Pasar al contenido principal

GENERATION OF RELIABLE SYNTHETIC HEALTH DATA FOR FEDERATED LEARNING IN SECURE DATA SPACES - UPC

PID2022-141045OB-C41

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2022
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Gamificación mediante retos semanales para la motivación y el aprendizaje universitario

  • Villar Rubio, Alejandro
  • Oprescu, Andreea M.
  • Calvo-Morata, Antonio
En los últimos años, se ha observado un cambio en las necesidades y los procesos de aprendizaje del estudiantado. La gamificación se presenta como una técnica capaz de motivar al estudiantado y aumentar su participación activa durante el aprendizaje. En este trabajo, se describe la experiencia de aplicar técnicas de gamificación en el aula, con el objetivo de fomentar el interés del estudiantado a la vez que se busca romper la barrera existente entre estudiante y profesor. La metodología presentada consiste en el planteamiento de retos semanales dentro del marco teórico de la asignatura o en la experiencia universitaria, pero evitando ser tareas académicas o ejercicios didácticos. La superación de estos retos semanales permite el acceso a material que facilita el seguimiento de la asignatura, compuesto por un resumen semanal, recomendaciones para avanzar en los ejercicios prácticos planteados, una imagen de carácter humorístico y el reto a superar para la siguiente semana. Esta metodología ha sido aplicada en dos asignaturas que se imparten en centros de informática, evaluando su eficacia mediante cuestionarios que muestran un efecto positivo en el aula, permitiendo así que esta metodología sea aplicable en cualquier asignatura.
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Iterative application of UMAP-based algorithms for fully synthetic healthcare tabular data generation

  • Lázaro Trilles, Carla|||0009-0003-4308-5032
  • Angulo Bahón, Cecilio|||0000-0001-9589-8199
Building on a previously developed partially synthetic data generation algorithm utilizing data visualization techniques, this study extends the novel algorithm to generate fully synthetic tabular healthcare data. In this enhanced form, the algorithm serves as an alternative to conventional methods based on Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs). By iteratively applying the original methodology, the adapted algorithm employs UMAP (Uniform Manifold Approximation and Projection), a dimensionality reduction technique, to validate generated samples through low-dimensional clustering. This approach has been successfully applied to three healthcare domains: prostate cancer, breast cancer, and cardiovascular disease. The generated synthetic data have been rigorously evaluated for fidelity and utility. Results show that the UMAP-based algorithm outperforms GAN- and VAE-based generation methods across different scenarios. In fidelity assessments, it achieved smaller maximum distances between the cumulative distribution functions of real and synthetic data for different attributes. In utility evaluations, the UMAP-based synthetic datasets enhanced machine learning model performance, particularly in classification tasks. In conclusion, this method represents a robust solution for generating secure, high-quality synthetic healthcare data, effectively addressing data scarcity challenges., This research was funded by the European Union Horizon Europe R&I program through the project FLUTE (Grant agreement no.: 101095382). It is also co-funded by the European Union–Next Generation EU funds, through the I+D+i PID2021-122835OBC21 research project ARTIFACTS (MCIN/AEI/10.13039/501000011033) and FEDER “Una manera de hacer Europa”., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Using UMAP for partially synthetic healthcare tabular data generation and validation

  • Lázaro Trilles, Carla|||0009-0003-4308-5032
  • Angulo Bahón, Cecilio|||0000-0001-9589-8199
In healthcare, vast amounts of data are increasingly collected through sensors for smart health applications and patient monitoring or diagnosis. However, such medical data often comprise sensitive patient information, posing challenges regarding data privacy, and are resource-intensive to acquire for significant research purposes. In addition, the common case of lack of information due to technical issues, transcript errors, or differences between descriptors considered in different health centers leads to the need for data imputation and partial data generation techniques. This study introduces a novel methodology for partially synthetic tabular data generation, designed to reduce the reliance on sensor measurements and ensure secure data exchange. Using the UMAP (Uniform Manifold Approximation and Projection) visualization algorithm to transform the original, high-dimensional reference data set into a reduced-dimensional space, we generate and validate synthetic values for incomplete data sets. This approach mitigates the need for extensive sensor readings while addressing data privacy concerns by generating realistic synthetic samples. The proposed method is validated on prostate and breast cancer data sets, showing its effectiveness in completing and augmenting incomplete data sets using fully available references. Furthermore, our results demonstrate superior performance in comparison to state-of-the-art imputation techniques. This work makes a dual contribution by not only proposing an innovative method for synthetic data generation, but also studying and establishing a formal framework to understand and solve synthetic data generation and imputation problems in sensor-driven environments., This research was funded by the European Union Horizon Europe R&I program through the project FLUTE (Grant agreement no.: 101095382). It is also co-funded by the European Union–Next Generation EU funds, through the I+D+i PID2021-122835OBC21 research project ARTIFACTS (MCIN/AEI/10.13039/501000011033) and FEDER “Una manera de hacer Europa”., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Iterative application of UMAP-based algorithms for fully synthetic healthcare tabular data generation

  • Lázaro Trilles, Carla
  • Angulo Bahón, Cecilio
Building on a previously developed partially synthetic data generation algorithm utilizing data visualization techniques, this study extends the novel algorithm to generate fully synthetic tabular healthcare data. In this enhanced form, the algorithm serves as an alternative to conventional methods based on Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs). By iteratively applying the original methodology, the adapted algorithm employs UMAP (Uniform Manifold Approximation and Projection), a dimensionality reduction technique, to validate generated samples through low-dimensional clustering. This approach has been successfully applied to three healthcare domains: prostate cancer, breast cancer, and cardiovascular disease. The generated synthetic data have been rigorously evaluated for fidelity and utility. Results show that the UMAP-based algorithm outperforms GAN- and VAE-based generation methods across different scenarios. In fidelity assessments, it achieved smaller maximum distances between the cumulative distribution functions of real and synthetic data for different attributes. In utility evaluations, the UMAP-based synthetic datasets enhanced machine learning model performance, particularly in classification tasks. In conclusion, this method represents a robust solution for generating secure, high-quality synthetic healthcare data, effectively addressing data scarcity challenges., This research was funded by the European Union Horizon Europe R&I program through the project FLUTE (Grant agreement no.: 101095382). It is also co-funded by the European Union–Next Generation EU funds, through the I+D+i PID2021-122835OBC21 research project ARTIFACTS (MCIN/AEI/10.13039/501000011033) and FEDER “Una manera de hacer Europa”., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Using UMAP for partially synthetic healthcare tabular data generation and validation

  • Lázaro Trilles, Carla
  • Angulo Bahón, Cecilio
In healthcare, vast amounts of data are increasingly collected through sensors for smart health applications and patient monitoring or diagnosis. However, such medical data often comprise sensitive patient information, posing challenges regarding data privacy, and are resource-intensive to acquire for significant research purposes. In addition, the common case of lack of information due to technical issues, transcript errors, or differences between descriptors considered in different health centers leads to the need for data imputation and partial data generation techniques. This study introduces a novel methodology for partially synthetic tabular data generation, designed to reduce the reliance on sensor measurements and ensure secure data exchange. Using the UMAP (Uniform Manifold Approximation and Projection) visualization algorithm to transform the original, high-dimensional reference data set into a reduced-dimensional space, we generate and validate synthetic values for incomplete data sets. This approach mitigates the need for extensive sensor readings while addressing data privacy concerns by generating realistic synthetic samples. The proposed method is validated on prostate and breast cancer data sets, showing its effectiveness in completing and augmenting incomplete data sets using fully available references. Furthermore, our results demonstrate superior performance in comparison to state-of-the-art imputation techniques. This work makes a dual contribution by not only proposing an innovative method for synthetic data generation, but also studying and establishing a formal framework to understand and solve synthetic data generation and imputation problems in sensor-driven environments., This research was funded by the European Union Horizon Europe R&I program through the project FLUTE (Grant agreement no.: 101095382). It is also co-funded by the European Union–Next Generation EU funds, through the I+D+i PID2021-122835OBC21 research project ARTIFACTS (MCIN/AEI/10.13039/501000011033) and FEDER “Una manera de hacer Europa”., Peer Reviewed, Postprint (published version)