☆ 4.7 Article

Fourier Graph Convolution Network for Time Series Prediction

MATHEMATICS (2023)

Related references

Note: Only part of the references are listed.

Article Engineering, Multidisciplinary

Partial differential grey model based on control matrix and its application in short-term traffic flow prediction

Huiming Duan et al.

Summary: Short-term traffic flow analysis is crucial for the intelligent transportation system and traffic management. Accurate prediction of short-term traffic flow provides reliable information for traffic control and guidance, improving travel efficiency.

APPLIED MATHEMATICAL MODELLING (2023)

Add to Collection

Article Automation & Control Systems

Partial Connection Based on Channel Attention for Differentiable Neural Architecture Search

Yu Xue et al.

Summary: This article proposes ADARTS, a differentiable neural architecture search method based on channel attention. By selecting channels with higher weights, important feature information is transmitted into the search space, leading to improved search efficiency and memory utilization, and avoiding the instability caused by random selection.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

Principal graph embedding convolutional recurrent network for traffic flow prediction

Yang Han et al.

Summary: As an essential part of traffic management, traffic flow prediction attracts worldwide attention. Existing methods have limitations in addressing data drift and overfitting. To overcome these challenges, we propose a novel model PGECRN that embeds the adjacency matrix to solve data drift and combines temporal variation and spatial correlations for accurate prediction.

APPLIED INTELLIGENCE (2023)

Add to Collection

Article Engineering, Civil

Dynamic Graph Convolution Network for Traffic Forecasting Based on Latent Network of Laplace Matrix Estimation

Kan Guo et al.

Summary: Traffic forecasting is a challenging problem due to the complexity and non-stationary nature of traffic data. Graph Convolution Network (GCN) based methods have shown promising performance in this area. However, current methods lack the utilization of spatial and temporal properties in graph construction. This paper proposes a novel dynamic graph convolution network that adaptively constructs dynamic road network graphs for traffic forecasting, achieving better performance than state-of-the-art methods.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

An improved dynamic Chebyshev graph convolution network for traffic flow prediction with spatial-temporal attention

Lyuchao Liao et al.

Summary: Accurate traffic flow prediction is crucial for urban traffic management, but there are limitations in exploring the dynamic characteristics of road networks using static learning methods and neglecting the dynamic global temporal and spatial properties. To tackle these issues, this paper proposes an improved dynamic Chebyshev graph convolutional neural network model called iDCGCN, which demonstrates superior performance through experimental results.

APPLIED INTELLIGENCE (2022)

Add to Collection

Article Engineering, Civil

A Short-Term Traffic Flow Prediction Model Based on an Improved Gate Recurrent Unit Neural Network

Wanneng Shu et al.

Summary: This paper explores the use of GRU neural network for traffic flow prediction, introducing an improved Bi-GRU prediction model to demonstrate its effectiveness.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Multi-Objective Feature Selection With Missing Data in Classification

Yu Xue et al.

Summary: Feature selection is a key topic in machine learning, but unreliable results may occur when facing missing data. This study proposes a novel FS modeling approach by introducing reliability as a third objective and applying the NSGA-III algorithm to address the issue. Experimental results demonstrate the effectiveness of this three-objective model coupled with NSGA-III in solving the problem.

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE (2022)

Add to Collection

Article Engineering, Civil

Dynamic Spatial-Temporal Representation Learning for Traffic Flow Prediction

Lingbo Liu et al.

Summary: Traffic flow prediction is a critical component in intelligent transportation systems, and a unified neural network called ATFM has been proposed to effectively learn spatial-temporal feature representations of traffic flow using an attention mechanism. Two deep learning frameworks based on ATFM have shown superior performance in predicting citywide short-term/long-term traffic flow, as well as forecasting passenger pickup/dropoff demands in traffic prediction. Extensive experiments have demonstrated the method's superiority, with code and data available for further exploration.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Traffic flow prediction over muti-sensor data correlation with graph convolution network

Wei Li et al.

Summary: This paper proposes a novel Multisensor Data Correlation Graph Convolution Network model, named MDCGCN, to address the spatial-temporal correlation issues in traffic flow prediction. Experimental results show that the proposed model can significantly improve the medium and long-term prediction accuracy for traffic networks of different sizes, and outperforms existing prediction methods.

NEUROCOMPUTING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

A Self-Adaptive Mutation Neural Architecture Search Algorithm Based on Blocks

Yu Xue et al.

Summary: The paper proposes a neural architecture search algorithm based on self-adaptive mutation strategy, which outperforms competitors in terms of classification performance and consumes fewer computing resources on CIFAR10 and CIFAR100 datasets.

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE (2021)

Add to Collection

Article Engineering, Civil

Approach for Short-Term Traffic Flow Prediction Based on Empirical Mode Decomposition and Combination Model Fusion

Zhongda Tian

Summary: This paper proposes a novel short-term traffic flow prediction approach based on empirical mode decomposition and combination model fusion, which outperforms state-of-the-art prediction methods or models in short-term traffic flow prediction according to experimental results.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2021)

Add to Collection

Article Green & Sustainable Science & Technology

Traffic Flow Prediction at Varied Time Scales via Ensemble Empirical Mode Decomposition and Artificial Neural Network

Xinqiang Chen et al.

SUSTAINABILITY (2020)

Add to Collection

Article Engineering, Civil

T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction

Ling Zhao et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Short-term traffic flow prediction: From the perspective of traffic flow decomposition

Li Chen et al.

NEUROCOMPUTING (2020)

Add to Collection

Article Computer Science, Information Systems

Self-Adaptive Particle Swarm Optimization for Large-Scale Feature Selection in Classification

Yu Xue et al.

ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA (2019)

Add to Collection

Article Engineering, Civil

Deep Spatial-Temporal 3D Convolutional Neural Networks for Traffic Data Forecasting

Shengnan Guo et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2019)

Add to Collection

Article Biochemistry & Molecular Biology

Molecular graph convolutions: moving beyond fingerprints

Steven Kearnes et al.

JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN (2016)

Add to Collection

Article Transportation Science & Technology

A hybrid short-term traffic flow forecasting method based on spectral analysis and statistical volatility model

Yanru Zhang et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2014)

Add to Collection

Article Engineering, Electrical & Electronic

An Interactive Procedure to Preserve the Desired Edges during the Image Processing of Noise Reduction

Chih-Yu Hsu et al.

EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING (2010)

Add to Collection

Article Engineering, Civil

A Bayesian network approach to traffic flow forecasting

SL Sun et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2006)

Add to Collection

Article Economics

Risk and volatility: Econometric models and financial practice

R Engle

AMERICAN ECONOMIC REVIEW (2004)

Add to Collection

Article Engineering, Civil

Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: Theoretical basis and empirical results

BM Williams et al.

JOURNAL OF TRANSPORTATION ENGINEERING (2003)

Add to Collection

© Peeref 2019-2024. All rights reserved.