strategy enhances the transfer of shared information among cross-task neighborhoods, allowing the algorithm to efficiently explore the search space and refine search areas.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2022)
