Yu Lei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yu Lei has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Boyi Yang
College of Information and Communication Engineering, Harbin Engineering University, Harbin, China
3 shared publications - Tao Chen
College of Information and Communication Engineering, Harbin Engineering University, Harbin, China
3 shared publications - Limin Guo
College of Information and Communication Engineering, Harbin Engineering University, Harbin, China
2 shared publications Limin Guo
College of Information and Communication Engineering Harbin Engineering University Harbin China
1 shared publicationTao Chen
College of Information and Communication Engineering Harbin Engineering University Harbin China
1 shared publication- Yuning Liu
College of Information and Communication Engineering Harbin Engineering University Harbin China
1 shared publication
Latest Publications
- Open Access
- 26 April 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (9) , 1538
MRCS-Net: Multi-Radar Clustering Segmentation Networks for Full-Pulse Sequences
To facilitate the full-pulse sequence received by a radar reconnaissance receiver, this study proposed a clustering segmentation method for radar signals. Owing to the influence of the complex electromagnetic environment, the probability of the occurrence of time–frequency overlapping of signals increases, and the demand for signal localization and classification becomes higher. However, most existing studies have only classified and identified individual pulse signals and lack the ability to analyze signals for full pulses. This study proposed a multi-radar cluster-based segmentation network (MRCS-Net) for large time-length full-pulse signals. The network innovatively addresses the processing challenges of prolonged full-pulse signals and effectively achieves the classification and recognition of different pulses under time–frequency overlapping conditions. The proposed algorithm filters the signal with SincNet and then sequentially feeds the sequence into a long short-term memory network. Consequently, the outputs are clustered and segmented using multilayer perceptrons and classifiers. Experiments were conducted on six different types of radar signals. The results demonstrated that the proposed method exhibited lower segmentation error rate metric compared to other similar methods. Moreover, it outperformed other methods in terms of recognition performance.
- 26 April 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (9) , 1538
Open AccessMRCS-Net: Multi-Radar Clustering Segmentation Networks for Full-Pulse Sequences
To facilitate the full-pulse sequence received by a radar reconnaissance receiver, this study proposed a clustering segmentation method for radar signals. Owing to the influence of the complex electromagnetic environment, the probability of the occurrence of time–frequency overlapping of signals increases, and the demand for signal localization and classification becomes higher. However, most existing studies have only classified and identified individual pulse signals and lack the ability to analyze signals for full pulses. This study proposed a multi-radar cluster-based segmentation network (MRCS-Net) for large time-length full-pulse signals. The network innovatively addresses the processing challenges of prolonged full-pulse signals and effectively achieves the classification and recognition of different pulses under time–frequency overlapping conditions. The proposed algorithm filters the signal with SincNet and then sequentially feeds the sequence into a long short-term memory network. Consequently, the outputs are clustered and segmented using multilayer perceptrons and classifiers. Experiments were conducted on six different types of radar signals. The results demonstrated that the proposed method exhibited lower segmentation error rate metric compared to other similar methods. Moreover, it outperformed other methods in terms of recognition performance.
- 13 March 2024
- Published by Springer Nature in Wireless Networks
- Vol. 30 (4) , 2855-2862
Multi-component signal separation based on ALSAE
- 13 March 2024
- Published by Springer Nature in Wireless Networks
- Vol. 30 (4) , 2855-2862
Multi-component signal separation based on ALSAE
- 8 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 71 (5) , 2879-2883
Single-Channel Radar Signal Separation Based on Instance Segmentation With Mask Optimization
This paper focuses on solving the overlapping problem of multicomponent signals. A single-channel radar signal separation algorithm based on visual separation with mask optimization is proposed. In this method, the reversible time-frequency transform using short-time Fourier is applied to the proposed method to complete time-frequency image pre-processing and time-domain signal reconstruction. Visual separation is achieved using an image instance segmentation network based on the Swin Transformer, FPN, RPN, and RolAlign structures. It can detect and mask individual signals using the same or different radar modulated type. The proposed model is considered a time-frequency domain visualization separation model, which is significantly different from existing deep learning models. To further address the issues of amplitude amplification and attenuation caused by visual separation, a mask optimization network based on convolution and deconvolution structures and its corresponding loss function based on global, local, and hyperlocal features is designed. Simulation experiments show that the proposed algorithm performs well and verify the feasibility of visual separation in radar signal separation.
- 8 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 71 (5) , 2879-2883
Single-Channel Radar Signal Separation Based on Instance Segmentation With Mask Optimization
This paper focuses on solving the overlapping problem of multicomponent signals. A single-channel radar signal separation algorithm based on visual separation with mask optimization is proposed. In this method, the reversible time-frequency transform using short-time Fourier is applied to the proposed method to complete time-frequency image pre-processing and time-domain signal reconstruction. Visual separation is achieved using an image instance segmentation network based on the Swin Transformer, FPN, RPN, and RolAlign structures. It can detect and mask individual signals using the same or different radar modulated type. The proposed model is considered a time-frequency domain visualization separation model, which is significantly different from existing deep learning models. To further address the issues of amplitude amplification and attenuation caused by visual separation, a mask optimization network based on convolution and deconvolution structures and its corresponding loss function based on global, local, and hyperlocal features is designed. Simulation experiments show that the proposed algorithm performs well and verify the feasibility of visual separation in radar signal separation.
- Open Access
- 1 August 2023
- Published by Institution of Engineering and Technology (IET) in IET Radar, Sonar & Navigation
- Vol. 17 (11) , 1626-1638
A novel deinterleaving method for radar pulse trains using pulse descriptor word dot matrix images and cascade‐recurrent loop network
Traditional signal deinterleaving methods depend on preset parameters, use complicated steps and have limitations in handling complex electromagnetic environments where signals overlap in the space, time and frequency domains. This paper presents a novel approach using a deep segmentation network for radar signal deinterleaving. The pulse descriptor word data is transformed into a dot matrix image, which is then processed by a Cascade‐Recurrent Loop Network (CRLN) for segmentation. The CRLN consists of a Type Segmentation Network, an Amount Decision Network and a Recurrent Individual Segmentation Network. By recursively segmenting each target and determining the number of sources, the CRLN overcomes the challenges posed by the discontinuity and high overlap of individuals in the dot matrix image. Experimental results demonstrate the effectiveness of the proposed method, surpassing traditional deinterleaving methods, achieving high accuracy, low omission rate and effectively mitigates the increasing batch problem in complex scenarios. The experiments conducted on a randomly generated dataset yielded impressive results: over 90% accuracy when dealing with pulses from 15 radars of different types, over 96% accuracy when deinterleaving pulses from 4 radar individuals of a same type and over 90% accuracy when handling 5 radars of different types with 10% pulse loss.
- 1 August 2023
- Published by Institution of Engineering and Technology (IET) in IET Radar, Sonar & Navigation
- Vol. 17 (11) , 1626-1638
Open AccessA novel deinterleaving method for radar pulse trains using pulse descriptor word dot matrix images and cascade‐recurrent loop network
Traditional signal deinterleaving methods depend on preset parameters, use complicated steps and have limitations in handling complex electromagnetic environments where signals overlap in the space, time and frequency domains. This paper presents a novel approach using a deep segmentation network for radar signal deinterleaving. The pulse descriptor word data is transformed into a dot matrix image, which is then processed by a Cascade‐Recurrent Loop Network (CRLN) for segmentation. The CRLN consists of a Type Segmentation Network, an Amount Decision Network and a Recurrent Individual Segmentation Network. By recursively segmenting each target and determining the number of sources, the CRLN overcomes the challenges posed by the discontinuity and high overlap of individuals in the dot matrix image. Experimental results demonstrate the effectiveness of the proposed method, surpassing traditional deinterleaving methods, achieving high accuracy, low omission rate and effectively mitigates the increasing batch problem in complex scenarios. The experiments conducted on a randomly generated dataset yielded impressive results: over 90% accuracy when dealing with pulses from 15 radars of different types, over 96% accuracy when deinterleaving pulses from 4 radar individuals of a same type and over 90% accuracy when handling 5 radars of different types with 10% pulse loss.