Convolutional low-rank tensor representation for structural missing traffic data imputation

BZ Li, XL Zhao, X Chen, M Ding… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Recently, low-rank tensor completion (LRTC) methods by exploiting the global low-rankness
of the target tensor have shown great potential for traffic data imputation. However, in real …

EvolutionViT: Multi-objective evolutionary vision transformer pruning under resource constraints

L Liu, GG Yen, Z He - Information Sciences, 2025‏ - Elsevier
Abstract Vision Transformer (ViT) has emerged as a pivotal model for a variety of visual
tasks, surpassing convolutional neural networks by a substantial margin. However, the …

A fast matrix autoregression algorithm based on Tucker decomposition for online prediction of nonlinear real-time taxi-hailing demand without pre-training

Z Xu, Z Lv, B Chu, J Li - Chaos, Solitons & Fractals, 2024‏ - Elsevier
Online prediction of real-time taxi-hailing demand generally provides better real-time
decision support for passengers and taxi drivers compared with offline prediction. Current …

Anti-circulant dynamic mode decomposition with sparsity-promoting for highway traffic dynamics analysis

X Wang, L Sun - Transportation research part C: emerging technologies, 2023‏ - Elsevier
Highway traffic state data collected from a network of sensors can be considered as a high-
dimensional nonlinear dynamical system. In this paper, we develop a novel data-driven …

Forecasting high-dimensional spatio-temporal systems from sparse measurements

J Song, Z Song, P Ren, NB Erichson… - Machine Learning …, 2024‏ - iopscience.iop.org
This paper introduces a new neural network architecture designed to forecast high-
dimensional spatio-temporal data using only sparse measurements. The architecture uses a …

[HTML][HTML] A Regionalization Approach Based on the Comparison of Different Clustering Techniques

JL Aguilar Colmenero, J Portela Garcia-Miguel - Applied Sciences, 2024‏ - mdpi.com
For biodiversity conservation and the development of protected areas, it is essential to
create strategic plans that ensure the preservation and sustainable use of natural resources …

Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting

W Chen, Y Liang - arxiv preprint arxiv:2410.12593, 2024‏ - arxiv.org
The widespread deployment of sensing devices leads to a surge in data for spatio-temporal
forecasting applications such as traffic flow, air quality, and wind energy. Although spatio …

Spatiotemporal regularized tucker decomposition approach for traffic data imputation

W Gong, Z Huang, L Yang - arxiv preprint arxiv:2305.06563, 2023‏ - arxiv.org
In intelligent transportation systems, traffic data imputation, estimating the missing value from
partially observed data is an inevitable and challenging task. Previous studies have not fully …

Guaranteed Multidimensional Time Series Prediction via Deterministic Tensor Completion Theory

H Shu, J Li, Y **, H Wang - arxiv preprint arxiv:2501.15388, 2025‏ - arxiv.org
In recent years, the prediction of multidimensional time series data has become increasingly
important due to its wide-ranging applications. Tensor-based prediction methods have …

[كتاب][B] Low-rank Models for Spatiotemporal Traffic Data Analysis

X Wang - 2024‏ - search.proquest.com
Smart cities have gained substantial attention due to rapid urbanization and the need to
transform congested urban areas into sustainable, efficient, and safe environments …