Selected work

Representative Papers

Ensemble of Radiomics and Convnext for Breast Cancer Diagnosis

Jun 18, 20252025 IEEE 38th International Symposium on Computer-Based Medical Systems (CBMS)

This study proposes an integrated approach combining radiomics and the ConvNeXt deep learning model to improve the accuracy of early breast cancer diagnosis from mammographic images. The method uniquely integrates radiomic features with the ConvNeXtV1-small architecture and incorporates a prediction calibration strategy, achieving robust cross-dataset performance on two independent cohorts—RSNA and TecSalud. Experimental results demonstrate that the ensemble model attains an AUC of 0.87 on testing data, significantly outperforming standalone ConvNeXt (AUC: 0.83) and radiomics-based models (AUC: 0.80). These findings underscore the efficacy and generalizability of multimodal fusion in enhancing breast cancer screening.

1 citationsRead paper

Per-Aetiology Contrastive Severity Embeddings with Phonological Pseudo-Labelling for Multilingual Dysarthric Speech

Sep 18, 2026

研究通过针对不同病因（脑瘫、帕金森病、肌萎缩侧索硬化）的对比嵌入模型及语音学伪标签方法，提高了多语言构音障碍严重程度评估系统的性能。

0 citationsRead paper

Toward a Decision-Assurance Layer for AI-Assisted Flight Planning in Air Traffic Management

Sep 11, 2026

本文提出AI信任与保证层（ATAL），通过评估AI生成的飞行计划输出的可靠性，解决航空交通管理中AI辅助决策的安全性和操作风险问题。

0 citationsRead paper

LUX: A Lesion-Aware Graph-Conditioned Visual - Language Architecture for Explainable Endoscopic Captioning

Aug 24, 2026

为解决内镜图像解读中病理证据局部化和关系性被忽略的问题，提出LUX架构，通过构建病变中心场景图并结合T5解码器实现可解释的图像描述。

0 citationsRead paper

Strategic Technical Debt: A Real Options Approach to Early-Stage Software Experimentation

Aug 17, 2026

This study addresses the challenge of rationally quantifying early-stage technical debt by reframing it as a real option. Leveraging finite-horizon dynamic programming and risk-neutral valuation, we propose the strategic debt boundary, shadow price, and refactoring pivot theorem. The research establishes a falsifiable model for predicting refactoring bursts, quantifies debt overhang thresholds, and empirically validates the impact of salvage value on strategy through preregistered analysis. By elucidating rational pricing mechanisms and optimal repayment timing under high uncertainty, this work facilitates a cognitive paradigm shift from viewing technical debt as an engineering pathology to recognizing it as a strategic financial instrument.

0 citationsRead paper

Recent publications

Latest Papers

Per-Aetiology Contrastive Severity Embeddings with Phonological Pseudo-Labelling for Multilingual Dysarthric Speech

Sep 18, 2026

研究通过针对不同病因（脑瘫、帕金森病、肌萎缩侧索硬化）的对比嵌入模型及语音学伪标签方法，提高了多语言构音障碍严重程度评估系统的性能。

0 citationsRead paper

Toward a Decision-Assurance Layer for AI-Assisted Flight Planning in Air Traffic Management

Sep 11, 2026

本文提出AI信任与保证层（ATAL），通过评估AI生成的飞行计划输出的可靠性，解决航空交通管理中AI辅助决策的安全性和操作风险问题。

0 citationsRead paper

LUX: A Lesion-Aware Graph-Conditioned Visual - Language Architecture for Explainable Endoscopic Captioning

Aug 24, 2026

为解决内镜图像解读中病理证据局部化和关系性被忽略的问题，提出LUX架构，通过构建病变中心场景图并结合T5解码器实现可解释的图像描述。

0 citationsRead paper

Strategic Technical Debt: A Real Options Approach to Early-Stage Software Experimentation

Aug 17, 2026

This study addresses the challenge of rationally quantifying early-stage technical debt by reframing it as a real option. Leveraging finite-horizon dynamic programming and risk-neutral valuation, we propose the strategic debt boundary, shadow price, and refactoring pivot theorem. The research establishes a falsifiable model for predicting refactoring bursts, quantifies debt overhang thresholds, and empirically validates the impact of salvage value on strategy through preregistered analysis. By elucidating rational pricing mechanisms and optimal repayment timing under high uncertainty, this work facilitates a cognitive paradigm shift from viewing technical debt as an engineering pathology to recognizing it as a strategic financial instrument.

0 citationsRead paper

Prompt engineering using order-of-addition experiments: An application to generating two-level fractional factorial designs

Jul 06, 2026

This study addresses the pronounced sensitivity of large language models (LLMs) to prompt phrasing order when generating two-level fractional factorial designs, demonstrating that the sequence of phrases in a prompt significantly affects output quality. To tackle this issue, the authors introduce, for the first time, a sequential addition experimental design framework into prompt engineering. This approach systematically quantifies the ordering effects of individual prompt components and automatically identifies the optimal prompt configuration. The proposed method not only elucidates the underlying mechanisms by which LLMs respond to structural variations in prompts but also substantially enhances both the performance and stability of LLMs in statistical experimental design tasks.

0 citationsRead paper