Heart Rate Variability LSTM Autoencoder for Autonomic Fatigue Profiling in Endurance Athletes from Cundinamarca, Colombia: Code, Models and Data

Fuente: Zenodo
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Tellez Tinjaca, Luis Andres, COLLAZOS MORALES, CARLOS ANDRES, Sánchez Cifuentes, Joaquín, peña, Jhonatan
Format: Recurso digital
Langue:espagnol
Publié: Zenodo 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866902008854740992
author Tellez Tinjaca, Luis Andres
COLLAZOS MORALES, CARLOS ANDRES
Sánchez Cifuentes, Joaquín
peña, Jhonatan
author_facet Tellez Tinjaca, Luis Andres
COLLAZOS MORALES, CARLOS ANDRES
Sánchez Cifuentes, Joaquín
peña, Jhonatan
contents <p>This repository contains the supplementary materials for the doctoral thesis <br>"Autonomic profiling of muscular fatigue in endurance athletes from <br>Cundinamarca using Heart Rate Variability and a Deep LSTM Autoencoder" <br>(Universidad Manuela Beltrán, Bogotá, 2026).</p> <p>CONTENTS:<br>- Phase 2 pipeline: synthetic data generation (CTGAN), LSTM Autoencoder <br>  training, 5-fold cross-validation, and latent space interpretability <br>  analysis. Includes the trained autoencoder (.h5), encoder (.h5), and <br>  fitted StandardScaler (.pkl).<br>- Phase 3 pipeline: application of the pre-trained encoder to 50 endurance <br>  athletes from Cundinamarca, K-Means clustering, t-SNE/PCA visualization, <br>  Mann-Whitney U tests with Bonferroni correction, and bootstrap-based <br>  cluster stability validation.<br>- Jupyter notebooks (Fase II.ipynb, Fase III.ipynb), 24 result tables <br>  (.xlsx), 17 publication-quality figures (300 DPI), validated synthetic <br>  dataset (4,750 records × 18 HRV variables), and 8-dimensional embeddings.</p> <p>INSTRUMENTATION: Heart Rate Variability was measured using a 15-channel <br>ECG (EDAN SE-15).</p> <p>REPRODUCIBILITY: Random seed SEED=42 fixed across NumPy, TensorFlow, <br>scikit-learn, and CTGAN. Library versions pinned (sdv==1.17.0, <br>scikit-learn==1.5.2). Environment: Google Colab, Python 3.10.</p> <p>Eighteen HRV variables were analyzed: HR, RR mean/max/min, Max/Min ratio, <br>SDNN, RMSSD, NN50, pNN50, SDSD, TINN, triangular index, LF, HF, LF_norm, <br>HF_norm, LF/HF ratio, and total power.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_20082945
institution Zenodo
language spa
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Heart Rate Variability LSTM Autoencoder for Autonomic Fatigue Profiling in Endurance Athletes from Cundinamarca, Colombia: Code, Models and Data
Tellez Tinjaca, Luis Andres
COLLAZOS MORALES, CARLOS ANDRES
Sánchez Cifuentes, Joaquín
peña, Jhonatan
Heart Rate Variability
hrv
LSTM Autoencoder
Deep learning
Autonomic Nervous System
Fatigue
Physical Endurance
Athletes
CTGAN
Synthetic data
Colombia
<p>This repository contains the supplementary materials for the doctoral thesis <br>"Autonomic profiling of muscular fatigue in endurance athletes from <br>Cundinamarca using Heart Rate Variability and a Deep LSTM Autoencoder" <br>(Universidad Manuela Beltrán, Bogotá, 2026).</p> <p>CONTENTS:<br>- Phase 2 pipeline: synthetic data generation (CTGAN), LSTM Autoencoder <br>  training, 5-fold cross-validation, and latent space interpretability <br>  analysis. Includes the trained autoencoder (.h5), encoder (.h5), and <br>  fitted StandardScaler (.pkl).<br>- Phase 3 pipeline: application of the pre-trained encoder to 50 endurance <br>  athletes from Cundinamarca, K-Means clustering, t-SNE/PCA visualization, <br>  Mann-Whitney U tests with Bonferroni correction, and bootstrap-based <br>  cluster stability validation.<br>- Jupyter notebooks (Fase II.ipynb, Fase III.ipynb), 24 result tables <br>  (.xlsx), 17 publication-quality figures (300 DPI), validated synthetic <br>  dataset (4,750 records × 18 HRV variables), and 8-dimensional embeddings.</p> <p>INSTRUMENTATION: Heart Rate Variability was measured using a 15-channel <br>ECG (EDAN SE-15).</p> <p>REPRODUCIBILITY: Random seed SEED=42 fixed across NumPy, TensorFlow, <br>scikit-learn, and CTGAN. Library versions pinned (sdv==1.17.0, <br>scikit-learn==1.5.2). Environment: Google Colab, Python 3.10.</p> <p>Eighteen HRV variables were analyzed: HR, RR mean/max/min, Max/Min ratio, <br>SDNN, RMSSD, NN50, pNN50, SDSD, TINN, triangular index, LF, HF, LF_norm, <br>HF_norm, LF/HF ratio, and total power.</p>
title Heart Rate Variability LSTM Autoencoder for Autonomic Fatigue Profiling in Endurance Athletes from Cundinamarca, Colombia: Code, Models and Data
topic Heart Rate Variability
hrv
LSTM Autoencoder
Deep learning
Autonomic Nervous System
Fatigue
Physical Endurance
Athletes
CTGAN
Synthetic data
Colombia
url https://doi.org/10.5281/zenodo.20082945