I am a Biomedical Engineering student at the University of Las Palmas de Gran Canaria, interested in the application of engineering and artificial intelligence to healthcare.

• Medical Artificial Intelligence
• Machine Learning applied to biosignals
• ECG and EEG signal processing
• Medical image processing
• Biomechanics
• Prosthetics and assistive technologies
• 3D modelling and biomedical design

• Python
• Scikit-learn
• Pandas
• NumPy
• Matplotlib
• Jupyter Notebook
• MATLAB
• Autodesk Fusion
• Git and GitHub

Educational biomedical signal-processing workflow including ECG filtering, R-peak detection, RR interval analysis, heart-rate variability metrics, QRS enhancement and wavelet-based denoising.

Technologies: MATLAB, Signal Processing Toolbox, Wavelet Toolbox

Originally developed jointly with Adriana Moreno Naranjo as a Biomedical Engineering academic project.

MATLAB workflow for synthetic-noise generation, FIR band-stop filtering, energy-based segmentation of sustained vowels and narrowband/wideband spectrogram analysis.

Technologies: MATLAB, Signal Processing Toolbox

Originally developed jointly with Adriana Moreno Naranjo as a Biomedical Engineering academic project.

MATLAB workflow for multichannel EEG preprocessing, wavelet denoising, frequency-band extraction, band-power estimation and exploratory comparison between interictal and annotated seizure segments from the CHB-MIT dataset.

Technologies: MATLAB, Signal Processing Toolbox, Wavelet Toolbox, PhysioNet

Originally developed jointly with Adriana Moreno Naranjo as a Biomedical Engineering academic project.

MATLAB project for extracting and analysing time-domain heart rate variability metrics from annotated ECG records in the MIT-BIH Arrhythmia Database. The project includes an individual comparison of normal and pathological rhythms and an automated workflow for processing 48 records, applying physiological RR filtering and calculating Mean RR, SDNN and RMSSD. The results highlight differences in cardiac rhythm variability while also demonstrating the limitations of using these metrics alone for reliable classification.

Technologies: MATLAB, ECG, heart rate variability, biomedical signal processing, PhysioNet, MIT-BIH Arrhythmia Database.

Originally developed jointly with Adriana Moreno Naranjo as a Biomedical Engineering academic project.

MATLAB project for separating independent audio sources from multichannel mixtures using Independent Component Analysis and the FastICA algorithm.

The repository includes a fully reproducible demonstration with synthetic audio signals, controlled noise generation, automatic component matching and correlation-based evaluation. The recovered sources achieved correlations above 0.997 with their original reference signals.

Technologies: MATLAB, Independent Component Analysis, FastICA, audio signal processing, blind source separation.

Originally developed jointly with Adriana Moreno Naranjo as a Biomedical Engineering academic project.

Reproducible Python machine learning workflow for classifying the presence of heart disease using the Cleveland dataset from the UCI Machine Learning Repository. The project compares Logistic Regression, Support Vector Machine, K-Nearest Neighbours, Random Forest and Gaussian Naive Bayes using five-fold stratified cross-validation.

Gaussian Naive Bayes achieved the highest mean accuracy, with a final out-of-fold accuracy of 85.48%, sensitivity of 82.01%, specificity of 88.41% and ROC AUC of 0.9009. The repository includes automatic dataset retrieval, leakage-safe preprocessing, model comparison, clinically relevant metrics, a confusion matrix and an ROC curve.

Technologies: Python, pandas, NumPy, scikit-learn, Matplotlib, UCI Machine Learning Repository.

Originally developed jointly with Adriana Moreno Naranjo as a Biomedical Engineering academic project.

Python workflow for automating the segmentation of anatomical structures and air-containing regions from chest CT images in 3D Slicer. The project creates body, exterior, skin, bone, and lungs-and-air segments using Hounsfield unit thresholding, logical operations, masking, smoothing, hollow surface generation, and connected-component analysis. The workflow was tested and visually validated with the CTChest sample volume in 3D Slicer 5.10.0.

Technologies: Python, NumPy, 3D Slicer, computed tomography, medical image segmentation, image processing.

Originally developed jointly with Adriana Moreno Naranjo as a Biomedical Engineering academic project.

I am currently improving and documenting several academic projects to turn them into reproducible and professionally structured repositories.

Some of the projects that will be available soon include:

• Sleep disorder risk prediction using Machine Learning
• 3D design of a prosthetic hand

I am building this portfolio to develop my skills in medical AI and biomedical technology and to prepare for future internships and professional opportunities.

• GitHub: miguel-martindominguez
• LinkedIn: Coming soon