Selected work

Representative Papers

SepsisAI Orchestrator: A Containerized and Scalable Platform for Deploying AI Models and Real-Time Monitoring in Early Sepsis Detection

May 21, 2026

This study addresses key barriers to deploying clinical AI models—namely data heterogeneity, lack of deployment standardization, and stringent hospital requirements for high concurrency and low latency. The authors propose an open-source, modular platform integrating FHIR-inspired CDA preprocessing, NoSQL storage, containerized LightGBM model serving, and a Streamlit-based clinical dashboard, with scalable orchestration via Docker and Kubernetes. For the first time, they quantitatively demonstrate a U-shaped scaling behavior under clinical AI inference workloads: on a 12-thread CPU, increasing service replicas from 3 to 12 reduces p95 latency by 57.3% (from 3.3 s to 1.41 s) and eliminates request failures, whereas further scaling degrades performance due to scheduling contention. This work delivers an end-to-end, reproducible architecture for high-performance clinical AI deployment.

0 citationsRead paper

Technical knowledge and soft skills in software startups within the Colombian entrepreneurial ecosystem

Nov 25, 2025

This study investigates the dynamic evolution of technical and soft skill requirements within founding teams of Colombian software startups during their early-stage development. Employing a survey-based methodology administered to active startup teams, it systematically analyzes the shifting importance of technical competencies—including requirements engineering, agile development, project management, and marketing—as well as soft skills such as communication, leadership, and teamwork. Results indicate that requirements engineering, agile methodologies, budget management, and communication/leadership consistently rank among the most critical capabilities; however, their relative importance undergoes significant shifts across distinct growth stages. This research provides the first empirical characterization of stage-dependent competency evolution in Latin American software startups. Its findings offer evidence-based guidance for entrepreneurial capability development, incubator curriculum design, and public policy formulation in entrepreneurship education—particularly within emerging markets.

0 citationsRead paper

An extension of Priestley duality to fuzzy topologies and positive MV-algebras

Aug 26, 2025

The absence of a unified categorical duality framework for many-valued logic and fuzzy structures hinders systematic connections between fuzzy topology and algebraic semantics. Method: This work systematically extends Priestley duality to the categories of fuzzy topological spaces and positive MV-algebras, integrating category theory, fuzzy topology, MV-algebra theory, and limit-truncation completeness techniques to establish a rigorous dual equivalence. Contribution/Results: The resulting duality unifies and generalizes both classical Priestley duality and Stone duality, transcending the limitations of binary logic. It constitutes the first Stone-type duality for fuzzy topology and many-valued logic grounded in ordered algebraic structures—specifically, positive MV-algebras. By doing so, it significantly broadens the applicability and expressive power of duality methods in non-classical logics, providing a foundational framework for further developments in fuzzy semantics, algebraic logic, and categorical model theory.

0 citationsRead paper

Recent publications

Latest Papers

SepsisAI Orchestrator: A Containerized and Scalable Platform for Deploying AI Models and Real-Time Monitoring in Early Sepsis Detection

May 21, 2026

This study addresses key barriers to deploying clinical AI models—namely data heterogeneity, lack of deployment standardization, and stringent hospital requirements for high concurrency and low latency. The authors propose an open-source, modular platform integrating FHIR-inspired CDA preprocessing, NoSQL storage, containerized LightGBM model serving, and a Streamlit-based clinical dashboard, with scalable orchestration via Docker and Kubernetes. For the first time, they quantitatively demonstrate a U-shaped scaling behavior under clinical AI inference workloads: on a 12-thread CPU, increasing service replicas from 3 to 12 reduces p95 latency by 57.3% (from 3.3 s to 1.41 s) and eliminates request failures, whereas further scaling degrades performance due to scheduling contention. This work delivers an end-to-end, reproducible architecture for high-performance clinical AI deployment.

0 citationsRead paper

Technical knowledge and soft skills in software startups within the Colombian entrepreneurial ecosystem

Nov 25, 2025

This study investigates the dynamic evolution of technical and soft skill requirements within founding teams of Colombian software startups during their early-stage development. Employing a survey-based methodology administered to active startup teams, it systematically analyzes the shifting importance of technical competencies—including requirements engineering, agile development, project management, and marketing—as well as soft skills such as communication, leadership, and teamwork. Results indicate that requirements engineering, agile methodologies, budget management, and communication/leadership consistently rank among the most critical capabilities; however, their relative importance undergoes significant shifts across distinct growth stages. This research provides the first empirical characterization of stage-dependent competency evolution in Latin American software startups. Its findings offer evidence-based guidance for entrepreneurial capability development, incubator curriculum design, and public policy formulation in entrepreneurship education—particularly within emerging markets.

0 citationsRead paper

An extension of Priestley duality to fuzzy topologies and positive MV-algebras

Aug 26, 2025

The absence of a unified categorical duality framework for many-valued logic and fuzzy structures hinders systematic connections between fuzzy topology and algebraic semantics. Method: This work systematically extends Priestley duality to the categories of fuzzy topological spaces and positive MV-algebras, integrating category theory, fuzzy topology, MV-algebra theory, and limit-truncation completeness techniques to establish a rigorous dual equivalence. Contribution/Results: The resulting duality unifies and generalizes both classical Priestley duality and Stone duality, transcending the limitations of binary logic. It constitutes the first Stone-type duality for fuzzy topology and many-valued logic grounded in ordered algebraic structures—specifically, positive MV-algebras. By doing so, it significantly broadens the applicability and expressive power of duality methods in non-classical logics, providing a foundational framework for further developments in fuzzy semantics, algebraic logic, and categorical model theory.

0 citationsRead paper