Machine Learning Research

Architectures and algorithms for distributed machine learning across secure data spaces, enabling collaborative model training over heterogeneous datasets without centralizing sensitive raw data.

• ARTIFACTS-UC3M: Secure data spaces for federated learning environments (AEI).

• Collaborative multi-dataset learning through shared and private model components in healthcare environments (Machine Learning with Applications, 2026)

Generative models and adversarial learning techniques for synthesizing high-fidelity, privacy-preserving data, alongside active labeling correction and robust outlier detection in sensitive domains.

• ARTIFACTS-UC3M: Reliable synthetic health data generation for secure data sharing.
• Neoris España: Adversarial learning techniques to increase transparency and privacy in digital platforms.

• Active Labeling Correction of Mealtimes and the Appearance of Types of Carbohydrates in Type 1 Diabetes Information Records (Mathematics, 2023)

Deep learning physiological models (RNNs, LSTMs, Attention mechanisms) for continuous blood glucose prediction, carbohydrate digestion modeling, and personalized health analytics for Type 1 Diabetes.

• Caloricious INC: Machine learning models for blood glucose prediction and nutrition tracking.

• Using absorption models for insulin and carbohydrates and deep leaning to improve glucose level predictions (Sensors, 2021)
• Algorithm for the comparison of human periodic movements using wearable devices (Journal of Healthcare Engineering, 2021)

Deep spatiotemporal architectures and Graph Neural Networks (GNNs) utilizing urban sensors, GPS, and mobility data for traffic flow estimation, accessible/eco-friendly routing, and epidemiological forecasting.

• REALES & FLATCITY: Real-time social sensor analysis and multimodal transport estimation.
• Hermes-Smartdriver: Healthy and efficient routes in open-data smart cities.

• A Deep Graph Neural Network Approach for Assessing Origin Destination Traffic Flow Estimates Based on COVID-19 Data (IEEE Access, 2024)
• A new RNN based machine learning model to forecast COVID-19 incidence, enhanced by the use of mobility data from the bike-sharing service in Madrid (Heliyon, 2023)
• Using Traffic Sensors in Smart Cities to Enhance a Spatio-Temporal Deep Learning Model for COVID-19 Forecasting (Mathematics, 2023)

Inertial sensor data processing (accelerometers, smart insoles) via CNNs and DRNNs for activity recognition, gait pattern analysis, driver stress detection, and movement tracking in children with ADHD.

• Analytics Using Sensor Data: Sensor analytics for mobile and wearable environments.

• Recurrent neural network with contextual attention for prognostics (Evolving Systems, 2025)
• Exploring commuter stress dynamics through machine learning and double optimization (Mehran University Research Journal, 2025)
• Tourist experiences recommender system based on emotion recognition with wearable data (Sensors, 2021)

Intelligent tutoring systems, adaptive educational recommenders, gamified competitive learning environments, and content modeling in smart learning ecosystems.

• Cominn: Gamification and educational technology innovation.

• Content Modeling in Smart Learning Environments: A systematic literature review (Journal of Universal Computer Science, 2024)

Application of generative AI for incident management support, automated ingesting and reasoning over scanned documentation, and AI-driven geopolitical risk models for supply chain resilience.

• LOGICALIS: Generative AI support for incident management systems.
• KARTEX RISK (2025-2026): Document automation and geopolitical risk modeling.
• Pistacia Vera (OLIV-IA): Applied AI for agrotech environments.

• Explicit Context Integrated Recurrent Neural Network for applications in smart environments (Expert Systems with Applications, 2024)
• Smart Contracts as a Tool to Support the Challenges of Buying and Selling Coffee Futures Contracts in Colombia (Agriculture, 2024)

Leading research in automated software testing, development of the Selenium ecosystem frameworks (Selenium-Jupiter, WebDriver Manager), and AI-assisted software modeling.

• AI4COCOMO (GeneticAI): Artificial intelligence applied to software estimation and modeling.

• Test automation with Selenium: A survey (Information and Software Technology, 2026)
• Selenium-Jupiter: A JUnit 5 extension for Selenium WebDriver (Journal of Systems and Software, 2022)
• Automated Driver Management for Selenium WebDriver (Empirical Software Engineering, 2021)