This page gathers my open-source software, public datasets, and reusable teaching resources. These projects are part of a broader goal: making machine learning more useful and accessible for health and biomedical research.
I am especially interested in resources that help clinicians, microbiologists, and biomedical researchers work with AI in a more practical, transparent, and reproducible way. Some entries are research prototypes, while others are designed as reusable community-facing tools and data assets.
The dataset includes CT axial scans from 40 subjects, 13 of which were manually annotated with a semantic segmentation of the osseous structures of the area surrounding the paranasal sinuses.
Our dataset includes 3,800 audio files, averaging 35.51 ± 5.91 recordings per patient, covering surgeries like Tonsillectomy, Functional Endoscopic Sinus Surgery, and Septoplasty.
Our dataset includes 2,977 audio files, averaging 26.88 ± 3.35 recordings per participant, 54 individuals diagnosed with Parkinson’s Disease and 58 healthy controls.
A library to retrieve any stock market data from EOD Historical Data market datafeed API.
Python code to Multi-view hierarchical Variational AutoEncoders with Factor Analysis latent space paper.
Bash simple script to monitorize the use of GPU by the colleagues of the department
Python code to Bayesian Sparse Factor Analysis with Kernelized Observations paper.
I have developed a powerful and user-friendly tool designed to manually correct automatic transcriptions of audio files. This tool is particularly useful for refining transcriptions made by Whisper, ensuring high accuracy and quality.
Python code to Exploring the Power of PPG Matrix for Atrial Fibrillation Detection with Integrated Explainability paper.
An unfinished project of reading public spanish electrical prices and do some ML
Slides of the BioInspired Learning course at MUIT UPM