Information Sciences, Technologies and Architecture Research Center

Financiador

Organização

Publicações

Neural Hierarchical Interpolation Time Series (NHITS) for Reservoir Level Multi-Horizon Forecasting in Hydroelectric Power Plants

Publication . Stefenon, Stefano Frizzo; Seman, Laio Oriel; Yamaguchi, Cristina Keiko; Coelho, Leandro Dos Santos; Mariani, Viviana Cocco; Matos-Carvalho, Joao Pedro; Leithardt, Valderi Reis Quietinho; UNINOVA-Instituto de Desenvolvimento de Novas Tecnologias; Institute of Electrical and Electronics Engineers (IEEE)

Energy planning in systems heavily influenced by hydroelectric power is based on assessing the availability of water in the future. In Brazil, based on the soil moisture active passive, the National Electricity System Operator defines electricity dispatch concerning a stochastic optimization problem. Currently, machine learning models are an alternative for improving forecasts, and could be a promising solution for predicting reservoir levels at hydroelectric dams. In this paper, neural hierarchical interpolation for time series (NHITS) is applied to improve forecasts and thus help decision-making in the management of electric power systems. The NHITS model achieved a root mean square error of 4.64×10-4 for a 1-hour forecast horizon, and 1.03×10-3for a 10-hour forecast horizon, being superior to multilayer perceptron (MLP) neural network, long short-term memory (LSTM), convolutional neural network with long short-term memory (CNN-LSTM), recurrent neural network (RNN), Dilated RNN, temporal convolutional neural (TCN), neural basis expansion analysis for interpretable time series forecasting (N-BEATS), and deep non-parametric time series forecaster (DeepNPTS) deep learning approaches.

2025Artigo científico

Acesso aberto

Ver mais

Electronic Word-of-Mouth and Tourist Satisfaction in Rural Tourism in Schist Villages

Publication . Santos, Marta; Rita, Paulo; Moro, Sérgio; Alturas, Bráulio; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management School

Consumers' decision-making processes and the way they purchase their products and services have been evolving over the years due to the influence of information technologies. Tourists are increasingly making their decisions based on online reviews made by other users, which contain descriptive comments and/or a rating system, leveraging electronic word-of-mouth (eWOM). This study aims to understand the variation of the eWOM in rural tourism as well as unveil the main characteristics that influence the satisfaction and the interest of the consumers. To that end, the content of the comments and quantitative classification of Portuguese schist villages' lodgings on the platforms of TripAdvisor and Facebook were studied using both sentiment polarity and frequency analysis. The results show that eWOM has increased in rural tourism and that the satisfaction of tourists are more influenced by the friendliness of the hosts, the variety and good breakfast or Portuguese cuisine, and the service provided.

2023-08-01Capítulo de livro

Acesso aberto

Ver mais

Entidade financiadora

Fundação para a Ciência e a Tecnologia

Programa de financiamento

6817 - DCRRNI ID

Número da atribuição

UIDP/04466/2020