DiaWhisper-DPO: Role-Attributed Transcription of Clinical Interviews via Failure-Mined Preference Optimization
为了解决临床访谈中自动抑郁症筛查时的发言者角色归属问题，提出了一种端到端模型DiaWhisper-DPO，通过LoRA微调和基于真实解码失败案例的优化方法，显著提高了角色归属准确率。
0 citationsRead paper
Selected work
Representative Papers
Candidate Generation and Definition-Guided Verification for Sentence-Level Depression Symptom Recognition
本文针对抑郁症症状识别中的表达相似性和定义不足问题，提出了一种两阶段框架，通过生成候选症状和基于定义的验证来提高识别准确性。
0 citationsRead paper
Predicting Pseudo-nitzschia harmful algal blooms along the Portuguese Coast using satellite-derived predictors
This study addresses the threat posed by harmful algal blooms (HABs) of Pseudo-nitzschia along the Portuguese coast to shellfish aquaculture and marine ecosystems by developing a spatiotemporal machine learning prediction framework based on satellite remote sensing data. Innovatively, river-informed spatial clustering is employed to delineate ecologically meaningful subregions, and a rigorous spatiotemporal cross-validation strategy—simultaneously excluding entire years and spatial clusters—is implemented to better reflect real-world forecasting conditions. Integrating over a thousand environmental and biological features, including sea surface temperature, upwelling indices, chlorophyll-a, and plankton functional types, the framework leverages Random Forest and Extra-Trees models. In L1–L2 hotspot zones, the models achieve an AUC of 0.74 ± 0.05 using only environmental variables, which improves to 0.77 ± 0.06 upon inclusion of biological variables, demonstrating strong potential for operational early-warning applications.
0 citationsRead paper
Recent publications
Latest Papers
DiaWhisper-DPO: Role-Attributed Transcription of Clinical Interviews via Failure-Mined Preference Optimization
为了解决临床访谈中自动抑郁症筛查时的发言者角色归属问题，提出了一种端到端模型DiaWhisper-DPO，通过LoRA微调和基于真实解码失败案例的优化方法，显著提高了角色归属准确率。
0 citationsRead paper
Candidate Generation and Definition-Guided Verification for Sentence-Level Depression Symptom Recognition
本文针对抑郁症症状识别中的表达相似性和定义不足问题，提出了一种两阶段框架，通过生成候选症状和基于定义的验证来提高识别准确性。
0 citationsRead paper
Predicting Pseudo-nitzschia harmful algal blooms along the Portuguese Coast using satellite-derived predictors
This study addresses the threat posed by harmful algal blooms (HABs) of Pseudo-nitzschia along the Portuguese coast to shellfish aquaculture and marine ecosystems by developing a spatiotemporal machine learning prediction framework based on satellite remote sensing data. Innovatively, river-informed spatial clustering is employed to delineate ecologically meaningful subregions, and a rigorous spatiotemporal cross-validation strategy—simultaneously excluding entire years and spatial clusters—is implemented to better reflect real-world forecasting conditions. Integrating over a thousand environmental and biological features, including sea surface temperature, upwelling indices, chlorophyll-a, and plankton functional types, the framework leverages Random Forest and Extra-Trees models. In L1–L2 hotspot zones, the models achieve an AUC of 0.74 ± 0.05 using only environmental variables, which improves to 0.77 ± 0.06 upon inclusion of biological variables, demonstrating strong potential for operational early-warning applications.
0 citationsRead paper