Publicacións

O CITEEC lidera a investigación en enxeñaría civil e edificación, enfocándose en solucións innovadoras para infraestruturas sostibles e materiais avanzados.

Home > Publicacións

publicacións

Investigación de vangarda para o desenvolvemento sostible

O CITEEC realiza investigación avanzada en enxeñaría civil, materiais, sustentabilidade e infraestruturas. A través de proxectos multidisciplinarios e colaboracións internacionais, xéranse publicacións científicas que abordan retos crave do sector. Nesta sección preséntanse as principais publicacións e resultados obtidos polos nosos grupos de investigación.

Accede a unha ampla variedade de publicacións científicas filtradas por temática, autor, ano e máis. Utiliza os filtros dispoñibles para atopar investigacións relevantes e obter detalles sobre cada unha das nosas contribucións ao avance do coñecemento.

Investigación de vangarda para o desenvolvemento sostible

Show all

2009

Rivero, Daniel; Dorado, Julián; Rabuñal-Dopico, Juan R.; Pazos, Alejandro

Evolving simple feed-forward and recurrent ANNs for signal classification: A comparison Conference

2009, ISBN: 9781424435531, (cited By 8).

Abstract | Links | BibTeX | Etiquetas: Artificial neural networks; Classification tasks; EEG signals; Epileptic seizures; Evolutionary method; Feed-Forward; Hidden neurons; Human expert; Machine learning techniques; Real-world problem; Signal classification; Training parameters, Learning algorithms, Neural networks

@conference{Rivero20092685,

title = {Evolving simple feed-forward and recurrent ANNs for signal classification: A comparison},

author = {Daniel Rivero and Julián Dorado and Juan R. Rabuñal-Dopico and Alejandro Pazos},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-70449395916&doi=10.1109%2fIJCNN.2009.5178621&partnerID=40&md5=19cbca88fdb79d64facaeeed89a4e26e},

doi = {10.1109/IJCNN.2009.5178621},

isbn = {9781424435531},

year  = {2009},

date = {2009-01-01},

urldate = {2009-01-01},

journal = {Proceedings of the International Joint Conference on Neural Networks},

pages = {2685-2692},

abstract = {Among all of the Machine Learning techniques used for classification tasks, Artificial Neural Networks (ANNs) have obtained much success in their applications. However, their development usually requires a manual effort from the human expert in which several parameter configurations (architectures, training parameters, etc) are tried. This paper proposes a new evolutionary method that evolves ANNs without any participation from the human expert. This system can be used to evolve feed-forward and recurrent ANNs. A real-world problem has been used to test the behaviour of this system: detection of epileptic seizures in EEG signals. A comparison of the results obtained using recurrent and feedforward ANNs to solve this problem is presented in this paper. This comparison shows the good accuracies obtained by this method (almost 100%). Moreover, these results show an important feature: the system tries to evolve simple ANNs, with a low number of neurons and connections (in many cases, the networks have only 1 hidden neuron). ©2009 IEEE.},

note = {cited By 8},

keywords = {Artificial neural networks; Classification tasks; EEG signals; Epileptic seizures; Evolutionary method; Feed-Forward; Hidden neurons; Human expert; Machine learning techniques; Real-world problem; Signal classification; Training parameters, Learning algorithms, Neural networks},

pubstate = {published},

tppubtype = {conference}

}