Utilize este identificador para referenciar este registo: http://hdl.handle.net/10198/10765
Título: Comparison of artificial neural network architectures in the task of tourism time series forecast
Autor: Teixeira, João Paulo
Fernandes, Paula O.
Palavras-chave: Artificial neural network architectures
Time series forecast
Data: 2012
Editora: World Academy of Science - Engineering and Technology
Citação: Teixeira, João Paulo; Fernandes, Paula O. (2012) - Comparison of artificial neural network architectures in the task of tourism time series forecast. World Academy of Science, Engineering and Technology (WASET). 66, p 978–983
Resumo: The authors have been developing several models based on artificial neural networks, linear regression models, Box-Jenkins methodology and ARIMA models to predict the time series of tourism. The time series consist in the “Monthly Number of Guest Nights in the Hotels” of one region. Several comparisons between the different type models have been experimented as well as the features used at the entrance of the models. The Artificial Neural Network (ANN) models have always had their performance at the top of the best models. Usually the feed-forward architecture was used due to their huge application and results. In this paper the author made a comparison between different architectures of the ANNs using simply the same input. Therefore, the traditional feed-forward architecture, the cascade forwards, a recurrent Elman architecture and a radial based architecture were discussed and compared based on the task of predicting the mentioned time series.
Peer review: yes
URI: http://hdl.handle.net/10198/10765
Aparece nas colecções:ESTiG - Artigos em Revistas Não Indexados à WoS/Scopus

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
versaodoeditor_v66-182.pdf472,15 kBAdobe PDFVer/Abrir    Acesso Restrito. Solicitar cópia ao autor!

FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Degois 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.