Long sequence time-series forecasting with deep learning: A survey
The development of deep learning technology has brought great improvements to the field
of time series forecasting. Short sequence time-series forecasting no longer satisfies the …
of time series forecasting. Short sequence time-series forecasting no longer satisfies the …
Attention mechanisms and their applications to complex systems
A Hernández, JM Amigó - Entropy, 2021 - mdpi.com
Deep learning models and graphics processing units have completely transformed the field
of machine learning. Recurrent neural networks and long short-term memories have been …
of machine learning. Recurrent neural networks and long short-term memories have been …
Informer: Beyond efficient transformer for long sequence time-series forecasting
Many real-world applications require the prediction of long sequence time-series, such as
electricity consumption planning. Long sequence time-series forecasting (LSTF) demands a …
electricity consumption planning. Long sequence time-series forecasting (LSTF) demands a …
Tsmae: a novel anomaly detection approach for internet of things time series data using memory-augmented autoencoder
With the development of communication, the Internet of Things (IoT) has been widely
deployed and used in industrial manufacturing, intelligent transportation, and healthcare …
deployed and used in industrial manufacturing, intelligent transportation, and healthcare …
DSTP-RNN: A dual-stage two-phase attention-based recurrent neural network for long-term and multivariate time series prediction
Y Liu, C Gong, L Yang, Y Chen - Expert Systems with Applications, 2020 - Elsevier
Long-term prediction of multivariate time series is still an important but challenging problem.
The key to solve this problem is capturing (1) the spatial correlations at the same time,(2) the …
The key to solve this problem is capturing (1) the spatial correlations at the same time,(2) the …
Joint modeling of local and global temporal dynamics for multivariate time series forecasting with missing values
Multivariate time series (MTS) forecasting is widely used in various domains, such as
meteorology and traffic. Due to limitations on data collection, transmission, and storage, real …
meteorology and traffic. Due to limitations on data collection, transmission, and storage, real …
[HTML][HTML] Assessing the performance of deep learning models for multivariate probabilistic energy forecasting
Deep learning models have the potential to advance the short-term decision-making of
electricity market participants and system operators by capturing the complex dependences …
electricity market participants and system operators by capturing the complex dependences …
FC-GAGA: Fully connected gated graph architecture for spatio-temporal traffic forecasting
BN Oreshkin, A Amini, L Coyle, M Coates - Proceedings of the AAAI …, 2021 - ojs.aaai.org
Forecasting of multivariate time-series is an important problem that has applications in traffic
management, cellular network configuration, and quantitative finance. A special case of the …
management, cellular network configuration, and quantitative finance. A special case of the …
TrajGAT: A graph-based long-term dependency modeling approach for trajectory similarity computation
Computing trajectory similarities is a critical and fundamental task for various spatial-
temporal applications, such as clustering, prediction, and anomaly detection. Traditional …
temporal applications, such as clustering, prediction, and anomaly detection. Traditional …
[HTML][HTML] A multivariate time series graph neural network for district heat load forecasting
Heat load prediction is essential for energy efficiency and carbon reduction in district heating
systems. However, heat load is influenced by many factors, such as building characteristics …
systems. However, heat load is influenced by many factors, such as building characteristics …