4.7 Article

Multivariate Time-Series Forecasting Model: Predictability Analysis and Empirical Study

Related references

Note: Only part of the references are listed.
Article Engineering, Electrical & Electronic

Spatio-temporal adaptive graph convolutional networks for traffic flow forecasting

Qiwei Ma et al.

Summary: Accurate forecasting of traffic flow is crucial for intelligent traffic control. However, the complexity and dynamics of traffic data pose challenges to prediction. Existing methods typically employ complex graph neural network architectures, but fail to consider the strong spatial dependency and the changing spatial correlations of traffic data. To address this, a novel spatio-temporal adaptive graph convolutional networks model (STAGCN) based on deep learning is proposed. It utilizes an adaptive graph generation block to capture both static and dynamic structures, and applies spatio-temporal convolution blocks to capture the spatio-temporal features. Experimental results on public traffic datasets in California, USA demonstrate that the STAGCN model outperforms multiple baseline methods in terms of prediction accuracy.

IET INTELLIGENT TRANSPORT SYSTEMS (2023)

Article Automation & Control Systems

TC-GATN: Temporal Causal Graph Attention Networks With Nonlinear Paradigm for Multivariate Time-Series Forecasting in Industrial Processes

Jince Li et al.

Summary: In this article, a novel prediction model called temporal causal graph attention networks with nonlinear paradigms (TC-GATN) is proposed to capture inherent dependencies on industrial multivariate time-series (MTS). The model utilizes a graph learning algorithm based on Granger causality to extract potential relationships among multiple variables and guide the directional edge connections of the hierarchy. Parallel gated recurrent unit encoders are introduced to perform the nonlinear interaction of node features, while the self-attention mechanism aggregates encoder hidden states across all stages. A temporal module is added to process information from the graph layer, achieving satisfactory predictions. The feasibility and effectiveness of TC-GATN are validated using two actual datasets.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2023)

Article Computer Science, Information Systems

Graph correlated attention recurrent neural network for multivariate time series forecasting

Xiulin Geng et al.

Summary: Multivariate time series (MTS) forecasting is a pressing problem, and attention-based methods can alleviate the limitations of recurrent neural networks. However, they fail to learn time-varying patterns. To address this, a GCAR model is proposed, which exhibits stability and achieves the highest predictive accuracy in experiments.

INFORMATION SCIENCES (2022)

Article Engineering, Civil

Adaptive Spatiotemporal Dependence Learning for Multi-Mode Transportation Demand Prediction

Haihui Xu et al.

Summary: In this paper, a Co-Modal Graph Attention neTwork (CMGAT) framework is proposed to uncover the impact of different spatial relationships and traffic mode interactions on traffic demand. The experiments on real-world datasets demonstrate the superiority of the model and highlight the necessity of considering multiple spatial relationships and traffic modes.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Article Engineering, Electrical & Electronic

FDSA-STG: Fully Dynamic Self-Attention Spatio-Temporal Graph Networks for Intelligent Traffic Flow Prediction

Youxiang Duan et al.

Summary: This study proposes a novel framework in the field of traffic flow prediction, which successfully models the intricate structural relationships of the transportation network by improving the attention mechanism and utilizing deep learning technology.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2022)

Article Computer Science, Artificial Intelligence

Predicting Taxi and Uber Demand in Cities: Approaching the Limit of Predictability

Kai Zhao et al.

Summary: This article investigates time series prediction in the context of taxi and Uber demand, addressing two key questions: how the regularity of time series affects prediction accuracy, and how to determine the best prediction algorithm. By using temporal-correlated entropy and testing with 14 million data samples, it is found that deep learning is not always the optimal algorithm, and predictability can assist in selecting the appropriate predictor.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2021)

Article Physics, Multidisciplinary

Examining the Limits of Predictability of Human Mobility

Vaibhav Kulkarni et al.

ENTROPY (2019)

Article Physics, Multidisciplinary

On predictability of time series

Paiheng Xu et al.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2019)

Proceedings Paper Computer Science, Information Systems

Traffic Congestion Prediction by Spatiotemporal Propagation Patterns

Xiaolei Di et al.

2019 20TH INTERNATIONAL CONFERENCE ON MOBILE DATA MANAGEMENT (MDM 2019) (2019)

Proceedings Paper Computer Science, Theory & Methods

Experimental Study of Multivariate Time Series Forecasting Models

Jiaming Yin et al.

PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM '19) (2019)

Article Computer Science, Information Systems

A Survey on Personalized PageRank Computation Algorithms

Sungchan Park et al.

IEEE ACCESS (2019)

Article Physics, Multidisciplinary

A Novel Multivariate Sample Entropy Algorithm for Modeling Time Series Synchronization

David Looney et al.

ENTROPY (2018)

Article Mathematics, Interdisciplinary Applications

Understanding predictability and exploration in human mobility

Andrea Cuttone et al.

EPJ DATA SCIENCE (2018)

Proceedings Paper Computer Science, Information Systems

Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks

Guokun Lai et al.

ACM/SIGIR PROCEEDINGS 2018 (2018)

Article Mathematics, Interdisciplinary Applications

An alternative approach to the limits of predictability in human mobility

Edin Lind Ikanovic et al.

EPJ DATA SCIENCE (2017)

Article Computer Science, Artificial Intelligence

A Bias and Variance Analysis for Multistep-Ahead Time Series Forecasting

Souhaib Ben Taieb et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2016)

Article Engineering, Electrical & Electronic

On the Limits of Predictability in Real-World Radio Spectrum State Dynamics: From Entropy Theory to 5G Spectrum Sharing

Guoru Ding et al.

IEEE COMMUNICATIONS MAGAZINE (2015)

Article Multidisciplinary Sciences

Understanding Human Mobility from Twitter

Raja Jurdak et al.

PLOS ONE (2015)

Article Multidisciplinary Sciences

Approaching the Limit of Predictability in Human Mobility

Xin Lu et al.

SCIENTIFIC REPORTS (2013)

Article Engineering, Electrical & Electronic

Multivariate Multiscale Entropy Analysis

Mosabber Uddin Ahmed et al.

IEEE SIGNAL PROCESSING LETTERS (2012)

Article Multidisciplinary Sciences

Limits of Predictability in Human Mobility

Chaoming Song et al.

SCIENCE (2010)

Article Economics

Direct multi-step estimation and forecasting

Guillaume Chevillon

JOURNAL OF ECONOMIC SURVEYS (2007)

Article Computer Science, Artificial Intelligence

Financial time series forecasting using support vector machines

KJ Kim

NEUROCOMPUTING (2003)

Article Computer Science, Artificial Intelligence

Time series forecasting using a hybrid ARIMA and neural network model

GP Zhang

NEUROCOMPUTING (2003)

Article Economics

The M3-Competition: results, conclusions and implications

S Makridakis et al.

INTERNATIONAL JOURNAL OF FORECASTING (2000)