Selected work

Representative Papers

Explainability in Generative Medical Diffusion Models: A Faithfulness-Based Analysis on MRI Synthesis

Feb 10, 2026

This study addresses the opacity of decision-making in generative diffusion models for medical MRI synthesis by introducing fidelity evaluation into the interpretability analysis of such models. The work proposes a novel interpretable framework that integrates denoising trajectories with prototype-based networks—including ProtoPNet, EPPNet, and ProtoPool—to elucidate the model’s underlying reasoning mechanisms. Experimental results demonstrate that the proposed approach, particularly when instantiated with EPPNet, achieves a fidelity score of 0.1534, significantly outperforming baseline methods. This advancement provides more reliable and transparent explanations of the generative process, thereby enhancing the safety and trustworthiness of medical AI systems.

0 citationsRead paper

MI CAM: Mutual Information Weighted Activation Mapping for Causal Visual Explanations of Convolutional Neural Networks

Jul 11, 2025

Convolutional neural networks (CNNs) lack causal interpretability in safety-critical domains such as healthcare and energy. Method: We propose MI-CAM, a mutual information-weighted class activation mapping method that dynamically fuses multi-layer feature maps by quantifying mutual information between feature maps and input images, generating causally plausible saliency maps; causal validity is further verified via counterfactual analysis. Contribution/Results: Unlike existing attribution methods, MI-CAM requires no additional training and operates as a post-hoc, computationally efficient, and theoretically grounded framework. On multiple benchmark datasets, MI-CAM yields qualitatively more human-aligned visualizations and achieves statistically significant improvements in quantitative faithfulness metrics—including Insertion AUC, Deletion AUC, and Faithfulness—outperforming Grad-CAM, Score-CAM, and other state-of-the-art approaches. Notably, it demonstrates superior bias mitigation and decision transparency in fine-grained classification tasks.

0 citationsRead paper

Modeling of Vertical Distribution of Suspended Sediment Concentration in Open Channel Turbulent Flows Using Fractional Differential Entropy

Jul 08, 2025

Modeling the vertical suspended sediment concentration profile in open-channel turbulent flows faces challenges of high computational complexity and insufficient accuracy. Method: This paper proposes a novel probabilistic modeling framework based on continuous-domain fractional-order differential entropy (FDE). Treating the dimensionless concentration as a random variable, it employs Ubriaco’s fractional entropy theory to derive a compact, physically interpretable distribution model. The approach integrates regression analysis with multi-source experimental and field-measured data for validation and rigorously assesses robustness via systematic error analysis. Results: The proposed model achieves significantly higher fitting accuracy than conventional deterministic and probabilistic models across diverse hydraulic and sediment conditions, reduces computational cost by over 40%, and demonstrates superior accuracy, stability, and broad applicability—establishing a generalizable, efficient paradigm for simulating sediment transport in open channels.

0 citationsRead paper

Recent publications

Latest Papers

Explainability in Generative Medical Diffusion Models: A Faithfulness-Based Analysis on MRI Synthesis

Feb 10, 2026

This study addresses the opacity of decision-making in generative diffusion models for medical MRI synthesis by introducing fidelity evaluation into the interpretability analysis of such models. The work proposes a novel interpretable framework that integrates denoising trajectories with prototype-based networks—including ProtoPNet, EPPNet, and ProtoPool—to elucidate the model’s underlying reasoning mechanisms. Experimental results demonstrate that the proposed approach, particularly when instantiated with EPPNet, achieves a fidelity score of 0.1534, significantly outperforming baseline methods. This advancement provides more reliable and transparent explanations of the generative process, thereby enhancing the safety and trustworthiness of medical AI systems.

0 citationsRead paper

MI CAM: Mutual Information Weighted Activation Mapping for Causal Visual Explanations of Convolutional Neural Networks

Jul 11, 2025

Convolutional neural networks (CNNs) lack causal interpretability in safety-critical domains such as healthcare and energy. Method: We propose MI-CAM, a mutual information-weighted class activation mapping method that dynamically fuses multi-layer feature maps by quantifying mutual information between feature maps and input images, generating causally plausible saliency maps; causal validity is further verified via counterfactual analysis. Contribution/Results: Unlike existing attribution methods, MI-CAM requires no additional training and operates as a post-hoc, computationally efficient, and theoretically grounded framework. On multiple benchmark datasets, MI-CAM yields qualitatively more human-aligned visualizations and achieves statistically significant improvements in quantitative faithfulness metrics—including Insertion AUC, Deletion AUC, and Faithfulness—outperforming Grad-CAM, Score-CAM, and other state-of-the-art approaches. Notably, it demonstrates superior bias mitigation and decision transparency in fine-grained classification tasks.

0 citationsRead paper

Modeling of Vertical Distribution of Suspended Sediment Concentration in Open Channel Turbulent Flows Using Fractional Differential Entropy

Jul 08, 2025

Modeling the vertical suspended sediment concentration profile in open-channel turbulent flows faces challenges of high computational complexity and insufficient accuracy. Method: This paper proposes a novel probabilistic modeling framework based on continuous-domain fractional-order differential entropy (FDE). Treating the dimensionless concentration as a random variable, it employs Ubriaco’s fractional entropy theory to derive a compact, physically interpretable distribution model. The approach integrates regression analysis with multi-source experimental and field-measured data for validation and rigorously assesses robustness via systematic error analysis. Results: The proposed model achieves significantly higher fitting accuracy than conventional deterministic and probabilistic models across diverse hydraulic and sediment conditions, reduces computational cost by over 40%, and demonstrates superior accuracy, stability, and broad applicability—establishing a generalizable, efficient paradigm for simulating sediment transport in open channels.

0 citationsRead paper