Tongsheng Shen

Dr. Tongsheng Shen


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
WWWenbo Wang
Wenbo Wang
LYLi Ye
Li Ye
TSTongsheng Shen
Tongsheng Shen
DZDeXin Zhao
DeXin Zhao
This paper proposes an underwater-acoustic class-incremental few-shot learning (UACIL) method for streaming data processing in practical underwater-acoustic target recognition scenarios. The core objective is to expand classification capabilities for new classes while mitigating catastrophic forgetting of existing knowledge. UACIL’s contributions encompass three key components: First, to enhance feature discriminability and generalization, an enhanced frequency-domain attention module is introduced to capture both spatial and temporal variation features. Second, it introduces a prototype classification mechanism with two operating modes corresponding to the base-training phase and the incremental training phase. In the base phase, sufficient pre-training is performed on the feature extraction network and the classification heads of inherent categories. In the incremental phase, for streaming data processing, only the classification heads of new categories are expanded and updated, while the parameters of the feature extractor remain stable through prototype classification. Third, a joint optimization strategy using multiple loss functions is designed to refine feature distribution. This method enables rapid deployment without complex cross-domain retraining when handling new data classes, effectively addressing overfitting and catastrophic forgetting in hydroacoustic signal classification. Experimental results with public datasets validate its superior incremental learning performance. The proposed method achieves 92.89% base recognition accuracy and maintains 68.44% overall accuracy after six increments. Compared with baseline methods, it improves base accuracy by 11.14% and reduces the incremental performance-dropping rate by 50.09%. These results demonstrate that UACIL enhances recognition accuracy while alleviating catastrophic forgetting, confirming its feasibility for practical applications.

Verified
Journal Article
Open access
PDF file
WWWenbo Wang
Wenbo Wang
LYLi Ye
Li Ye
LMLuwen Meng
Luwen Meng
TSTongsheng Shen
Tongsheng Shen
DZDeXin Zhao
DeXin Zhao
In order to solve the problem of mainlobe interference in small hydroacoustic array signal processing, this paper proposes a beamforming method based on the high-resolution direction of arrival (DOA) estimation and interference coherence matrix (ICM) reconstruction. The DOA estimation is first performed using an improved sparse iterative covariance-based (SPICE) method, unaffected by the coherent signal, and it can provide highly accurate DOA estimation for multiple targets. The fitted signal energy distribution obtained from the SPICE is then utilized for the reconstruction of the signal coherence matrix. The reconstructed ICM matrix is used to construct a blocking masking matrix and an eigen-projection matrix to suppress the mainlobe interference signal. Compared with existing methods, the method in this paper possesses better mainlobe interference suppression ability. Within the mainlobe interference interval angle of 3° to 13.5° from the signal of interest (SOI) based on eight-element uniform linear arrays, the method in this paper can enhance the signal-to-interference ratio (SIR) by about 15.59 dB on average compared with the interference-free suppression of conventional beamforming (CBF) and outperforms the other interference suppression methods simultaneously. Simulations and experiments demonstrate the effectiveness of this method in mainlobe interference scenarios.

23 October 2025 in Materials
Verified
Journal Article
Open access
PDF file
CZChao Zhang
Chao Zhang
CZChunrong Zou
Chunrong Zou
SGShaojun Guo
Shaojun Guo
YZYanwen Zhao
Yanwen Zhao
TSTongsheng Shen
Tongsheng Shen
Electromagnetic (EM) metamaterials have a wide range of applications due to their unique properties, but their design is often based on specific topological structures, which come with certain limitations. Designing with stochastic topologies can provide more diverse EM properties. However, this requires experienced designers to search and optimise in a vast design space, which is time-consuming and requires substantial computational resources. In this paper, we employ a deep learning network agent model to replace time-consuming full-wave simulations and quickly establish the mapping relationship between the metamaterial structure and its electromagnetic response. The proposed framework integrates a Convolutional Block Attention Module-enhanced Variational Autoencoder (CBAM-VAE) with a Transformer-based predictor. Incorporating CBAM into the VAE architecture significantly enhances the model’s capacity to extract and reconstruct critical structural features of metamaterials. The Transformer predictor utilises an encoder-only configuration that leverages the sequential data characteristics, enabling accurate prediction of electromagnetic responses from latent variables while significantly enhancing computational efficiency. The dataset is randomly generated based on the filling rate of unit cells, requiring only a small fraction of samples compared to the full design space for training. We employ the trained model for the inverse design of metamaterials, enabling the rapid generation of two cells for 1-bit coding metamaterials. Compared to a similarly sized metallic plate, the designed coding metamaterial radar cross-section (RCS) reduces by over 10 dB from 6 to 18 GHz. Simulation and experimental measurement results validate the reliability of this design approach, providing a novel perspective for the design of EM metamaterials.