Jifei Pan

Prof. Dr. Jifei Pan

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
14 December 2021 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
ZLZhihui Li
Zhihui Li
JSJunpeng Shi
Junpeng Shi
WLWeijian Liu
Weijian Liu
JPJifei Pan
Jifei Pan
BLBinbin Li
Binbin Li
This paper deals with the joint design problem of transmit waveform and receive filter for the robust detection of ground moving target with multiple-input multiple-output Space time adaptive processing (MIMO- STAP) radar in the presence of target and clutter uncertainties. With the prior knowledge of target and clutter statistics, the averaged signal-to-interference-plus-noise ratio (SINR) is formulated as a figure of merit to maximize. The robust joint design problems for the continuous and discrete phase cases, respectively, are formulated with the constant-modulus and similarity constraints. Then, an efficient iterative algorithm is developed for improving the SINR. Specifically, each iteration of the proposed algorithm involves the generalized eigenvalue decomposition to optimize the receive filter, while a nested iterative procedure involving Dinkelbach’s framework and alternating direction penalty method (ADPM) algorithm to design transmit waveform. The proposed algorithm can achieve higher SINR with reduced computational load compared to the recently developed ones. Numerical examples demonstrate the effectiveness of the proposed method for the robust detection of moving target in MIMO-STAP radar.

29 January 2025 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
MDMingyang Du
Mingyang Du
JPJifei Pan
Jifei Pan
DBDaping Bi
Daping Bi
The use of supervised deep neural network (DNN) for automatic modulation classification, offering an end-to-end diagram, has gained significant attention in military and civilian field, e.g., spectrum monitoring, specific emitter identification and cognitive radio. However, this approach suffers from issues such as generalization error and spurious correlations. In an effort to capture and extract more abstract and useful concepts that can enhance performance on downstream tasks, one of the promising representation learning methods, known as “contrastive learning”, has achieved notable success in computer vision and natural language processing. This approach maximizes the similarities between different views of the same data example in the latent space to learn useful features. In this paper, we propose a contrastive-based objective for improving the transferability performance on the lower signal-to-noise ratios (SNR) dataset. Compared to the previous denoised-based methods used for classifying noisy signal data, we eliminate the constraints of pairwise input. This means that our model can leverage arbitrary combination of noisy and clean signal examples within same category. Additionally, the introduction of the noise level estimation enhances the robustness to the uncertain noise conditions. Simulation results on both the synthetic radar signal dataset and public communication signal dataset demonstrate that the proposed method exhibits minimal generalization error and showcases promising performance on signal data with different noise type.

10 May 2017 in Journal of Drug Targeting
Verified
Journal Article
Closed access
LZLin Zhang
Lin Zhang
JPJifei Pan
Jifei Pan
SDShibo Dong
Shibo Dong
ZLZhaoming Li
Zhaoming Li
Finding adequate carriers for proteins/peptides and anticancer drugs delivery has become an urgent need, owing to the growing number of therapeutic macromolecules and the increasing amount of cancer incidence. Polysaccharide-based nanogels have attracted interest as carriers for proteins/peptides and anticancer drugs because of their characteristic properties like biodegradability, biocompatibility, stimuli-responsive behaviour, softness and swelling to help achieve a controlled, triggered response at the target site. In addition, the groups of the polysaccharide backbone are able to be modified to develop functional nanogels. Some polysaccharides have the intrinsic ability to recognise specific cell types, allowing the design of targeted drug delivery systems through receptor-mediated endocytosis. This review is aimed at describing and exploring the potential of polysaccharides that are used in nanogels which can help to deliver proteins/peptides and anticancer drugs.

7 May 2021 in IET Radar, Sonar & Navigation
Verified
Journal Article
Open access
PDF file
XXXinsong Xu
Xinsong Xu
DBDaping Bi
Daping Bi
JPJifei Pan
Jifei Pan
Radar signal recognition plays a vital role in electronic warfare. For the multifunction radars (MFRs) with complex dynamical modes, the signal recognition needs to identify not only the emitter but also its current functional state. Existing research on MFR recognition mainly focuses on hierarchical modelling approaches. Inspired by recent progress of deep neural networks, the authors propose to further develop radar signal modelling with recurrent neural networks. Here, the authors propose a more efficient method for functional state recognition of MFRs based on a gated recurrent unit (GRU). The method makes full use of the ability of GRUs to automatically learn the characteristics of radar signal sequences, and the nonlinear modelling of GRUs can deal with the corrupted data well. Simulation results on the Mercury radar show that the proposed method achieves a great recognition accuracy with little prior information, and the designed GRU model outperforms the predictive state representation model under the same condition.

1 November 2022
Verified
Conference Paper
Closed access
JPJifei Pan
Jifei Pan
LGLinqing Guo
Linqing Guo
QCQiuju Chen
Qiuju Chen
SZShengli Zhang
Shengli Zhang
JXJingwei Xiong
Jingwei Xiong
With the development of the multifunction radar, the traditional specific emitter identification (SEI) can no longer meet the needs of the observe-orient-decide-act (OODA) closed loop, and most identification networks are in the process of converting one-dimensional (1D) radar emitter signals into two-dimensional (2D) signals to adapt the network input, which easily misses information. To address the above problems, this paper adopts a 1D convolutional residual neural network with the convolutional block attention module (1D-CBAM-ResNet) for automatic learning and single-step identification of 1D inter-mediate frequency (IF) signals to improve SEI accuracy. The model combines the 1D residual building unit (1D-RBV) with the 1D convolutional block attention module (1D-CBAM) to effectively aggregate channel and spatial information to accurately capture fingerprint features within the pulse. The simulation results demonstrate that the overall identification accuracy of the algorithm for 10 emitters of the same type reaches 93.03%, which proves the effectiveness and feasibility of the module.

14 March 2023 in Sensors
Verified
Journal Article
Open access
PDF file
JPJifei Pan
Jifei Pan
JXJingwei Xiong
Jingwei Xiong
YZYihong Zhuo
Yihong Zhuo
Mode recognition is a basic task to interpret the behavior of multi-functional radar. The existing methods need to train complex and huge neural networks to improve the recognition ability, and it is difficult to deal with the mismatch between the training set and the test set. In this paper, a learning framework based on residual neural network (ResNet) and support vector machine (SVM) is designed, to solve the problem of mode recognition for non-specific radar, called multi-source joint recognition framework (MSJR). The key idea of the framework is to embed the prior knowledge of radar mode into the machine learning model, and combine the manual intervention and automatic extraction of features. The model can purposefully learn the feature representation of the signal on the working mode, which weakens the impact brought by the mismatch between training and test data. In order to solve the problem of difficult recognition under signal defect conditions, a two-stage cascade training method is designed, to give full play to the data representation ability of ResNet and the high-dimensional feature classification ability of SVM. Experiments show that the average recognition rate of the proposed model, with embedded radar knowledge, is improved by 33.7% compared with the purely data-driven model. Compared with other similar state-of-the-art reported models, such as AlexNet, VGGNet, LeNet, ResNet, and ConvNet, the recognition rate is increased by 12%. Under the condition of 0–35% leaky pulses in the independent test set, MSJR still has a recognition rate of more than 90%, which also proves its effectiveness and robustness in the recognition of unknown signals with similar semantic characteristics.