1 resultado para forecast combination
em Instituto Politécnico de Bragança
Filtro por publicador
- Aberystwyth University Repository - Reino Unido (1)
- Acceda, el repositorio institucional de la Universidad de Las Palmas de Gran Canaria. España (2)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (5)
- AMS Tesi di Laurea - Alm@DL - Università di Bologna (1)
- Aquatic Commons (8)
- Archive of European Integration (23)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (5)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (23)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (6)
- Biblioteca Digital de Teses e Dissertações Eletrônicas da UERJ (1)
- Biodiversity Heritage Library, United States (1)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (148)
- Brunel University (1)
- Cambridge University Engineering Department Publications Database (41)
- CentAUR: Central Archive University of Reading - UK (105)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (75)
- Cochin University of Science & Technology (CUSAT), India (4)
- Collection Of Biostatistics Research Archive (1)
- Comissão Econômica para a América Latina e o Caribe (CEPAL) (3)
- CUNY Academic Works (2)
- Dalarna University College Electronic Archive (2)
- Deakin Research Online - Australia (50)
- DI-fusion - The institutional repository of Université Libre de Bruxelles (7)
- Digital Commons - Michigan Tech (1)
- Digital Peer Publishing (1)
- Digital Repository at Iowa State University (1)
- DigitalCommons@The Texas Medical Center (9)
- Duke University (3)
- eResearch Archive - Queensland Department of Agriculture; Fisheries and Forestry (3)
- Greenwich Academic Literature Archive - UK (2)
- Helda - Digital Repository of University of Helsinki (5)
- Indian Institute of Science - Bangalore - Índia (32)
- Instituto Politécnico de Bragança (1)
- Instituto Politécnico do Porto, Portugal (7)
- Massachusetts Institute of Technology (4)
- Ministerio de Cultura, Spain (2)
- National Center for Biotechnology Information - NCBI (10)
- Plymouth Marine Science Electronic Archive (PlyMSEA) (4)
- Publishing Network for Geoscientific & Environmental Data (4)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (86)
- Queensland University of Technology - ePrints Archive (54)
- ReCiL - Repositório Científico Lusófona - Grupo Lusófona, Portugal (1)
- Repositório digital da Fundação Getúlio Vargas - FGV (11)
- Repositório Digital da UNIVERSIDADE DA MADEIRA - Portugal (3)
- Repositório Institucional da Universidade de Aveiro - Portugal (1)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (96)
- RUN (Repositório da Universidade Nova de Lisboa) - FCT (Faculdade de Cienecias e Technologia), Universidade Nova de Lisboa (UNL), Portugal (1)
- SAPIENTIA - Universidade do Algarve - Portugal (1)
- SerWisS - Server für Wissenschaftliche Schriften der Fachhochschule Hannover (1)
- Universidad de Alicante (2)
- Universidad Politécnica de Madrid (20)
- Universidade Complutense de Madrid (2)
- Universidade de Lisboa - Repositório Aberto (1)
- Universidade Federal do Rio Grande do Norte (UFRN) (2)
- Universitat de Girona, Spain (1)
- Universitätsbibliothek Kassel, Universität Kassel, Germany (2)
- Université de Lausanne, Switzerland (10)
- Université de Montréal, Canada (2)
- University of Connecticut - USA (1)
- University of Michigan (59)
- University of Queensland eSpace - Australia (19)
- WestminsterResearch - UK (2)
- Worcester Research and Publications - Worcester Research and Publications - UK (3)
Resumo:
In this chapter four combinations of input features and the feedforward, cascade forward and recurrent architectures are compared for the task of forecast tourism time series. The input features of the ANNs consist in the combination of the previous 12 months, the index time modeled by two nodes used to the year and month and one input with the daily hours of sunshine (insolation duration). The index time features associated to the previous twelve values of the time series proved its relevance in this forecast task. The insolation variable can improved results with some architectures, namely the cascade forward architecture. Finally, the experimented ANN models/architectures produced a mean absolute percentage error between 4 and 6%, proving the ability of the ANN models based to forecast this time series. Besides, the feedforward architecture behaved better considering validation and test sets, with 4.2% percentage error in test set.