Exploiting the stimuli encoding scheme of evolving Spiking Neural Networks for stream learning
Authors: Lobo, Jesus L.,Oregi, Izaskun,Bifet, Albert,Del Ser, Javier
Stream data processing has lately gained momentum with the arrival of new Big Data scenarios and applications dealing with continuously produced information flows. Unfortunately, traditional machine learning algorithms are not prepared to tackle the specific challenges imposed by data stream…
Elsevier BV
WHY DEEP LEARNING PERFORMS BETTER THAN CLASSICAL MACHINE LEARNING?
Authors: ARTZAI PICON RUIZ,AITOR ALVAREZ GILA,UNAI IRUSTA,JONE ECHAZARRA HUGUET
During the last years, deep learning techniques have demonstrated their capability to outperform traditional machine learning methods in completing complex pattern recognition tasks. In this article we will try to explain the reasons behind this. UK Zhende Publishing Limited Company
Stream Learning in Energy IoT Systems: A Case Study in Combined Cycle Power Plants
Authors: Jesus L. Lobo,Igor Ballesteros,Izaskun Oregi,Javier Del Ser,Sancho Salcedo-Sanz
The prediction of electrical power produced in combined cycle power plants is a key challenge in the electrical power and energy systems field. This power production can vary depending on environmental variables, such as temperature, pressure, and humidity. Thus, the business problem is how to…
MDPI AG
Magnetic field-based arc stability sensor for electric arc furnaces
Authors: Asier Vicente,Artzai Picon,Jose Antonio Arteche,Miguel Linares,Arturo Velasco,Jose Angel Sainz
Abstract During the last decades the strategy to define the optimal Electric Arc Furnaces (EAF) electrical operational parameters has been constantly evolving. Foaming slag practice is currently used to allow high power factors that ensures higher energy efficiency. However, this performance…
Elsevier BV
An optimal scaling to computationally tractable dimensionless models: Study of latex particles morphology formation
Authors: Elena Akhmatskaya,Elena Akhmatskaya,Denys Dutykh,Simone Rusconi,Dmitri Sokolovski,Dmitri Sokolovski,Arghir Zarnescu,Arghir Zarnescu,Arghir Zarnescu
In modelling of chemical, physical or biological systems it may occur that the coefficients, multiplying various terms in the equation of interest, differ greatly in magnitude, if a particular system of units is used. Such is, for instance, the case of the Population Balance Equations (PBE)…
Elsevier BV
On the design of hybrid bio‐inspired meta‐heuristics for complex multiattribute vehicle routing problems
Authors: Ana‐Maria Nogareda,Javier Del Ser,Eneko Osaba,David Camacho
AbstractThis paper addresses a multiattribute vehicle routing problem, the rich vehicle routing problem, with time constraints, heterogeneous fleet, multiple depots, multiple routes, and incompatibilities of goods. Four different approaches are presented and applied to 15 real datasets. They are…
Wiley
Distributed Coordination of Heterogeneous Robotic Swarms Using Stochastic Diffusion Search
Authors: Osaba, Eneko,Del Ser, Javier,Jubeto, Xabier,Iglesias, Andrés,Fister, Iztok,Gálvez, Akemi,Fister, Iztok
The term Swarm Robotics collectively refers to a population of robotic devices that efficiently undertakes diverse tasks in a collaborative way by virtue of computational intelligence techniques. This paradigm has given rise to a profitable stream of contributions in recent years, all sharing a…
Springer International Publishing
An Intelligent Procedure for the Methodology of Energy Consumption in Industrial Environments
Authors: Mendia, Izaskun,Gil-Lopez, Sergio,Del Ser, Javier,Grau, Iñaki,Lejarazu, Adelaida,Maqueda, Erik,Perea, Eugenio
The concern of the industrial sector about the increase of energy costs has stimulated the development of new strategies for the effective management of energy consumption in industrial setups. Along with this growth, the irruption and continuous development of digital technologies have generated…
Springer International Publishing
COEBA: A Coevolutionary Bat Algorithm for Discrete Evolutionary Multitasking
Authors: Osaba, Eneko,Del Ser, Javier,Yang, Xin-She,Iglesias, Andres,Galvez, Akemi
13 pages, 0 figures, paper submitted and accepted in the 11th workshop Computational Optimization, Modelling and Simulation (COMS 2020), part of the International Conference on Computational Science (ICCS 2020) Springer International Publishing
Using External Knowledge to Improve Zero-Shot Action Recognition in Egocentric Videos
Authors: Adrián Núñez-Marcos,Gorka Azkune,Eneko Agirre,Diego López-de-Ipiña,Ignacio Arganda-Carreras
Zero-shot learning is a very promising research topic. For a vision-based action recognition system, for instance, zero-shot learning allows to recognise actions never seen during the training phase. Previous works in zero-shot action recognition have exploited in several ways the visual appearance…
Springer International Publishing
Evaluating Multimodal Representations on Visual Semantic Textual Similarity
Authors: Oier Lopez de Lacalle,Aitor Soroa,Eneko Agirre,Gorka Azkune,Ander Salaberria
The combination of visual and textual representations has produced excellent results in tasks such as image captioning and visual question answering, but the inference capabilities of multimodal representations are largely untested. In the case of textual representations, inference tasks such as…
arXiv
Data Augmentation for Industrial Prognosis Using Generative Adversarial Networks
Authors: Ortego, Patxi,Diez-Olivan, Alberto,Del Ser, Javier,Sierra, Basilio
The Industry 4.0 revolution allows monitoring and intelligent processing of big amounts of data. When monitoring certain assets, very few data is found for operation under faulty conditions because the cost of not operating properly is unacceptable and thus preventive strategies are put in practice…
Springer International Publishing
A Deep Neural Network as Surrogate Model for Forward Simulation of Borehole Resistivity Measurements
Authors: Florian Sobieczky,Bernhard Moser,Mostafa Shahriari,David Pardo,David Pardo,David Pardo
Inverse problems appear in multiple industrial applications. Solving such inverse problems require the repeated solution of the forward problem. This is the most time-consuming stage when employing inversion techniques, and it constitutes a severe limitation when the inversion needs to be performed…
Elsevier BV
Visualization of Numerical Association Rules by Hill Slopes
Authors: Fister, Iztok,Fister, Dušan,Iglesias, Andres,Galvez, Akemi,Osaba, Eneko,Del Ser, Javier,Fister, Iztok
Association Rule Mining belongs to one of the more prominent methods in Data Mining, where relations are looked for among features in a transaction database. Normally, algorithms for Association Rule Mining mine a lot of association rules, from which it is hard to extract knowledge. This paper…
Springer International Publishing
Design of Loss Functions for Solving Inverse Problems Using Deep Learning
Authors: Rivera, J.A.,Pardo, D.,Alberdi, E.
Solving inverse problems is a crucial task in several applications that strongly affect our daily lives, including multiple engineering fields, military operations, and/or energy production. There exist different methods for solving inverse problems, including gradient based methods, statistics…
Springer International Publishing
Data-Driven Optimization for Transportation Logistics and Smart Mobility Applications [Guest Editorial]
Authors: Eneko Osaba,Javier J. Sanchez Medina,Eleni I. Vlahogianni,Xin-She Yang,Antonio D. Masegosa,Joshue Perez Rastelli,Javier Del Ser
The articles in this special section focus on data driven optimization for transportation and smart mobility applications. We live in an era of major societal and technological changes. Transportation de-carbonization and postindustrial demographic trends, such as massive migrations and an aging…
Institute of Electrical and Electronics Engineers (IEEE)
Parametric Learning of Associative Functional Networks Through a Modified Memetic Self-adaptive Firefly Algorithm
Authors: Akemi Gálvez,Andrés Iglesias,Eneko Osaba,Javier Del Ser
Functional networks are a powerful extension of neural networks where the scalar weights are replaced by neural functions. This paper concerns the problem of parametric learning of the associative model, a functional network that represents the associativity operator. This problem can be formulated…
Springer International Publishing