Institution profile

Staffordshire University

Academic institutioneurope · gb
Official website
Research library2linked papers
Opportunities0open roles
Selected work

Representative Papers

A Complete-Data Likelihood for Epidemic Processes on Partially Observed Dynamic Networks

Jul 16, 2026

This study addresses the compounded challenges in inferring epidemic spread on partially observed dynamic contact networks—namely, unknown infection times, incomplete network evolution, measurement errors in contacts, and external sources of infection. The authors propose a unified continuous-time stochastic process framework that jointly models SEIR transmission dynamics, state-dependent network evolution, and a symptom-contact observation mechanism. They derive, for the first time, the complete-data event-history likelihood of the coupled epidemic-network process under partial observability, establishing a theoretical foundation for both likelihood-based and Bayesian inference, and demonstrating that existing models arise as special cases. By integrating data augmentation and probabilistic graphical modeling, the approach simultaneously accounts for latent incubation periods, intermittent observations, contact misreporting, and exogenous infection pressure, revealing how disease progression and contact dynamics jointly govern parameter identifiability.

0 citationsRead paper

XMedFusion: A Knowledge-Guided Multimodal Perception and Reasoning Framework for Autonomous Medical Systems

Jun 08, 2026

This study addresses the limited visual grounding capability of existing end-to-end multimodal models in medical image report generation, which often leads to missed subtle lesions and unreliable diagnostic explanations. To overcome this, the authors propose a modular multi-agent collaborative framework that simulates expert diagnostic reasoning: a visual perception agent extracts image-based evidence, while a knowledge graph construction agent structures clinical findings; these components are integrated with retrieval-augmented and iterative reasoning verification mechanisms. The approach significantly enhances report accuracy, consistency, and interpretability, achieving state-of-the-art results on a public chest X-ray dataset with BLEU-1 of 0.3359 (↑0.2866), ROUGE-L of 0.2440, and METEOR of 0.1708, along with human evaluation scores of 7.80 for consistency and 6.93 for accuracy.

0 citationsRead paper
Recent publications

Latest Papers

A Complete-Data Likelihood for Epidemic Processes on Partially Observed Dynamic Networks

Jul 16, 2026

This study addresses the compounded challenges in inferring epidemic spread on partially observed dynamic contact networks—namely, unknown infection times, incomplete network evolution, measurement errors in contacts, and external sources of infection. The authors propose a unified continuous-time stochastic process framework that jointly models SEIR transmission dynamics, state-dependent network evolution, and a symptom-contact observation mechanism. They derive, for the first time, the complete-data event-history likelihood of the coupled epidemic-network process under partial observability, establishing a theoretical foundation for both likelihood-based and Bayesian inference, and demonstrating that existing models arise as special cases. By integrating data augmentation and probabilistic graphical modeling, the approach simultaneously accounts for latent incubation periods, intermittent observations, contact misreporting, and exogenous infection pressure, revealing how disease progression and contact dynamics jointly govern parameter identifiability.

0 citationsRead paper

XMedFusion: A Knowledge-Guided Multimodal Perception and Reasoning Framework for Autonomous Medical Systems

Jun 08, 2026

This study addresses the limited visual grounding capability of existing end-to-end multimodal models in medical image report generation, which often leads to missed subtle lesions and unreliable diagnostic explanations. To overcome this, the authors propose a modular multi-agent collaborative framework that simulates expert diagnostic reasoning: a visual perception agent extracts image-based evidence, while a knowledge graph construction agent structures clinical findings; these components are integrated with retrieval-augmented and iterative reasoning verification mechanisms. The approach significantly enhances report accuracy, consistency, and interpretability, achieving state-of-the-art results on a public chest X-ray dataset with BLEU-1 of 0.3359 (↑0.2866), ROUGE-L of 0.2440, and METEOR of 0.1708, along with human evaluation scores of 7.80 for consistency and 6.93 for accuracy.

0 citationsRead paper