Selected work

Representative Papers

Physically Aware Radiomics Without Interpolation: Disentangling Voxel Geometry and Signal Modification in CT and MRI

Jul 14, 2026

This study addresses the instability of conventional radiomics features in anisotropic CT/MRI images, which arises from conflating voxel geometry with signal alterations introduced by interpolation. To resolve this issue, the authors propose a voxel-spacing-aware radiomics framework that explicitly models the physical geometry of vox日晚间 through metadata, thereby decoupling intrinsic geometric structure from interpolation-induced distortions—all without image resampling or alteration of the original signal. Implemented within PyRadiomics, four configurations (NR, RS, VS, FK) were evaluated for robustness using intraclass correlation coefficients (ICC), Friedman tests, feature selection, and multilayer perceptron performance. Results demonstrate that the proposed VS method achieves near-perfect agreement with non-resampled baseline features in both CT and MRI (ICC > 0.997), delivers comparable predictive performance, and effectively circumvents resampling-related biases.

0 citationsRead paper

Hacia una moderna "republica de las ideas" via un nuevo ecosistema de comunicacion cientifica (Toward a modern "Republic of Ideas" via a new Ecosystem of Scientific Communication)

Dec 04, 2025

Contemporary scholarly communication faces a systemic crisis: the Enlightenment ideal of open knowledge sharing has been eroded by instrumentalized, centralized publishing regimes. This paper proposes a novel scientific communication framework integrating ordoliberalism, humanistic economics, digital humanities, and decentralized science (DeSci)—the first systematic synthesis of these four paradigms. Grounded in human flourishing as its normative aim, power-balanced governance as its institutional mechanism, and techno-ethical alignment (“technology for good”) as its moral foundation, the framework leverages smart contracts, DAOs, token-based incentives, verifiable digital identities, and an open academic protocol stack to deliver end-to-end design—from theoretical modeling and architectural specification to mechanism validation and phased transition. Its principal contribution is the first decentralized scholarly communication “New Charter” that simultaneously satisfies philosophical legitimacy, institutional robustness, and technical implementability—offering a pragmatic, sovereignty-preserving roadmap toward academic self-governance, equitable incentive structures, and censorship-resistant collaboration.

0 citationsRead paper

Procedimiento de auditor'ia de ciberseguridad para sistemas aut'onomos: metodolog'ia, amenazas y mitigaciones

Nov 07, 2025

The widespread deployment of autonomous systems in industrial, medical, logistics, and domestic settings has significantly expanded their cyberattack surface, necessitating systematic security assessment methodologies tailored to highly complex human-robot interaction systems. This paper proposes the first hierarchical security auditing framework for autonomous systems, integrating a robot-specific threat taxonomy with actionable mitigation strategies to enable cross-platform, operationally realistic evaluations. Its contributions are threefold: (1) it establishes the first layered auditing process specifically designed for autonomous systems; (2) it introduces a fine-grained threat classification model grounded in robotic architecture and runtime context; and (3) it unifies vulnerability analysis with mitigation mechanisms, empirically validated on four representative platforms—Vision 60, A1, UR3, and Pepper. Results demonstrate that the framework effectively identifies critical vulnerabilities and delivers adaptable, implementation-ready security hardening recommendations.

0 citationsRead paper

Cumplimiento del Reglamento (UE) 2024/1689 en robótica y sistemas autónomos: una revisión sistemática de la literatura

Sep 04, 2025

This study addresses critical compliance gaps of autonomous robotic systems under the EU AI Act (Regulation 2024/1689), specifically concerning deficiencies in explainability, absence of real-time human oversight, and non-auditable knowledge bases within cybersecurity frameworks. Following the PRISMA protocol, we systematically reviewed 243 studies from IEEE Xplore, ACM Digital Library, Scopus, and Web of Science, ultimately selecting 22 for in-depth analysis. Quantitative evaluation revealed that only 40% of existing approaches satisfy transparency requirements, and merely 30% incorporate robust fault intervention mechanisms. To bridge these gaps, we propose a modular compliance framework integrating dynamic risk management, real-time human-in-the-loop supervision, and continuous auditability. Crucially, transparency and fault intervention are systematically embedded into the architectural design—not treated as post-hoc add-ons. The framework provides both a methodological foundation and an engineering pathway for implementing the EU AI Act in high-autonomy operational contexts.

0 citationsRead paper

Predicting fall risk in older adults: A machine learning comparison of accelerometric and non-accelerometric factors

Aug 04, 2025

This study addresses the limited accuracy of existing fall-risk prediction models for older adults by proposing a novel multimodal assessment framework that integrates motion data (accelerometry) with non-motor clinical features (e.g., age, comorbidities). Using multimodal data from 146 older adults, we systematically evaluated multiple machine learning models and identified Bayesian ridge regression as the top-performing method when leveraging fused data (MSE = 0.6746; R² = 0.9941), significantly outperforming unimodal baselines. Our key contributions are twofold: (1) We provide the first empirical validation that non-motor factors contribute independently and substantially to fall-risk prediction—beyond motion-derived metrics alone; and (2) we establish an interpretable, clinically actionable assessment paradigm grounded in “multisource data fusion + Bayesian modeling,” enabling precise, quantifiable risk estimation to support early clinical intervention.

0 citationsRead paper

Recent publications

Latest Papers

Physically Aware Radiomics Without Interpolation: Disentangling Voxel Geometry and Signal Modification in CT and MRI

Jul 14, 2026

This study addresses the instability of conventional radiomics features in anisotropic CT/MRI images, which arises from conflating voxel geometry with signal alterations introduced by interpolation. To resolve this issue, the authors propose a voxel-spacing-aware radiomics framework that explicitly models the physical geometry of vox日晚间 through metadata, thereby decoupling intrinsic geometric structure from interpolation-induced distortions—all without image resampling or alteration of the original signal. Implemented within PyRadiomics, four configurations (NR, RS, VS, FK) were evaluated for robustness using intraclass correlation coefficients (ICC), Friedman tests, feature selection, and multilayer perceptron performance. Results demonstrate that the proposed VS method achieves near-perfect agreement with non-resampled baseline features in both CT and MRI (ICC > 0.997), delivers comparable predictive performance, and effectively circumvents resampling-related biases.

0 citationsRead paper

Hacia una moderna "republica de las ideas" via un nuevo ecosistema de comunicacion cientifica (Toward a modern "Republic of Ideas" via a new Ecosystem of Scientific Communication)

Dec 04, 2025

Contemporary scholarly communication faces a systemic crisis: the Enlightenment ideal of open knowledge sharing has been eroded by instrumentalized, centralized publishing regimes. This paper proposes a novel scientific communication framework integrating ordoliberalism, humanistic economics, digital humanities, and decentralized science (DeSci)—the first systematic synthesis of these four paradigms. Grounded in human flourishing as its normative aim, power-balanced governance as its institutional mechanism, and techno-ethical alignment (“technology for good”) as its moral foundation, the framework leverages smart contracts, DAOs, token-based incentives, verifiable digital identities, and an open academic protocol stack to deliver end-to-end design—from theoretical modeling and architectural specification to mechanism validation and phased transition. Its principal contribution is the first decentralized scholarly communication “New Charter” that simultaneously satisfies philosophical legitimacy, institutional robustness, and technical implementability—offering a pragmatic, sovereignty-preserving roadmap toward academic self-governance, equitable incentive structures, and censorship-resistant collaboration.

0 citationsRead paper

Procedimiento de auditor'ia de ciberseguridad para sistemas aut'onomos: metodolog'ia, amenazas y mitigaciones

Nov 07, 2025

The widespread deployment of autonomous systems in industrial, medical, logistics, and domestic settings has significantly expanded their cyberattack surface, necessitating systematic security assessment methodologies tailored to highly complex human-robot interaction systems. This paper proposes the first hierarchical security auditing framework for autonomous systems, integrating a robot-specific threat taxonomy with actionable mitigation strategies to enable cross-platform, operationally realistic evaluations. Its contributions are threefold: (1) it establishes the first layered auditing process specifically designed for autonomous systems; (2) it introduces a fine-grained threat classification model grounded in robotic architecture and runtime context; and (3) it unifies vulnerability analysis with mitigation mechanisms, empirically validated on four representative platforms—Vision 60, A1, UR3, and Pepper. Results demonstrate that the framework effectively identifies critical vulnerabilities and delivers adaptable, implementation-ready security hardening recommendations.

0 citationsRead paper

Cumplimiento del Reglamento (UE) 2024/1689 en robótica y sistemas autónomos: una revisión sistemática de la literatura

Sep 04, 2025

This study addresses critical compliance gaps of autonomous robotic systems under the EU AI Act (Regulation 2024/1689), specifically concerning deficiencies in explainability, absence of real-time human oversight, and non-auditable knowledge bases within cybersecurity frameworks. Following the PRISMA protocol, we systematically reviewed 243 studies from IEEE Xplore, ACM Digital Library, Scopus, and Web of Science, ultimately selecting 22 for in-depth analysis. Quantitative evaluation revealed that only 40% of existing approaches satisfy transparency requirements, and merely 30% incorporate robust fault intervention mechanisms. To bridge these gaps, we propose a modular compliance framework integrating dynamic risk management, real-time human-in-the-loop supervision, and continuous auditability. Crucially, transparency and fault intervention are systematically embedded into the architectural design—not treated as post-hoc add-ons. The framework provides both a methodological foundation and an engineering pathway for implementing the EU AI Act in high-autonomy operational contexts.

0 citationsRead paper

Predicting fall risk in older adults: A machine learning comparison of accelerometric and non-accelerometric factors

Aug 04, 2025

This study addresses the limited accuracy of existing fall-risk prediction models for older adults by proposing a novel multimodal assessment framework that integrates motion data (accelerometry) with non-motor clinical features (e.g., age, comorbidities). Using multimodal data from 146 older adults, we systematically evaluated multiple machine learning models and identified Bayesian ridge regression as the top-performing method when leveraging fused data (MSE = 0.6746; R² = 0.9941), significantly outperforming unimodal baselines. Our key contributions are twofold: (1) We provide the first empirical validation that non-motor factors contribute independently and substantially to fall-risk prediction—beyond motion-derived metrics alone; and (2) we establish an interpretable, clinically actionable assessment paradigm grounded in “multisource data fusion + Bayesian modeling,” enabling precise, quantifiable risk estimation to support early clinical intervention.

0 citationsRead paper