Grups d'Investigació

GIUV2016-283

The group's activities are divided along the following main lines: Simulation of cardiac eletrophysiology. Simulation of fluid dynamics. Automatic learning models: where we work with reinforcement learning techniques, as well as with classifiers of different types oriented towards the development of systems to aid the medical act (SAAM for its Spanish acronym meaning Sistemas de ayuda al acto médico). Broadly speaking, the group's activities are divided, on the one hand, into research oriented towards biomedical simulation (electrophysiology and fluids) and, on the other, research into automatic learning models (classical + deep learning) capable of handling large volumes of data, thus offering very useful applications for the medical sector based on the multiple simulation results derived from classical techniques and acquired in different projects.

http://www.uv.es/commlab

• Simulacion de procesos complejos aplicados a medicina, fisica y ciencias del comportamiento asi como la creacion de modelos de aprendizaje automatico capaces de analizar grandes volumenes de datos (biomedicos, etc) y de ofrecer sistemas de asistencia al acto medico en distintos ambitos (cardiologia, vascular,..).

• Cardiac elctrophysiology.The research group works on the modelling and multiscale simulation of the activation process of cardiac tissue, in order to characterise and predict different pathologies. The group has high-resolution simulation software that allows fully synthetic electrocardiograms to be reproduced, with the possibility of simulating different pathologies. Another active line of work in this field is the estimation of the cardiac conduction system using analysis of data acquired during surgical practice.
• Fluid simulation.The CoMMLab group uses computational fluid mechanics techniques applied to different fields. In biomedical engineering, the group uses fluid models for the simulation of the vascular system, especially in large vessels, to analyse and predict pathologies such as aneurysms. In the field of computer graphics, non-Newtonian fluid models are developed with applications mainly in interactive simulation (virtual reality, videogames,...) and in simulations for physics-based animation and special effects.
• Machine learning.In addition to the experience acquired over the years by the members of the group in different areas of simulation, mainly in bioengineering and mechanical engineering, recent advances in machine learning have been assimilated by the group as another way of exploiting the results of its simulations. The group has applied these techniques to the development of pedestrain models applied to crowd simulation. It also allows a further step in transferring the results of the simulations to new medical and industrial sectors (i.e. predictors of ectopic foci, aneurysms, arrhythmia detectors, etc.).

• -

• Computer Science

• Electrofisiología, Corazón, Purkinje, Modelado, Simulación
• Simulación de fluidos, Fluidos no Newtonianos, animación por computador
• Aprendizaje automático, Simulación, Aprendizaje por refuerzo, Sistemas de ayuda a la decisión/acto médica.