Zhihao Lin

Mr. Zhihao Lin


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.

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.

5 August 2026 in Algorithms
Verified
Journal Article
Open access
PDF file
CXChen Xie
Chen Xie
MCMingju Chen
Mingju Chen
YWYuyan Wang
Yuyan Wang
MCMingju Chen
Mingju Chen
MCMingju Chen
Mingju Chen
ZLZhihao Lin
Zhihao Lin
Accurate photovoltaic (PV) energy forecasting is vital for grid stability and the global low-carbon transition. However, existing data-driven and channel-independent PV energy forecasting models struggle to capture nonlinear meteorological couplings, heterogeneous physical scales across stations, and high-frequency non-stationary fluctuations. To address these limitations, this study proposes a Physics-Guided Cross-Variable Temporal Transformer architecture. Building upon a channel-independent foundation, we introduce a Cross-Variable Attention mechanism to explicitly reconstruct nonlinear photothermal couplings via dynamic attention weights. To resolve multi-station physical scale discrepancies, a Physical Feature-wise Linear Modulation network utilizes installed capacity as a static prior for adaptive cross-station scale alignment. During optimization, a Time Dynamics-Aware Perceiving Loss jointly penalizes absolute errors and first-order time differences, constraining the network’s tracking ability for transient ramping. Experiments demonstrate that the proposed architecture overcomes traditional channel-isolation limitations. The model achieves a 21.6% reduction in MSE compared to PatchTST, a 44.0% reduction compared to Autoformer, and a 2.7% improvement in R2 over Informer. This provides an accurate, generalizable, and physically interpretable solution for collaborative multi-station distributed PV energy forecasting.