Bridge damage identification under varying environmental and operational conditions combining Deep Learning and numerical simulations
Authors: Ana Fernandez-Navamuel,David Pardo,Filipe Magalhães,Diego Zamora-Sánchez,Ángel J. Omella,David Garcia-Sanchez
This work proposes a novel supervised learning approach to identify damage in operating bridge structures. We propose a method to introduce the effect of environmental and operational conditions into the synthetic damage scenarios employed for training a Deep Neural Network, which is applicable to…
Elsevier BV
Variable selection with LASSO regression for complex survey data
Authors: Amaia Iparragirre,Thomas Lumley,Irantzu Barrio,Inmaculada Arostegui
Variable selection is an important step to end up with good prediction models. LASSO regression models are one of the most commonly used methods for this purpose, for which cross‐validation is the most widely applied validation technique to choose the tuning parameter . Validation techniques in a…
Wiley
Unsupervised Domain Adaption for Neural Information Retrieval
Authors: Dominguez, Carlos,Campos, Jon Ander,Agirre, Eneko,Azkune, Gorka
Neural information retrieval requires costly annotated data for each target domain to be competitive. Synthetic annotation by query generation using Large Language Models or rule-based string manipulation has been proposed as an alternative, but their relative merits have not been analysed. In this…
Elsevier BV
State-of-the-Art in Language Technology and Language-centric Artificial Intelligence
Authors: Rodrigo Agerri,Eneko Agirre,Itziar Aldabe,Nora Aranberri,Jose Maria Arriola,Aitziber Atutxa,Gorka Azkune,Jon Ander Campos,Arantza Casillas,Ainara Estarrona,Aritz Farwell,Iakes Goenaga,Josu Goikoetxea,Koldo Gojenola,Inma Hernáez,Mikel Iruskieta,Gorka…
AbstractThis chapter landscapes the field of Language Technology (LT) and language- centric AI by assembling a comprehensive state-of-the-art of basic and applied research in the area. It sketches all recent advances in AI, including the most recent deep learning neural technologies. The chapter…
Springer International Publishing
Automatic Logical Forms improve fidelity in Table-to-Text generation
Authors: Iñigo Alonso,Eneko Agirre
Table-to-text systems generate natural language statements from structured data like tables. While end-to-end techniques suffer from low factual correctness (fidelity), a previous study reported gains when using manual logical forms (LF) that represent the selected content and the semantics of the…
Elsevier BV
Estimation of the ROC curve and the area under it with complex survey data
Authors: Amaia Iparragirre,Irantzu Barrio,Inmaculada Arostegui
Logistic regression models are widely applied in daily practice. Hence, it is necessary to ensure they have an adequate predictive performance, which is usually estimated by means of the receiver operating characteristic (ROC) curve and the area under it (area under the curve [AUC]). Traditional…
Wiley
Estimating Future Costs of Emerging Wave Energy Technologies
Authors: Pablo Ruiz-Minguela,Donald R. Noble,Vincenzo Nava,Shona Pennock,Jesus M. Blanco,Henry Jeffrey
The development of new renewable energy technologies is generally perceived as a critical factor in the fight against climate change. However, significant difficulties arise when estimating the future performance and costs of nascent technologies such as wave energy. Robust methods to estimate the…
MDPI AG
Eigenvalue Curves for Generalized MIT Bag Models
Authors: Naiara Arrizabalaga,Albert Mas,Tomás Sanz-Perela,Luis Vega
We study spectral properties of Dirac operators on bounded domains $Ω\subset \mathbb{R}^3$ with boundary conditions of electrostatic and Lorentz scalar type and which depend on a parameter $τ\in\mathbb{R}$; the case $τ= 0$ corresponds to the MIT bag model. We show that the eigenvalues are…
Springer Science and Business Media LLC
Jointly optimized ensemble deep random vector functional link network for semi-supervised classification
Authors: Qiushi Shi,Ponnuthurai Nagaratnam Suganthan,Javier Del Ser
Randomized neural networks have become more and more attractive recently since they use closed-form solutions for parameter training instead of gradient-based approaches. Among them, the random vector functional link network (RVFL) and its deeper version ensemble deep random vector functional link…
Elsevier BV
Group’n Route: An Edge Learning-Based Clustering and Efficient Routing Scheme Leveraging Social Strength for the Internet of Vehicles
Authors: Naercio Magaia,Pedro Ferreira,Paulo Rogerio Pereira,Khan Muhammad,Javier Del Ser,Victor Hugo C. de Albuquerque
The Internet of Vehicles (IoV) is undoubtedly at the core of the future of intelligent transportation. It will prevail over the road ecosystem, and it will have a huge impact on our lives throughout the provision of seamless connectivity among diverse transportation means. For the network to…
Institute of Electrical and Electronics Engineers (IEEE)
EDA++: Estimation of Distribution Algorithms With Feasibility Conserving Mechanisms for Constrained Continuous Optimization
Authors: Abolfazl Shirazi,Josu Ceberio,Jose A. Lozano
Handling non-linear constraints in continuous optimization is challenging, and finding a feasible solution is usually a difficult task. In the past few decades, various techniques have been developed to deal with linear and non-linear constraints. However, reaching feasible solutions has been a…
Institute of Electrical and Electronics Engineers (IEEE)
Refined isogeometric analysis of quadratic eigenvalue problems
Authors: Hashemian, Ali,Garcia, Daniel,Pardo, David,Calo, Victor M.
Certain applications that analyze damping effects require the solution of quadratic eigenvalue problems (QEPs). We use refined isogeometric analysis (rIGA) to solve quadratic eigenproblems. rIGA discretization, while conserving desirable properties of maximum-continuity isogeometric analysis (IGA…
Elsevier BV
Numerical Regge pole analysis of resonance structures in state-to-state reactive differential cross sections
Authors: Elena Akhmatskaya,Dmitri Sokolovski
This is the third (and the last) code in a collection of three programs [Sokolovski et al (2011), Akhmatskaya et al (2014)] dedicated to the analysis of numerical data, obtained in an accurate simulation of an atom-diatom chemical reaction. Our purpose is to provide a detailed description of a…
Elsevier BV
Time series classifier recommendation by a meta-learning approach
Authors: A. Abanda,U. Mori,Jose A. Lozano
This work addresses time series classifier recommendation for the first time in the literature by considering several recommendation forms or meta-targets: classifier accuracies, complete ranking, top-M ranking, best set and best classifier. For this, an ad-hoc set of quick estimators of the…
Elsevier BV
Pulseless electrical activity in in-hospital cardiac arrest – A crossroad for decisions
Authors: Norvik, A.,Unneland, E.,Bergum, D.,Buckler, D.G.,Bhardwaj, A.,Eftestøl, T.,Aramendi Ecenarro, Elisabete,Nordseth, T.,Abella, B.S.,Kvaløy, J.T.,Skogvoll, E.
PEA is often seen during resuscitation, either as the presenting clinical state in cardiac arrest or as a secondary rhythm following transient return of spontaneous circulation (ROSC), ventricular fibrillation/tachycardia (VF/VT), or asystole (ASY). The aim of this study was to explore and quantify…
Elsevier BV
Airway strategy and ventilation rates in the pragmatic airway resuscitation trial
Authors: Henry E, Wang,Xabier, Jaureguibeitia,Elisabete, Aramendi,Graham, Nichol,Tom, Aufderheide,Mohamud R, Daya,Matthew, Hansen,Michelle, Nassal,Ashish R, Panchal,Dhimitri A, Nikolla,Erik, Alonso,Jestin, Carlson,Robert H, Schmicker,Shannon W, Stephens,Unai,…
We sought to describe ventilation rates during out-of-hospital cardiac arrest (OHCA) resuscitation and their associations with airway management strategy and outcomes.We analyzed continuous end-tidal carbon dioxide capnography data from adult OHCA enrolled in the Pragmatic Airway Resuscitation…
Elsevier BV