Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/14848
Registo completo
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor.author | Peralta Donate, Juan | - |
dc.contributor.author | Cortez, Paulo | - |
dc.contributor.author | Gutierrez Sanchez, German | - |
dc.contributor.author | Sanchis de Miguel, Araceli | - |
dc.date.accessioned | 2011-12-05T17:37:45Z | - |
dc.date.available | 2011-12-05T17:37:45Z | - |
dc.date.issued | 2011-07 | - |
dc.identifier.isbn | 978-1-4503-0690-4 | - |
dc.identifier.uri | https://hdl.handle.net/1822/14848 | - |
dc.description.abstract | Time Series Forecasting (TSF) is an important tool to sup- port decision making. Artificial Neural Networks (ANN) are innate candidates for TSF due to advantages such as nonlin- ear learning and noise tolerance. However, the search for the best ANN is a complex task that highly affects the forecast- ing performance. In this paper, we propose a novel Sparsely connected Evolutionary ANN (SEANN), which evolves more flexible ANN structures to perform multi-step ahead fore- casts. This approach is compared with a similar strategy but that only evolves fully connected ANNs (FEANN) and a conventional TSF method (i.e. ARIMA methodology). A set of six time series, from different real-world domains, was used in the comparison. Overall, the obtained results re- veal the proposed SEANN approach as the best forecasting method, optimizing more simpler structures and requiring less computational effort when compared with the fully con- nected evolutionary ANN strategy. | por |
dc.description.sponsorship | Community of Madrid under project CCG10-UC3M/TIC-5174. | por |
dc.language.iso | eng | por |
dc.publisher | ACM | por |
dc.rights | openAccess | por |
dc.subject | Connectionism and neural nets | por |
dc.subject | Hybrid systems | por |
dc.subject | estimation distribution algorithm | por |
dc.subject | forecasting | por |
dc.subject | multilayer perceptron | por |
dc.subject | time series | por |
dc.title | Evolving sparsely connected neural networks for multi-step ahead forecasting | por |
dc.type | conferencePaper | por |
dc.peerreviewed | yes | por |
dc.relation.publisherversion | http://dl.acm.org/ | por |
sdum.publicationstatus | published | por |
oaire.citationStartPage | 219 | por |
oaire.citationEndPage | 220 | por |
oaire.citationConferencePlace | Dublin, Ireland | por |
oaire.citationTitle | Proceedings of the 2011 Genetic and Evolutionary Computation Conference (GECCO) | por |
dc.identifier.doi | 10.1145/2001858.2001982 | por |
sdum.conferencePublication | Proceedings of the 2011 Genetic and Evolutionary Computation Conference (GECCO) | por |
Aparece nas coleções: | DSI - Engenharia da Programação e dos Sistemas Informáticos |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
pp191-Peralta.pdf | 111,02 kB | Adobe PDF | Ver/Abrir |