Senyuan Li

Mr. Senyuan Li

orcid

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
27 July 2025 in Sensors
Verified
Journal Article
Open access
PDF file
XSXiaofei Song
Xiaofei Song
MCMingju Chen
Mingju Chen
JRJie Rao
Jie Rao
MCMingju Chen
Mingju Chen
ZLZhihao Lin
Zhihao Lin
潇胡潇 胡
潇 胡
To improve semantic segmentation performance for complex urban remote sensing images with multi-scale object distribution, class similarity, and small object omission, this paper proposes MFPI-Net, an encoder–decoder-based semantic segmentation network. It includes four core modules: a Swin Transformer backbone encoder, a diverse dilation rates attention shuffle decoder (DDRASD), a multi-scale convolutional feature enhancement module (MCFEM), and a cross-path residual fusion module (CPRFM). The Swin Transformer efficiently extracts multi-level global semantic features through its hierarchical structure and window attention mechanism. The DDRASD’s diverse dilation rates attention (DDRA) block combines convolutions with diverse dilation rates and channel-coordinate attention to enhance multi-scale contextual awareness, while Shuffle Block improves resolution via pixel rearrangement and avoids checkerboard artifacts. The MCFEM enhances local feature modeling through parallel multi-kernel convolutions, forming a complementary relationship with the Swin Transformer’s global perception capability. The CPRFM employs multi-branch convolutions and a residual multiplication–addition fusion mechanism to enhance interactions among multi-source features, thereby improving the recognition of small objects and similar categories. Experiments on the ISPRS Vaihingen and Potsdam datasets show that MFPI-Net outperforms mainstream methods, achieving 82.57% and 88.49% mIoU, validating its superior segmentation performance in urban remote sensing.

25 June 2025 in Electronics
Verified
Journal Article
Open access
PDF file
JWJie Wu
Jie Wu
ZCZhengwei Chang
Zhengwei Chang
LZLinghao Zhang
Linghao Zhang
MCMingju Chen
Mingju Chen
SLSenyuan Li
Senyuan Li
FQFuhong Qiu
Fuhong Qiu
Wind power generation provides clean and renewable electricity for microgrids, but its intermittency and uncertainty pose challenges to the operation and power quality of microgrids. Accurate forecasting is conducive to maintaining the stability of microgrids and improving the efficiency of energy management. Therefore, this study proposes a dual-branch frequency transformer (DBFformer), which leverages multi-scale spectral transformation and the multi-head attention mechanism to improve the prediction accuracy of microgrid wind turbines. In the encoder, two parallel branches are designed to extract the global features and local dynamic features of meteorological data based on Fourier transform and wavelet transform, respectively. In the decoder, an exponential smoothing attention (ESA) mechanism and a frequency attention (FA) mechanism are introduced to extract multi-scale temporal features. ESA enhances the model’s ability to capture long-term growth trends, whereas FA focuses on periodic pattern recognition. Additionally, to further optimize the model’s performance, a periodic weight coefficient (PWC) mechanism is employed to dynamically adjust the fusion coefficients to further improve the fusion performance and prediction accuracy. The factors influencing wind turbine power are analyzed; then, the most relevant factors are selected for the experiment. According to the experimental results, the proposed DBFformer accurately predicts the output power of wind turbines and exhibits superior performance. It achieves lower mean squared error (MSE) and mean absolute error (MAE) values than other state-of-the-art models. Specifically, its MSE values are 0.195, 0.216, 0.457, and 0.583, and the corresponding MAE values are 0.318, 0.335, 0.474, and 0.503 for different rated wind turbines. Furthermore, comprehensive ablation experiments validate that the dual-branch structure, frequency transformations, dual-attention mechanisms, and PWC module have a positive impact on the proposed model. Therefore, this research offers a novel and effective approach for wind power forecasting and supports the broader goal of integrating clean energy into microgrids.

14 August 2025 in Sensors
Verified
Journal Article
Open access
PDF file
潇胡潇 胡
潇 胡
MCMingju Chen
Mingju Chen
XZXingyue Zhang
Xingyue Zhang
JRJie Rao
Jie Rao
SLSenyuan Li
Senyuan Li
XSXiaofei Song
Xiaofei Song
In order to solve the problems of modulation signals in low signal-to-noise ratio (SNR), such as poor feature extraction ability, strong dependence on single modal data, and insufficient recognition accuracy, this paper proposes a multi-dimensional feature MFCA-transformer recognition network that integrates phase, frequency and power information. The network uses Triple Dynamic Feature Fusion (TDFF) to fuse constellation, time-frequency, and power spectrum features through the adaptive dynamic mechanism to improve the quality of feature fusion. A Channel Prior Convolutional Attention (CPCA) module is introduced to solve the problem of insufficient information interaction between different channels in multi-dimensional feature recognition tasks, promote information transmission between various feature channels, and enhance the recognition ability of the model for complex features. The label smoothing technique is added to the loss function to reduce the overfitting of the model to the specific label and improve the generalization ability of the model by adjusting the distribution of the real label. Experiments show that the recognition accuracy of the proposed method is significantly improved on the public datasets, at high signal-to-noise ratios, the recognition accuracy can reach 93.2%, which is 3% to 14% higher than those of the existing deep learning recognition methods.

19 June 2025 in Measurement Science and Technology
Verified
Journal Article
Closed access
SLSenyuan Li
Senyuan Li
MCMingju Chen
Mingju Chen
MYMei Yang
Mei Yang
XZXingyue Zhang
Xingyue Zhang
JRJie Rao
Jie Rao
XHXiao Hu
Xiao Hu
Parkinson’s disease (PD) is characterized by distinct gait abnormalities that serve as key indicators for diagnosis and treatment monitoring. In this study, we present a dual-task deep learning framework that integrates optimal gait feature extraction with accurate prediction of the Hoehn–Yahr (H&Y) staging of PD patients. Our approach begins with the extraction of three-dimensional (3D) gait features, which capture the comprehensive spatial and temporal dynamics of patient movement. These 3D features are then refined through a variational autoencoder with single encoder and multiple decoders (VA-SEMD), which synergistically combines convolutional neural networks and a hybrid attention mechanism inspired by Transformers. This model automatically extracts essential gait features that correlate strongly with demographic indicators. The selected features are subsequently processed by a multi-branch attention-enhanced multi-layer perceptron (MB-AMLP) that employs multi-branch convolutional feature extraction and an attention-enhanced fusion module to significantly improve staging accuracy. Experimental results indicate that the VA-SEMD model achieves superior performance compared to commonly used feature selection approaches, while the MB-AMLP model achieves superior performance in H&Y staging prediction, recording an F1 score of 91.28%, an accuracy of 92.83%, and a Cohen’s Kappa of 0.88. Overall, our framework underscores the immense potential of deep learning technologies in the intelligent diagnosis and clinical management of PD.

11 April 2026 in Measurement Science and Technology
Verified
Journal Article
Closed access
SLSenyuan Li
Senyuan Li
MYMei Yang
Mei Yang
XZXingyue Zhang
Xingyue Zhang
MCMingju Chen
Mingju Chen
YWYilin Wang
Yilin Wang
ZLZhihao Lin
Zhihao Lin
The early diagnosis and precise staging of disease severity in Parkinson's disease (PD) represent significant challenges in current clinical practice, primarily limited by the subjectivity and instability of traditional assessment methods. In recent years, deep learning methods based on multimodal neuroimaging have offered a new avenue for objective and automated assessment; however, they still face key bottlenecks such as inefficient fusion of heterogeneous modalities and insufficient clinical plausibility of the models. To address these limitations, this study proposes an innovative two-stage multimodal deep learning framework, DM-PAFNet, which integrates a dual-branch multi-modal classification network (DB-MCNet) and a medical prior-guided attention fusion network (MP-AFNet). The framework is centered on a progressive strategy of "diagnosis for pre-training, staging for fine-tuning," modeling PD assessment as a hierarchical knowledge transfer process. In the first stage, we construct the DB-MCNet, which introduces a dual-stream adaptive fusion (DSAF) module to efficiently integrate information from T1-weighted imaging (T1-MRI) and diffusion tensor imaging (DTI). This stage achieves high-precision PD diagnosis and yields an image feature encoder with strong generalization capabilities. In the second stage, we propose the MP-AFNet. Building upon the inherited pre-trained weights, it utilizes a gated cross-modal attention (GCA) module to fuse imaging features with clinical variables. Furthermore, it innovatively introduces a medically-informed constraint (MIC) module, which embeds clinical knowledge as a soft constraint during training to enhance the credibility and stability of the staging predictions. Experimental results on the public PPMI dataset demonstrate the outstanding performance of our framework. The first-stage DB-MCNet achieved an accuracy of 95.85% in the PD vs. healthy control classification task, with the learned imaging encoder subsequently transferred to initialize the second stage. In the more challenging Hoehn and Yahr (H&Y) staging prediction across 410 subjects (H&Y stages 0–3), the complete framework achieved an accuracy of 88.3%, significantly outperforming several mainstream baseline methods. In conclusion, by virtue of its two-stage structural design, efficient multimodal fusion mechanisms, and clinical prior-guided strategy, the DM-PAFNet provides an accurate, objective, and clinically interpretable solution for the automated diagnosis and fine-grained staging of PD.

8 May 2026 in Sensors
Verified
Journal Article
Open access
PDF file
MCMingju Chen
Mingju Chen
ZLZhihao Lin
Zhihao Lin
XSXiaofei Song
Xiaofei Song
MCMingju Chen
Mingju Chen
MCMingju Chen
Mingju Chen
CXChen Xie
Chen Xie
The rapid evolution of diffusion models has shifted visual synthesis from text-only inputs to precisely controlled generation driven by multi-source heterogeneous sensor signals (e.g., audio, 3D, and physiological data). This paper presents a systematic review of cross-modal mapping and controllable generation under multi-source collaboration. More precisely, we propose a unified “cross-modal mapping and injection” taxonomy by abstracting the intervention logic of heterogeneous signals. Fundamentally, we analyze these mechanisms in a backbone-agnostic manner, delineating the architectural transition from legacy U-Net dependencies to scalable architectures like Diffusion Transformers (DiTs) and tracing the technical evolution from single-source atomic driving to complex multi-source collaborative paradigms. Our mechanistic analysis reveals that seamless feature fusion heavily relies on gradient conflict resolution, rigorous arbitration, and dynamic disentanglement under multi-constraint scenarios. Furthermore, by systematizing current evaluation metrics, we identify intrinsic quality-controllability trade-offs through performance game analysis (e.g., Pareto optimization), yielding a scientifically grounded technical selection guide. The study concludes that overcoming current generation limitations necessitates integrating Hardware-in-the-Loop (HIL) deployment, PDE-driven physical constraints, and causal inference, laying the foundation for next-generation robust and real-time generative models.