Yanling Shi

Dr. Yanling Shi


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 July 2022 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YSYanling Shi
Yanling Shi
YGYaxing Guo
Yaxing Guo
TYTingting Yao
Tingting Yao
ZLZipeng Liu
Zipeng Liu
In this paper, we propose the False-Alarm-Rate-Controllable (FAC) classification of sea clutter Recurrence Plots (RPs) based on Convolutional Neural Networks (CNN), which is shortened as RPs-CNN. Sea clutter data is a non-linear and recursive time series, and RPs provide qualitative analysis of non-linear and recursive dynamic systems. Thus, we construct the RPs datasets to extract the recursive feature of sea clutter. In the RPs datasets, RPs parameters, embedding delay τ and embedding dimension m, are obtained by the average mutual information (AMI) and false nearest neighbor (FNN) algorithms, respectively. In addition, in order to extract the local features of RPs, CNN is applied. CNN makes full use of local features of the datasets, has the advantages of translation invariance and strong generalization ability, and shares the available weights to simplify network structure. We implement a proper LeNet-5 CNN training on the constructed RPs datasets, and verity it by IPIX measured datasets. The experimental results demonstrate that the CNN successfully classifies the RPs of targets and clutter. Moreover, the feasibility of RPs-CNN is verified by seven aspects, i.e., Accuracy, Precision, False Alarm, Miss Rate, Recall, F1-measure and Kappa. In addition, six parameters that may affect the classification performance are also analyzed, including time-series length, embedding delay, embedding dimension, convolutional kernel size, kernel depth, and optimization function. The results indicate that the proposed RPs-CNN method can reach a 92.05% F1-measure and 87.19% Kappa which performs better than other classification methods. Meanwhile, the false alarm rate (FAR) of the RPs-CNN is testified by the FAC classification. Experimental results demonstrate that the proposed RPs-CNN significantly improves the detection probability over other classification detectors in low FAR cases.

21 July 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
YSYanling Shi
Yanling Shi
YHYuefeng Hu
Yuefeng Hu
Abstract For the feature-based detector of small targets in sea clutter, on the one hand, the three-dimensional convex hull-based detector deviates from the distribution of sea clutter vectors in the feature space and only combines the information of low-dimen-sional features. On the other hand, the redundancy and correla-tion between high-dimensional features are high. Consequently, we propose a detector for detecting small floating targets in sea clutter in high-dimensional feature space (HDFS) in this paper. First, the mRMR algorithm to choose the low-relatedness features from the HDFS is proposed. For the mRMR algorithm, we choose the target features and sea clutter features from the 8-dimensional feature space (8-DFS), where the target features and sea clutter features have the highest degree of discrimination in the 3-dimen-sionalfeature space (3-DFS). Second, the distributionof sea clutter in the 3-DFS is concave or convex, which depends on the selection of features. In most cases, the distribution is concave. Using the traditional convex hull to match the concave distribution of sea clutter inevitably enlarges the judgment area and considerably de-creases the detection probability. Due to the concave distribution of sea clutter in the 3-DFS, we propose a new false alarm control-lable three-dimensional concave hull detector based on the mRMR (mRMR-Tri-ConcaveHull detector). In the mRMR-Tri-Concave-Hull detector, the feature vectors in the 3-DFS, which are selected by mRMR, form a concave area that is more suitable for the Con-caveHull detector. Through theexperimentalanalysisof the meas-ured data, we find that the proposed mRMR-Tri-ConcaveHull in this paper can significantly enhance the detection performance compared with the three-feature convex hull detector.

28 April 2025 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
YSYanling Shi
Yanling Shi
XGXingyi Gao
Xingyi Gao
The non-stationary, non-Gaussian, and non-homogeneous sea clutter pose significant challenges for the detection of small floating targets in sea clutter. Traditional detectors based on statistical models often encounter performance limitations. However, recent research has shown that echo signals contain abundant frequency, amplitude, and phase information, which is of great significance for the development of feature-based detector. Due to the ordered target and the chaotic clutter, we extract the Symmetric Dot Pattern (SDP) image features to capture the regularity of signal in the time dynamic trends and propose a threshold controllable random forest detector (SDP-TC-RF) to detect the small target in sea clutter. The amplitude of signal is transformed by SDP into mirror-symmetric snowflake images in a two-dimensional polar coordinate space, referred to as SDP images. It is demonstrated that target SDP images exhibit an ordered structure, such as sharp boundary definition, morphological smoothness, and rotational symmetry, while clutter SDP images appear disordered, resembling the distinction between non-chaotic targets and chaotic clutter. Subsequently, texture features and edge features of both the sea clutter SDP images and the target SDP images are extracted and fed into the Random Forest (RF) detector with a control the false alarm rate based on the Neyman-Pearson criterion. To leverage the different features extracted from the SDP images, we design two detectors: the TC-RF detector based on the texture features of the SDP images (SDP-T-TC-RF) and the TC-RF detector based on the Sobel edge features of the SDP images (SDP-S-TC-RF). Experimental validation is carried out with the publicly available IPIX radar dataset. With an accumulation time of 1.024 seconds and a false alarm probability of 0.001, the average detection probabilities of the SDP-T-TC-RF and SDP-S-TC-RF detectors reach 0.5852 and 0.9316, respectively, demonstrating an effective detection performance.

7 April 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YSYanling Shi
Yanling Shi
WCWeisheng Chen
Weisheng Chen
In the complex marine environment, traditional detectors based on the classifiers cannot guarantee the global false alarm control. In this paper, we propose a detector based on dual channel convolutional neural network (DC-CNN) and global false alarm controllable adaptive boosting tree (GFAC-A), which is shortened as DC-CNN-GFAC-A. DC-CNN focuses on the correlation features of radar echoes in time domain and frequency domain, better use multi-dimensional features and show a better feature extraction ability. Through the application of GFAC-A, the false alarm rate is introduced into the algorithm combining decision tree and AdaBoost to achieve the high-performance detection of global false alarm controllable for high-dimensional features. It is heuristics. The combination of DC-CNN and GFAC-A solves the disadvantage that current classifiers cannot meet the conditions of good performance and low false alarm. First, the connectivity information is obtained by using the frequency domain amplitude characteristics of radar echo data, and the recursive information is obtained by using the nonlinear recursive time series characteristics. And the dual-channel datasets of targets and clutter are built. Then, DC-CNN is built to extract and fuse high-dimensional features to obtain feature vectors of targets and clutter. Besides, the performance comparison of different neural network model combinations is carried out. Finally, compared with the traditional threshold-controllable classifiers, the proposed GFAC-A classifier achieves the high detection performance under the global controlled false alarm. The results show that DC-CNN-GFAC-A can achieve 96.491% detection accuracy when the false alarm rate is 10 -3 , which is superior to other detections.

11 December 2024 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
SSSun Sizhe
Sun Sizhe
YSYanling Shi
Yanling Shi
Multi-Function Radar (MFR) can be probabilistically transferred to different operating modes according to the surrounding environment, and multi-radar is often the case in reality. Compared with one-to-one jamming, multi-radar jamming involves the selection of jamming action of each radar and the scheduling of the whole resource. Therefore, the development of intelligent jamming methods for cluster asymmetric countermeasures has become an important task in electronic warfare. In this manuscript, we propose a solution to address the problem of formulating jamming schemes under conditions of asymmetrical countermeasures within a cluster with limited resources. Specifically, we have investigated a Joint Optimization of Resource Utilization and Jamming Method Selection for Cluster Asymmetrical MFRs (JO-RUJMSCAR). Considering the threat level of the overall MFR operating states and the variations in jamming power across different alignment states, we have meticulously designed the reward function, radar state space, and action space. Furthermore, for the asymmetrical tasks of the cluster, we have proposed a set of evaluation criteria for the jamming scheme, which takes into account the overall threat level and the power expenditure. Ultimately, the simulation results demonstrate that the proposed algorithm is capable of learning highly adaptive strategies within asymmetrical cluster jamming and has achieved commendable performance in terms of jamming. The model proposed in this manuscript not only has a good performance in the field of electronic countermeasures, but also has a certain universality to other cluster non-peer environments.

4 May 2026 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
JYJianguo Yao
Jianguo Yao
YSYanling Shi
Yanling Shi
Ziwei LiuZiwei Liu
Ziwei Liu
XBXiaodong Bai
Xiaodong Bai
This paper presents an orthogonal waveform design framework for multiple-input multiple-output synthetic aperture radar (MIMO-SAR) systems using optimal frequency hopping patterns (OFHPs) derived from two-dimensional cyclic shifts of an algebraically constructed Costas array. The resulting waveform set exhibits ideal two-dimensional autocorrelation and cross-correlation properties, enabling enhanced resolution and reduced inter-antenna interference. An ambiguity volume reduction strategy based upon the proposed OFHPs is introduced to improve performance in cluttered environments with overlapping reflections. Moreover, each frequency-hopping subpulse incorporates a subchirp to enhance resolution, while alternating positive and negative-slope subchirps are employed to suppress sidelobes in the ambiguity and cross-ambiguity functions. Analytical expressions are established to characterize the signal synthesis process and to elucidate the associated correlation properties of the proposed OFHP-based waveform design. Simulation results and comparative analysis with existing mainstream MIMO-SAR waveforms demonstrate the effectiveness of the proposed method for high-resolution imaging, robust interference suppression, and advanced MIMO-SAR applications, as evidenced by superior ambiguity and cross-ambiguity performance, reduced ambiguity volume, and mitigated mutual interference.