I am a passionate student and researcher in Deep Learning and Data Science, currently working part-time with the Minerva research team at University of Seville since last year. My research encompasses areas such as Machine Learning, Deep Learning, Time Series Forecasting, and Explainable Artificial Intelligence (XAI). While I keep learning about Computer Vision and Natural Language Processing.
Following this research role, I am a Graduate in Computer Engineering and also in Mathematics, where I gained a solid foundation in Optimization and Artificial Intelligence. My academic journey is marked by a continuous drive to align my education with my passion for data science and research. I am currently enhancing my academic credentials with a Master's in Data Engineering and preparing to embark on a Doctorate.
I am always eager to evolve and grow, both personally and professionally. Beyond my profound interest in research, I always keep an open eye for new opportunities to learn and acquire new skills. That is why I also find a great interest in other areas such as Software Development.
- More about me and my interest on Linkedin
- Research profile on Scholar, Research Gate and University of Seville Portal.
A Feature Selection and Association Rule Approach to Identify Genes Associated with Metastasis and Low Survival in Sarcoma
International Conference on Hybrid Artificial Intelligence Systems (HAIS 2023)
This work proposes a methodology that combines preprocessing, feature selection and association rule mining to identify relevant genes and significant relationships in biological data from sarcoma patients.
Multi-Objective Lagged Feature Selection Based on Dependence Coefficient for Time-Series Forecasting
National Conference of the Spanish Association for Artificial Intelligence (CAEPIA 2024)
Awarded as second best paper of TAMIDA Symposium. This paper presents a novel feature selection approach that integrates a statistical metric based on the Conditional Dependence Coefficient with a multi-objective evolutionary algorithm. Applied to the prediction of multivariate time-series in fields such as air quality forecasting, electricity demand, urban traffic management, and preventive maintenance of systems, the method demonstrates strong performance and significant reduction in model complexity.
You can find the complete list of my works in my Scholar profile.