Pasar al contenido principal

PROCESAMIENTO DE SEÑAL PARA DATOS DEFINIDOS SOBRE GRAFOS: APROVECHANDO LA ESTRUCTURA EN DOMINIOS IRREGULARES

PID2019-105032GB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2019
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD REY JUAN CARLOS

Resultados relacionados

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

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Non-invasive estimation of atrial fibrillation driver position using long-short term memory neural networks and body surface potentials

  • Gutiérrez-Fernández-Calvillo, Miriam
  • Cámara-Vázquez, Miguel Ángel
  • Hernández-Romero, Ismael
  • Climent, Andreu M.
  • Barquero-Pérez, Óscar
  • Guillem Sánchez, María Salud|||0000-0001-5660-3693
  • Fambuena-Santos, Carlos
[EN] Background and Objective: Atrial Fibrillation (AF) is a supraventricular tachyarrhythmia that can lead to thromboembolism, hearlt failure, ischemic stroke, and a decreased quality of life. Characterizing the locations where the mechanisms of AF are initialized and maintained is key to accomplishing an effective ablation of the targets, hence restoring sinus rhythm. Many methods have been investigated to locate such targets in a non-invasive way, such as Electrocardiographic Imaging, which enables an on -invasive and panoramic characterization of cardiac electrical activity using recording Body Surface Potentials (BSP) and a torso model of the patient. Nonetheless, this technique entails some major issues stemming from solving the inverse problem, which is known to be severely ill -posed. In this context, many machine learning and deep learning approaches aim to tackle the characterization and classification of AF targets to improve AF diagnosis and treatment. Methods: In this work, we propose a method to locate AF drivers as a supervised classification problem. We employed a hybrid form of the convolutional -recurrent network which enables feature extraction and sequential data modeling utilizing labeled realistic computerized AF models. Thus, we used 16 AF electrograms, 1 atrium, and 10 torso geometries to compute the forward problem. Previously, the AF models were labeled by assigning each sample of the signals a region from the atria from 0 (no driver) to 7, according to the spatial location of the AF driver. The resulting 160 BSP signals, which resemble a 64 -lead vest recording, are preprocessed and then introduced into the network following a 4 -fold cross -validation in batches of 50 samples. Results: The results show a mean accuracy of 74.75% among the 4 folds, with a better performance in detecting sinus rhythm, and drivers near the left superior pulmonary vein (R1), and right superior pulmonary vein (R3) whose mean sensitivity bounds around 84%-87%. Significantly good results are obtained in mean sensitivity (87%) and specificity (83%) in R1. Conclusions: Good results in R1 are highly convenient since AF drivers are commonly found in this area: the left atrial appendage, as suggested in some previous studies. These promising results indicate that using CNN-LSTM networks could lead to new strategies exploiting temporal correlations to address this challenge effectively., This work has been partially supported by: Ministerio de Ciencia e Innovacion (PID2019-105032GB-I00, PID2022-136887NB-I00) , Rey Juan Carlos University (2023/00004/006-F918) , Instituto de Salud Carlos III and Ministerio de Ciencia, Innovacion y Universidades (supported by FEDER Fondo Europeo de Desarrollo Regional PI17/01106 and Consejeria de Ciencia, Universidades e Innovacion of the Comunidad de Madrid through the program RIS3 (S-2020/L2-622) , EIT Health Activity code 19600 and the European Union Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No. 860974.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Electrocardiographic imaging including intracardiac information to achieve accurate global mapping during atrial fibrillation

  • Cámara-Vázquez, Miguel Ángel
  • Hernández-Romero, Ismael
  • Rodrigo, Miguel
  • Alonso-Atienza, Felipe
  • Figuera, Carlos
  • Morgado-Reyes, Eduardo
  • Atienza, Felipe
  • Barquero-Pérez, Óscar
  • Guillem Sánchez, María Salud|||0000-0001-5660-3693
  • Andreu M. Climent|||0000-0002-7260-8811
[EN] Atrial fibrillation (AF) is characterized by complex and irregular propagation patterns. Noninvasive electrocardiographic imaging (ECGI) has been tested during AF conditions with promising results. However, current regularization methods face important challenges in this type of unstable electrical activity scenarios. Combination of intracardiac and non-invasive simultaneous recordings could improve ECGI performance and allow real-time global mapping of complex AF patterns. In this work, we propose an ECGI method that incorporates intracardiac measurements as a constraint in a reformulation of the classical Tikhonov method. We used realistic mathematical models of atria and torso that simulates a wide number of epicardial electrical activity patterns. Body surface potentials were obtained from simulated electrograms (EGMs) by using Boundary Element Method and corrupted with Gaussian noise. Epicardial potentials were estimated using inverse problem with Tikhonov regularization, including intracavitary information as a second constraint. Results showed that first-order Constrained Tikhonov formulation provided more reliable reconstructions than the classical Tikhonov approach in AF conditions using at least 32 uniformly distributed endocardial EGMs (CC between 0.87 and 0.28, depending on the AF complexity). Constrained Tikhonov provided more accurate spatial mass functions (SMF) of PS locations (CC smF between 0.24 and 0.86). This methodology was tested on real patient data, obtaining a mean DF RMSE of 0.85 Hz, outperforming the classical Tikhonov approach. Limitations of this study include the fact that the model considered endocardium and epicardium as a single layer. Further research will include endocardium-epicardium bilayer model approximations and validation using more real patient data., This work has been partially supported by projects TEC2016-75361R and PID2019-105032GB-I00 from the Spanish Ministry of Economy and Spanish Ministry of Science and Innovation, respectively, projects IJCI-2014-22178, PI16-01123, DTS16/00160, PI17/0159, PI17/01106 from the Spanish Ministry of Economy through the Carlos III Health Institute with FEDER founds, grant GVA APOSTD/2017/068 and projects AICO/2018/267, GV/2018/103 from the Education, Research, Culture and Sports department of Generalitat Valenciana, Spain.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Detection of Atrial Fibrillation Driver Locations Using CNN and Body Surface Potentials

  • Cámara-Vázquez, Miguel Ángel
  • Hernández-Romero, Ismael
  • Morgado-Reyes, Eduardo
  • Barquero-Pérez, Óscar
  • Guillem Sánchez, María Salud|||0000-0001-5660-3693
  • Andreu M. Climent|||0000-0002-7260-8811
[EN] Atrial fibrillation (AF) is characterized by complex and irregular propagation patterns, and AF onset locations and drivers responsible for its perpetuation are main targets for ablation procedures. Several Deep Learningbased methods have proposed to detect AF, but the estimation of the atrial area where the drivers are found is a topic where further research is needed. In this work, we propose to estimate the zone where AF drivers are found from body surface potentials (BSPs) and Convolutional Neural Networks (CNN), modeling a supervised classification problem. Accuracy in the test set was 0.89 when using noisy BSPs (SNR=20dB), while the Cohen¿s Kappa was 0.85. Therefore, the proposed method could help to identify target regions for ablation using a non-invasive procedure, and avoiding the use of ECG Imaging (ECGI)., This work has been partially supported by: Ministerio de Ciencia e Innovacion (PID2019-105032GB-I00), Instituto de Salud Carlos III, and Ministerio de Ciencia, Innovacion y Universidades (supported by FEDER Fondo Europeo de Desarrollo Regional PI17/01106 and RYC2018-024346B-750), Consejeria de Ciencia, Universidades e Innovacion of the Comunidad de Madrid through the program RIS3 (S-2020/L2-622), EIT Health (Activity code 19600, EIT Health is supported by EIT, a body of the European Union) and the European Union's Horizon 2020 research and innovation program under the Marie Skodowska-Curie grant agreement No. 860974.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Non-invasive Estimation of Atrial Fibrillation Driver Position With Convolutional Neural Networks and Body Surface Potentials

  • Cámara-Vázquez, Miguel Ángel
  • Hernández-Romero, Ismael
  • Morgado-Reyes, Eduardo
  • Barquero-Pérez, Oscar
  • Guillem Sánchez, María Salud|||0000-0001-5660-3693
  • Andreu M. Climent|||0000-0002-7260-8811
[EN] Atrial fibrillation (AF) is characterized by complex and irregular propagation patterns, and AF onset locations and drivers responsible for its perpetuation are the main targets for ablation procedures. ECG imaging (ECGI) has been demonstrated as a promising tool to identify AF drivers and guide ablation procedures, being able to reconstruct the electrophysiological activity on the heart surface by using a non-invasive recording of body surface potentials (BSP). However, the inverse problem of ECGI is ill-posed, and it requires accurate mathematical modeling of both atria and torso, mainly from CT or MR images. Several deep learning-based methods have been proposed to detect AF, but most of the AF-based studies do not include the estimation of ablation targets. In this study, we propose to model the location of AF drivers from BSP as a supervised classification problem using convolutional neural networks (CNN). Accuracy in the test set ranged between 0.75 (SNR = 5 dB) and 0.93 (SNR = 20 dB upward) when assuming time independence, but it worsened to 0.52 or lower when dividing AF models into blocks. Therefore, CNN could be a robust method that could help to non-invasively identify target regions for ablation in AF by using body surface potential mapping, avoiding the use of ECGI., This work has been partially supported by: Ministerio de Ciencia e Innovacion (PID2019-105032GB-I00), Instituto de Salud Carlos III, and Ministerio de Ciencia, Innovacion y Universidades (supported by FEDER Fondo Europeo de Desarrollo Regional PI17/01106 and RYC2018-024346B-750), Consejeria de Ciencia, Universidades e Innovacion of the Comunidad de Madrid through the program RIS3 (S-2020/L2-622), EIT Health (Activity code 19600, EIT Health is supported by EIT, a body of the European Union) and the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No. 860974.
Repositorio Institucional de la Universidad de Burgos (RIUBU)
Publicación Contribución de congreso (ConferenceOutput)

Signal processing and machine learning for air traffic delay prediction

  • Tenorio, Víctor M.
  • García Marqués, Antonio
  • Cadarso, Luis
Trabajo presentado en: R-Evolucionando el transporte, XIV Congreso de Ingeniería del Transporte (CIT 2021), realizado en modalidad online los días 6, 7 y 8 de julio de 2021, organizado por la Universidad de Burgos, As data quality and quantity increase, the prediction of future events using machine learning (ML) techniques across engineering disciplines grows by the day. Air transportation cannot be an exception. Delay prediction is paramount in the aerospace industry, since air traffic delays are responsible for millions of dollars in losses to airlines and passengers, along with negative impacts on the environment. In this contribution, we leverage recent signal processing and ML advances to put forth a processing-and-learning pipeline for the prediction of air traffic delays. The proposed approach is executed in several steps. Firstly, we apply signal processing and data science techniques to filter and denoise the original information. Secondly, we run a descriptive analysis of the data and design new features tailored to the prediction problem. Thirdly, we implement a scheme to select the most informative of those features, contributing to a better generalization performance, and offering useful insights. Two algorithms are used to that end: one based on random forests and one employing a sparse logistic regression approach. Finally, once the features are selected, we implement, analyse, and compare several ML architectures (from classical classifiers to deep learning) to predict the delay. While the focus of the comparison is prediction accuracy, metrics such as sample and computational complexity are also discussed. Numerical experiments are drawn from the US domestic market for the year 2018, when more than 7 million flights between 358 airports were flown. The designed processing/learning pipeline reveals interesting insights and achieves better prediction results than the state of the art. The results confirm that air traffic delay prediction is a challenging problem, mainly because the delay is extremely airport-dependent and the data is highly unbalanced (i.e., only a small percentage of flights are noticeable delayed), and identify worth-pursuing future lines of work., The authors want to thank Sergio Rozada for his help in designing and coding the algorithms used in this publication and the Spanish “Agencia Estatal de Investigación” for the support via Project Grants TRA2016-76914-C3-3-P, PID2019-105032GB-I00, and CAS19/00036 and CAM grant PEJ-2020-AI/TIC-18964.