4D hypercomplex-valued neural network in multivariate time series forecasting [PDF]
Scientific ReportsThe goal of this paper is to test three classes of neural network (NN) architectures based on four-dimensional (4D) hypercomplex algebras for multivariate time series forecasting.
Radosław Kycia, Agnieszka Niemczynowicz
doaj +2 more sources
FCP-Former: Enhancing Long-Term Multivariate Time Series Forecasting with Frequency Compensation [PDF]
SensorsLong-term multivariate time series forecasting is crucial for real-world applications, including energy consumption, traffic flow, healthcare, and finance.
Ming Li +5 more
doaj +2 more sources
Improving long-term multivariate time series forecasting with a seasonal-trend decomposition-based 2-dimensional temporal convolution dense network [PDF]
Scientific ReportsImproving the accuracy of long-term multivariate time series forecasting is important for practical applications. Various Transformer-based solutions emerging for time series forecasting.
Jianhua Hao, Fangai Liu
doaj +2 more sources
A novel extreme adaptive GRU for multivariate time series forecasting [PDF]
Scientific ReportsMultivariate time series forecasting is a critical problem in many real-world scenarios. Recent advances in deep learning have significantly enhanced the ability to tackle such problems.
Yifan Zhang +3 more
doaj +2 more sources
Attention-Based Models for Multivariate Time Series Forecasting: Multi-step Solar Irradiation Prediction [PDF]
HeliyonBangladesh's subtropical climate with an abundance of sunlight throughout the greater portion of the year results in increased effectiveness of solar panels.
Sadman Sakib +7 more
doaj +2 more sources
Sparse transformer with local and seasonal adaptation for multivariate time series forecasting [PDF]
Scientific ReportsTransformers have achieved remarkable performance in multivariate time series(MTS) forecasting due to their capability to capture long-term dependencies.
Yifan Zhang +3 more
doaj +2 more sources
Skip-RCNN: A Cost-Effective Multivariate Time Series Forecasting Model
IEEE Access, 2023 Multivariate time series (MTS) forecasting is a crucial aspect in many classification and regression tasks. In recent years, deep learning models have become the mainstream framework for MTS forecasting. Among these deep learning methods, the transformer
Haitao Song +6 more
doaj +1 more source
Forecasting Multivariate Time Series with the Theta Method [PDF]
Journal of Forecasting, 2015 AbstractIn this study building on earlier work on the properties and performance of the univariate Theta method for a unit root data‐generating process we: (a) derive new theoretical formulations for the application of the method on multivariate time series; (b) investigate the conditions for which the multivariate Theta method is expected to forecast ...
Dimitrios D. Thomakos +1 more
openaire +1 more source
Hierarchical Joint Graph Learning and Multivariate Time Series Forecasting
IEEE Access, 2023 Multivariate time series is prevalent in many scientific and industrial domains. Modeling multivariate signals is challenging due to their long-range temporal dependencies and intricate interactions–both direct and indirect.
Juhyeon Kim +5 more
doaj +1 more source
Multivariate time series prediction of high dimensional data based on deep reinforcement learning [PDF]
E3S Web of Conferences, 2021 In order to improve the prediction accuracy of high-dimensional data time series, a high-dimensional data multivariate time series prediction method based on deep reinforcement learning is proposed. The deep reinforcement learning method is used to solve
Ji Xin +5 more
doaj +1 more source