A5034712928- Fractional Differential Equations Solutions
- Complex Systems and Time Series Analysis
- Chaos control and synchronization
- COVID-19 epidemiological studies
- stochastic dynamics and bifurcation
- Hate Speech and Cyberbullying Detection
- SARS-CoV-2 and COVID-19 Research
- Authorship Attribution and Profiling
- Diffusion and Search Dynamics
- COVID-19 diagnosis using AI
- Probabilistic and Robust Engineering Design
- Time Series Analysis and Forecasting
- Advanced Mathematical Modeling in Engineering
- Neural Networks and Applications
- Climate Change Policy and Economics
- NMR spectroscopy and applications
- Viral Infections and Outbreaks Research
- Innovation, Sustainability, Human-Machine Systems
- Energy Load and Power Forecasting
- Nonlinear Dynamics and Pattern Formation
- Numerical methods for differential equations
- Image and Signal Denoising Methods
- Evolution and Genetic Dynamics
- Model Reduction and Neural Networks
- Gene Regulatory Network Analysis
Universitat Politècnica de València
2019-2025
Valencian International University
2022-2025
Artificial Intelligence Research Institute
2023
Deviations from Brownian motion leading to anomalous diffusion are ubiquitously found in transport dynamics, playing a crucial role phenomena quantum physics life sciences. The detection and characterization of the measurement an individual trajectory challenging tasks, which traditionally rely on calculating mean squared displacement trajectory. However, this approach breaks down for cases important practical interest, e.g., short or noisy trajectories, ensembles heterogeneous non-ergodic...
The 2030 Agenda of the United Nations (UN) revolves around Sustainable Development Goals (SDGs). A critical step towards that objective is identifying whether scientific production aligns with SDGs' achievement. To assess this, funders and research managers need to manually estimate impact their funding agenda on SDGs, focusing accuracy, scalability, objectiveness. With this in mind, work, we develop ASDG, an easy-to-use Artificial-Intelligence-based model for automatically potential papers...
Abstract The results of the Anomalous Diffusion Challenge (AnDi Challenge) (Muñoz-Gil G et al 2021 Nat. Commun. 12 6253) have shown that machine learning methods can outperform classical statistical methodology at characterization anomalous diffusion in both inference exponent α associated with each trajectory (Task 1), and determination underlying diffusive regime which produced such trajectories 2). Furthermore, five teams finished top three across tasks AnDi Challenge, those used...
Controlling the healthfulness of breeding sows is one most critical factors in pig farms since, throughout production process, show continuous changes their general condition due to motherhood. However, existing approaches for estimating body are mostly manual and low precision, which limit its automated calculation subsequent management. To contribute this area, we propose an IoT Information System measuring controlling degree reserves based on calculations that use two actual physical...
Anomalous diffusion is characterized by nonlinear growth in the mean square displacement of a trajectory. Recent advances using statistical methods and recurrent neural networks have made it possible to detect such phenomena, even noisy conditions. In this work, we explore feature extraction through parametric non-parametric spectral analysis decode anomalously diffusing trajectories, achieving reduced computational costs compared with other approaches that require additional data or prior...
Anomalous diffusion is present at all scales, from atomic to large ones. Some exemplary systems are ultracold atoms, telomeres in the nucleus of cells, moisture transport cement-based materials, arthropods' free movement, and birds' migration patterns. The characterization gives critical information about dynamics these provides an interdisciplinary framework with which study diffusive transport. Thus, problem identifying underlying regimes inferring anomalous exponent α high confidence...
Abstract Anomalous diffusion occurs at very different scales in nature, from atomic systems to motions cell organelles, biological tissues or ecology, and also artificial materials, such as cement. Being able accurately measure the anomalous exponent associated a given particle trajectory, thus determining whether subdiffuses, superdiffuses performs normal diffusion, is of key importance understand process. Also it often important trustingly identify model behind this gives large amount...
This document describes a text change of representation approach to the task Multilingual Detection Hate Speech Against Immigrants and Women in Twitter, as part SemEval-2019 1 . The is divided two sub-tasks. Sub-task A consists classifying tweets being hateful or not hateful, whereas sub-task B requires fine tuning classification by directed single individuals generic, if tweet aggressive not. Our space into statistical descriptors which characterize text. In addition, dimensional reduction...
The classification of time series using machine learning (ML) analysis and entropy-based features is an urgent task for the study nonlinear signals in fields finance, biology medicine, including EEG Brain–Computer Interfacing. As several entropy measures exist, problem assessing effectiveness entropies used as ML dynamics series. We propose a method, called global efficiency (GEFMCC), chaotic mappings. GEFMCC fitness function optimizing type parameters problems. analyze fuzzy (FuzzyEn)...
Abstract We infer the parameters of fractional discrete Wu Baleanu time series by using machine learning architectures based on recurrent neural networks. Our results shed light how clearly one can determine that a given trajectory comes from specific dynamical system estimating exponent and growth parameter $$\mu $$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>μ</mml:mi> </mml:math> . With this example, we also show methods be incorporated into study systems.
We study the accuracy of machine learning methods for inferring parameters noisy fractional Wu-Baleanu trajectories with some missing initial terms. Our model is based on a combination convolutional and recurrent neural networks (LSTM), which permits extraction characteristics from while preserving time dependency. show that these approach exhibit good results despite poor quality data.
The evolution of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in humans has been monitored at an unprecedented level due to the public health crisis, yet stochastic dynamics underlying such a process is dubious. Here, considering number acquired mutations as displacement viral particle from origin, we performed biostatistical analyses numerous whole genome sequences on basis time-dependent probabilistic mathematical model. We showed that model with constant variant-dependent...
Abstract We adapt the Covasim agent-based model for predicting new COVID-19 cases by tuning transmissibility rate with information on impact of most common non-pharmaceutical interventions (NPIs) obtained through machine learning models. Such has been estimated thanks to applying pools NPIs worldwide from Oxford Government Response Tracker. This approach permits simulation a whole country or smaller region, providing about asymptomatic, recovery, severe, and critical enabling governments...
<p>Anomalous diffusion (AD) describes transport phenomena where the mean-square displacement (MSD) of a particle does not scale linearly with time, deviating from classical diffusion. This behavior, often linked to non-equilibrium phenomena, sheds light on underlying mechanisms in various systems, including biological and financial domains.</p><p>Integrating insights anomalous into analysis could significantly improve our understanding market behaviors, similar their...
We show how machine learning methods can unveil the fractional and delayed nature of discrete dynamical systems. In particular, we study case logistic map. that given a trajectory, detect if it has some delay effect or not, also to characterize component underlying generation model.
We describe the deep learning-based COVID-19 cases predictor and Pareto-optimal Non-Pharmaceutical Intervention (NPI) prescriptor developed by winning team of 500k XPRIZE Pandemic Response Challenge. The competition aimed at developing data-driven AI models to predict infection rates prescribe NPI Plans that governments, business leaders organizations could implement minimize harm when reopening their economies. In addition validation performed with real data, our were validated in a...
The recent success of biological engineering is due to a tremendous amount research effort and the increasing number market opportunities. Indeed, this has been partially possible contribution advanced mathematical tools application principles in genetic-circuit development. In work, we use rationally designed genetic circuit show how models can support motivate students apply mathematics their future careers. A four-state machine analyzed using three frameworks: deterministic stochastic...
Abstract We infer the parameters of fractional discrete Wu-Baleanu time series by using machine learning architectures based on recurrent neural networks. Our results shed light how clearly one can determine that a given trajectory comes from specific dynamical system estimating exponent and scaling factor.