no code implementations • 24 Apr 2024 • ChengYuan Zhang, Kehua Chen, Meixin Zhu, Hai Yang, Lijun Sun
Learning and understanding car-following (CF) behaviors are crucial for microscopic traffic simulation.
no code implementations • 1 Feb 2024 • Vincent Zhihao Zheng, Lijun Sun
Accurately modeling the correlation structure of errors is essential for reliable uncertainty quantification in probabilistic time series forecasting.
Computational Efficiency Probabilistic Time Series Forecasting +2
1 code implementation • 4 Dec 2023 • Jinguo Cheng, Ke Li, Yuxuan Liang, Lijun Sun, Junchi Yan, Yuankai Wu
To address this challenge, we present the Super-Multivariate Urban Mobility Transformer (SUMformer), which utilizes a specially designed attention mechanism to calculate temporal and cross-variable correlations and reduce computational costs stemming from a large number of time series.
no code implementations • 5 Nov 2023 • Dedong Li, Ziyue Li, Zhishuai Li, Lei Bai, Qingyuan Gong, Lijun Sun, Wolfgang Ketter, Rui Zhao
Then, we propose a Multi-view Graph and Complexity Aware Transformer (MGCAT) model to encode these semantics in trajectory pre-training from two aspects: 1) adaptively aggregate the multi-view graph features considering trajectory pattern, and 2) higher attention to critical nodes in a complex trajectory.
no code implementations • 31 Oct 2023 • Ziyue Li, Hao Yan, Chen Zhang, Lijun Sun, Wolfgang Ketter, Fugee Tsung
In this paper, we propose a novel tensor Dirichlet Process Multinomial Mixture model with graphs, which can preserve the hierarchical structure of the multi-dimensional trip information and cluster them in a unified one-step manner with the ability to determine the number of clusters automatically.
1 code implementation • 2 Aug 2023 • Chunwei Yang, Xiaoxu Chen, Lijun Sun, Hongyu Yang, Yuankai Wu
To address this gap, we propose an unsupervised method called Floss that automatically regularizes learned representations in the frequency domain.
1 code implementation • 4 Jul 2023 • Tong Nie, Guoyang Qin, Lijun Sun, Wei Ma, Yu Mei, Jian Sun
Spatiotemporal urban data (STUD) displays complex correlational patterns.
no code implementations • 23 Jun 2023 • Ziyue Li, Hao Yan, Chen Zhang, Andi Wang, Wolfgang Ketter, Lijun Sun, Fugee Tsung
In this paper, we propose a novel Tensor Dirichlet Process Multinomial Mixture model (Tensor-DPMM), which is designed to preserve the multi-mode and hierarchical structure of the multi-dimensional trip information via tensor, and cluster them in a unified one-step manner.
no code implementations • 26 May 2023 • Vincent Zhihao Zheng, Seongjin Choi, Lijun Sun
Deep probabilistic time series forecasting has gained attention for its ability to provide nonlinear approximation and valuable uncertainty quantification for decision-making.
1 code implementation • 4 Mar 2023 • Fan Wu, Zhanhong Cheng, Huiyu Chen, Tony Z. Qiu, Lijun Sun
However, the lack of sensors often results in incomplete traffic state data, making it challenging to obtain reliable information for decision-making.
no code implementations • 28 Feb 2023 • MengYing Lei, Lijun Sun
However, such simple kernel specifications are deficient in learning functions with complex features, such as being nonstationary, nonseparable, and multimodal.
no code implementations • 17 Jan 2023 • Vincent Zhihao Zheng, Seongjin Choi, Lijun Sun
Deep learning models for traffic forecasting often assume the residual is independent and isotropic across time and space.
no code implementations • 10 Dec 2022 • Seongjin Choi, Nicolas Saunier, Vincent Zhihao Zheng, Martin Trepanier, Lijun Sun
Deep learning-based multivariate and multistep-ahead traffic forecasting models are typically trained with the mean squared error (MSE) or mean absolute error (MAE) as the loss function in a sequence-to-sequence setting, simply assuming that the errors follow an independent and isotropic Gaussian or Laplacian distributions.
1 code implementation • 3 Dec 2022 • Xinyu Chen, Zhanhong Cheng, Nicolas Saunier, Lijun Sun
In this study, we first introduce a Laplacian kernel to temporal regularization for characterizing local trends in traffic time series, which can be formulated in the form of circular convolution.
1 code implementation • 28 Nov 2022 • Xinyu Chen, ChengYuan Zhang, Xiaoxu Chen, Nicolas Saunier, Lijun Sun
In the temporal context, the complex time-varying system behaviors can be revealed by the temporal modes in the proposed model.
no code implementations • 21 Aug 2022 • MengYing Lei, Aurelie Labbe, Lijun Sun
Probabilistic modeling of multidimensional spatiotemporal data is critical to many real-world applications.
1 code implementation • 24 Jun 2022 • Lijun Sun, Yu-Cheng Chang, Chao Lyu, Ye Shi, Yuhui Shi, Chin-Teng Lin
The proposed distributed algorithm: fuzzy self-organizing cooperative coevolution (FSC2) is then leveraged to resolve the three challenges in multi-target SOP: distributed self-organizing search (SOS), distributed task allocation, and distributed single-target pursuit.
1 code implementation • 20 Mar 2022 • Xinyu Chen, ChengYuan Zhang, Xi-Le Zhao, Nicolas Saunier, Lijun Sun
Modern time series datasets are often high-dimensional, incomplete/sparse, and nonstationary.
no code implementations • 2 Nov 2021 • Jiawei Wang, Lijun Sun
However, the operation of a bus fleet is unstable in nature, and bus bunching has become a common phenomenon that undermines the efficiency and reliability of bus systems.
no code implementations • 8 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.
1 code implementation • 24 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.
no code implementations • 17 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.
no code implementations • 10 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.
no code implementations • 6 Sep 2021 • Yuankai Wu, Zhanhong Cheng, Lijun Sun
Individual mobility prediction is an essential task for transportation demand management and traffic system operation.
no code implementations • 31 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.
1 code implementation • 21 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.
no code implementations • 2 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.
1 code implementation • 30 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.
no code implementations • 1 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.
no code implementations • 18 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.
2 code implementations • 7 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.
no code implementations • 6 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.
no code implementations • 1 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.
1 code implementation • 18 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.
1 code implementation • 13 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.
1 code implementation • 23 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.
3 code implementations • 14 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.
1 code implementation • 18 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.
1 code implementation • 23 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