A5042326416- Advanced Multi-Objective Optimization Algorithms
- Metaheuristic Optimization Algorithms Research
- Evolutionary Algorithms and Applications
- Anomaly Detection Techniques and Applications
- Neural Networks and Applications
- Model Reduction and Neural Networks
- Finance, Taxation, and Governance
- Machine Learning and Data Classification
- Probabilistic and Robust Engineering Design
- Computational Physics and Python Applications
- Topic Modeling
- Artificial Immune Systems Applications
- Economic Theory and Policy
- Fuzzy Logic and Control Systems
- Time Series Analysis and Forecasting
- Risk and Safety Analysis
- Data Quality and Management
- Water Systems and Optimization
- Fault Detection and Control Systems
- Advanced Neural Network Applications
- Advanced Control Systems Optimization
- Reservoir Engineering and Simulation Methods
- Occupational Health and Safety Research
- Semantic Web and Ontologies
- Context-Aware Activity Recognition Systems
Inria Chile
2019-2025
Hospital d'Igualada
2024
Institute of Computing Technology
2021
Universidade Federal Fluminense
2015-2019
Institut national de recherche en informatique et en automatique
2016-2017
Laboratoire de Recherche en Informatique
2016-2017
Centre National de la Recherche Scientifique
2016-2017
Université Paris-Saclay
2016-2017
Université Paris-Sud
2016
Pontifical Catholic University of Rio de Janeiro
2013-2015
Anomaly detection is the problem of finding patterns in data that do not conform to an a priori expected behavior. This related which some samples are distant, terms given metric, from rest dataset, where these anomalous indicated as outliers. has recently attracted attention research community, because its relevance real-world applications, like intrusion detection, fraud fault and system health monitoring, among many others. Anomalies themselves can have positive or negative nature,...
In this work we put forward a comprehensive study on the design of global stopping criteria for multi-objective optimization. We describe novel criterion, denominated MGBM criterion that combines mutual domination rate (MDR) improvement indicator with simplified Kalman filter is used evidence gathering process. The MDR indicator, which introduced along, special purpose solution meant task. It capable gauging progress optimization low computational cost and therefore suitable solving complex...
The classic classification scheme for Active Galactic Nuclei (AGNs) was recently challenged by the discovery of so-called changing-state (changing-look) AGNs (CSAGNs). physical mechanism behind this phenomenon is still a matter open debate and samples are too small serendipitous nature to provide robust answers. In order tackle problem, we need design methods that able detect AGN right in act changing-state. Here present an anomaly detection (AD) technique designed identify light curves with...
Frost forecast is an important issue in climate research because of its economic impact on several industries. In this study, we propose GRAST-Frost, a graph neural network (GNN) with spatio-temporal architecture, which used to predict minimum temperatures and the incidence frost. We developed IoT platform capable acquiring weather data from experimental site, addition, were collected 10 stations close proximity aforementioned site. The model considers spatial temporal relations while...
Humanity is getting old fast.By 2050, 30% of mankind will be over 60 years old.Aging gradually compromises people's independence.Ambient Assisted Living (AAL) technologies can help elderly individuals maintain their independence while providing added safety on a daily basis.Multiple sensors monitor seniors' activities to detect situations in which they might need help.Most research this area has targeted indoor environments, but citizen's outdoors are just as important, many risky may...
In this work we present a novel and efficient algorithm independent stopping criterion, called the MGBM suitable for Multiobjective Optimization Evolutionary Algorithms (MOEAs). The after each iteration of optimization algorithm, gathers evidence improvement solutions obtained so far. A global (execution wise) accumulation process inspired by recursive Bayesian estimation decides when should be stopped. Evidenceis collected using relative measure constructed on top Pareto dominance...
In this paper we explore the model-building issue of multiobjective optimization estimation distribution algorithms. We argue that has some characteristics differentiate it from other machine learning tasks. A novel algorithm called neural (MONEDA) is proposed to meet those characteristics. This uses a custom version growing gas (GNG) network specially meant for task. As part work, MONEDA assessed with regard classical and state-of-the-art evolutionary optimizers when solving community...
The multi-objective optimization neural estimation of distribution algorithm (MONEDA) was devised with the purpose dealing model-building issues MOEDAs and, therefore address their scalability.
The need for a stopping criterion in MOEA's is repeatedly mentioned matter the domain of MOOP's, even though it usually left aside as secondary, while criteria are still based on an a-priori chosen number maximum iterations. In this paper we want to present three different indicators already community. These indicators, some which were originally designed solution quality measuring (as function distance optimal Pareto front), will be processed so they can applied part global criterion,...
The carbon pump of the world's ocean plays a vital role in biosphere and climate earth, urging improved understanding functions influences for change analyses. State-of-the-art techniques are required to develop models that can capture complexity currents temperature flows. This work explores benefits using physics-informed neural networks (PINNs) solving partial differential equations related modeling; such as Burgers, wave, advection-diffusion equations. We explore trade-offs data vs....
Context. The chemical composition of a star’s atmosphere reflects the its birth environment. Therefore, it should be feasible to recognize stars born together that have scattered throughout galaxy, solely based on their chemistry. This concept, known as “strong tagging”, is major objective spectroscopic studies, but has yet yield anticipated results. Aims. We assess existence and robustness relation between abundances birthplace using member open clusters. Methods. followed supervised...
Soft computing methods, and Multi-Objective Evolutionary Algorithms (MOEAs) in particular, lack a general convergence criterion which prevents these algorithms from detecting the generation where further evolution will provide little improvements (or none at all) over current solution, making them waste computational resources. This paper presents Least Squares Stopping Criterion (LSSC), an easily configurable implementable, robust efficient stopping criterion, based on simple statistical...
In this work we present a novel and efficient algorithm independent stopping criterion, called the MGBM criterion,suitable for Multi-objective Optimization Evolutionary Algorithms(MOEAs).The after each iteration of optimization algorithm, gathers evidence improvement solutions obtained so far. A global (execution wise) accumulation process inspired by recursive Bayesian estimation decides when should be stopped. Evidence is collected using relative measure constructed on top Pareto dominance...