Search Results for author: Lijun Sun

Found 20 papers, 8 papers with code

Hankel-structured Tensor Robust PCA for Multivariate Traffic Time Series Anomaly Detection

no code implementations8 Oct 2021 Xudong Wang, Luis Miranda-Moreno, Lijun Sun

We treat the raw data with anomalies as a multivariate time series matrix (location $\times$ time) and assume the denoised matrix has a low-rank structure.

Anomaly Detection Time Series

Spatial Aggregation and Temporal Convolution Networks for Real-time Kriging

no code implementations24 Sep 2021 Yuankai Wu, Dingyi Zhuang, MengYing Lei, Aurelie Labbe, Lijun Sun

Specifically, we propose a novel spatial aggregation network (SAN) inspired by Principal Neighborhood Aggregation, which uses multiple aggregation functions to help one node gather diverse information from its neighbors.

Dynamic Spatiotemporal Graph Convolutional Neural Networks for Traffic Data Imputation with Complex Missing Patterns

no code implementations17 Sep 2021 Yuebing Liang, Zhan Zhao, Lijun Sun

The results show that our proposed model outperforms existing deep learning models in all kinds of missing scenarios and the graph structure estimation technique contributes to the model performance.

Imputation Traffic Data Imputation

Spatially Focused Attack against Spatiotemporal Graph Neural Networks

no code implementations10 Sep 2021 Fuqiang Liu, Luis Miranda-Moreno, Lijun Sun

However, despite that recent studies have demonstrated that deep neural networks (DNNs) are vulnerable to carefully designed perturbations in multiple domains like objection classification and graph representation, current adversarial works cannot be directly applied to spatiotemporal forecasting due to the causal nature and spatiotemporal mechanisms in forecasting models.

Traffic Prediction

Individual Mobility Prediction via Attentive Marked Temporal Point Processes

no code implementations6 Sep 2021 Yuankai Wu, Zhanhong Cheng, Lijun Sun

Individual mobility prediction is an essential task for transportation demand management and traffic system operation.

Point Processes

Scalable Spatiotemporally Varying Coefficient Modeling with Bayesian Kernelized Tensor Regression

no code implementations31 Aug 2021 MengYing Lei, Aurelie Labbe, Lijun Sun

To address this challenge, we summarize the spatiotemporally varying coefficients using a third-order tensor structure and propose to reformulate the spatiotemporally varying coefficient model as a special low-rank tensor regression problem.

Low-Rank Hankel Tensor Completion for Traffic Speed Estimation

no code implementations21 May 2021 Xudong Wang, Yuankai Wu, Dingyi Zhuang, Lijun Sun

This paper studies the traffic state estimation (TSE) problem using sparse observations from mobile sensors.

Matrix Completion

Reducing Bus Bunching with Asynchronous Multi-Agent Reinforcement Learning

no code implementations2 May 2021 Jiawei Wang, Lijun Sun

However, due to the significant uncertainties in passenger demand and traffic conditions, bus operation is unstable in nature and bus bunching has become a common phenomenon that undermines the reliability and efficiency of bus services.

Graph Attention Multi-agent Reinforcement Learning

Low-Rank Autoregressive Tensor Completion for Spatiotemporal Traffic Data Imputation

1 code implementation30 Apr 2021 Xinyu Chen, MengYing Lei, Nicolas Saunier, Lijun Sun

In this paper, we propose a low-rank autoregressive tensor completion (LATC) framework by introducing \textit{temporal variation} as a new regularization term into the completion of a third-order (sensor $\times$ time of day $\times$ day) tensor.

Imputation Time Series +1

One Vertex Attack on Graph Neural Networks-based Spatiotemporal Forecasting

no code implementations1 Jan 2021 Fuqiang Liu, Luis Miranda Moreno, Lijun Sun

Empirical studies prove that perturbations in one vertex can be diffused into most of the graph when spatiotemporal GNNs are under One Vertex Attack.

Graph Classification

Industrial Topics in Urban Labor System

no code implementations18 Sep 2020 Jaehyuk Park, Morgan R. Frank, Lijun Sun, Hyejin Youn

It is therefore important to recognize that classification system are not necessarily static, especially for economic systems, and even more so in urban areas where most innovation takes place and is implemented.

Classification General Classification

Scalable Low-Rank Tensor Learning for Spatiotemporal Traffic Data Imputation

3 code implementations7 Aug 2020 Xinyu Chen, Yixian Chen, Nicolas Saunier, Lijun Sun

Recent studies based on tensor nuclear norm have demonstrated the superiority of tensor learning in imputation tasks by effectively characterizing the complex correlations/dependencies in spatiotemporal data.

Imputation Traffic Data Imputation

Efficient Connected and Automated Driving Systemwith Multi-agent Graph Reinforcement Learning

no code implementations6 Jul 2020 Tianyu Shi, Jiawei Wang, Yuankai Wu, Luis Miranda-Moreno, Lijun Sun

Instead of learning a reliable behavior for ego automated vehicle, we focus on how to improve the outcomes of the total transportation system by allowing each automated vehicle to learn cooperation with each other and regulate human-driven traffic flow.

Decision Making

Incremental Bayesian tensor learning for structural monitoring data imputation and response forecasting

no code implementations1 Jul 2020 Pu Ren, Xinyu Chen, Lijun Sun, Hao Sun

To address this fundamental issue, this paper presents an incremental Bayesian tensor learning method for reconstruction of spatiotemporal missing data in SHM and forecasting of structural response.

Imputation Incremental Learning +1

Low-Rank Autoregressive Tensor Completion for Multivariate Time Series Forecasting

1 code implementation18 Jun 2020 Xinyu Chen, Lijun Sun

In this paper, we propose a low-rank autoregressive tensor completion (LATC) framework to model multivariate time series data.

Imputation Multivariate Time Series Forecasting +2

Inductive Graph Neural Networks for Spatiotemporal Kriging

1 code implementation13 Jun 2020 Yuankai Wu, Dingyi Zhuang, Aurelie Labbe, Lijun Sun

Time series forecasting and spatiotemporal kriging are the two most important tasks in spatiotemporal data analysis.

Time Series Time Series Forecasting

A Nonconvex Low-Rank Tensor Completion Model for Spatiotemporal Traffic Data Imputation

2 code implementations23 Mar 2020 Xinyu Chen, Jinming Yang, Lijun Sun

Sparsity and missing data problems are very common in spatiotemporal traffic data collected from various sensing systems.

Imputation Traffic Data Imputation

Bayesian Temporal Factorization for Multidimensional Time Series Prediction

3 code implementations14 Oct 2019 Xinyu Chen, Lijun Sun

In this paper, we propose a Bayesian temporal factorization (BTF) framework for modeling multidimensional time series -- in particular spatiotemporal data -- in the presence of missing values.

Imputation Time Series +1

Efficient Motion Planning for Automated Lane Change based on Imitation Learning and Mixed-Integer Optimization

1 code implementation18 Apr 2019 Chenyang Xi, Tianyu Shi, Yuankai Wu, Lijun Sun

Traditional motion planning methods suffer from several drawbacks in terms of optimality, efficiency and generalization capability.

Action Generation Autonomous Driving +2

Cooperative coevolution of real predator robots and virtual robots in the pursuit domain

1 code implementation23 Jan 2019 Lijun Sun, Chao Lyu, Yuhui Shi

This paper presents a particle swarm optimization (PSO) based cooperative coevolutionary algorithm for the (predator) robots, called CCPSO-R, where real and virtual robots coexist in an evolutionary algorithm (EA).

Robotics Multiagent Systems

Cannot find the paper you are looking for? You can Submit a new open access paper.