Dynamic Spatial Transformer WaveNet Network for Traffic Forecasting

Traffic forecasting is a challenging task due to complex spatial and temporal dependencies across sensor locations and time. Interest in solving this task has increased, but current research focuses on manually constructing neural network architectures without the aid of neural architecture search (NAS). In our work, we explore evolutionary neural architecture search (ENAS) by deploying a genetic algorithm (GA) to find optimal neural network architectures for predicting traffic conditions. The search space for the GA consists of arbitrary combinations of dilated convolutions and graph convolutions for modelling temporal and spatial dependencies respectively, limited in complexity only by technical constraints. Experimental results show that model architectures obtained via GA are able to match the current state-of-the-art on traffic prediction benchmarks.

PSTFormer: A novel parallel spatial-temporal transformer for remaining useful life prediction of aeroengine

Accurately obtaining accurate information about the future traffic flow of all roads in the transportation network is essential for traffic management and control applications. In order to address the challenges of acquiring dynamic global spatial correlations between transportation links and modeling time dependencies in multi-step prediction, we propose a spatial linear transformer and temporal convolution network (SLTTCN). The model is using spatial linear transformers to aggregate the spatial information of the traffic flow, and bidirectional temporal convolution network to capture the temporal dependency of the traffic flow. The spatial linear transformer effectively reduces the complexity of data calculation and storage while capturing spatial dependence, and the time convolutional network with bidirectional and gate fusion mechanisms avoids the problems of gradient vanishing and high computational cost caused by long time intervals during model training. We conducted extensive experiments using two publicly available large-scale traffic data sets and compared SLTTCN with other baselines. Numerical results show that SLTTCN achieves the best predictive performance in various error measurements. We also performed attention visualization analysis on the spatial linear transformer, verifying its effectiveness in capturing dynamic global spatial dependency.

Traffic forecasting is of great importance to vehicle routing, traffic signal control and urban planning. However, traffic forecasting task is challenging due to several factors, such as complex spatial topological structure and dynamic changing of traffic status. Most existing methods have limited ability to capture both spatial and temporal dependence of traffic data. In this paper, we propose a novel end-to-end deep learning model, Attention based Graph Bi-LSTM networks (AGBN) to perform the traffic forecasting task. It uses graph convolutional network (GCN) to extract spatial features and bidirectional long short-term memory networks (Bi-LSTM) to capture the temporal dependence. The attention mechanism is used to select relevant features at all time steps. Experiments show that our model could extract both spatial and temporal dependence well and outperforms other baselines on real-world traffic datasets.

Dynamic multi-scale spatial–temporal graph convolutional network for traffic flow prediction

Understanding crowd behavior is a pivotal step toward urban scene analysis. This is considered a very challenging task and has rarely been addressed to date due to the complexity of motion dynamics co-occurring across a given scene, which involves spatial and temporal dependencies. Unlike the mainstream research, which usually treats the temporal and spatial dependencies in a crowd separately, this paper presents a deep end-to-end approach that jointly considers the spatiotemporal information, leading to a rich understanding of crowd behavior. We first extract the displacement information describing crowd motion patterns from tracklets/trajectories. This information is subsequently fed into a convolutional layer to learn the underlying motion patterns and create high-level representations. The derived representations are used as inputs to a long short-term memory-based architecture to learn the underlying spatiotemporal cues in a single operation for the entire crowd in a given scene. We evaluate our approach on a widely used, large-scale benchmark datasets for three critical applications: pedestrian path forecasting, destination estimation, and holistic crowd behavior classification. The results show a drastic improvement compared to recently trending works.

A latent variable representation of count data models to accommodate spatial and temporal dependence: Application to predicting crash frequency at intersections

The generation of synthetic time series is important in contemporary water sciences for their wide applicability and ability to model environmental uncertainty. Hydroclimatic variables often exhibit highly skewed distributions, intermittency (that is, alternating dry and wet intervals), and spatial and temporal dependencies that pose a particular challenge to their study. Vine copula models offer an appealing approach to generate synthetic time series because of their ability to preserve any marginal distribution while modeling a variety of probabilistic dependence structures. In this work, we focus on the stochastic modeling of hydroclimatic processes using vine copula models. We provide an approach to model intermittency by coupling Markov chains with vine copula models. Our approach preserves first-order auto- and cross-dependencies (correlation). Moreover, we present a novel framework that is able to model multiple processes simultaneously. This method is based on the coupling of temporal and spatial dependence models through repetitive sampling. The result is a parsimonious and flexible method that can adequately account for temporal and spatial dependencies. Our method is illustrated within the context of a recent reliability assessment of a historical hydraulic structure in central Mexico. Our results show that by ignoring important characteristics of probabilistic dependence that are well captured by our approach, the reliability of the structure could be severely underestimated.

Multi-level Graph Memory Network Cluster Convolutional Recurrent Network for traffic forecasting

Long-term prediction of physical systems on irregular unstructured meshes is extremely challenging due to the spatial complexityof meshes and the dynamic changes over time; namely, spatial dependence and temporal dependence. Recently, graph-based next-step prediction models have achieved great success in the task of modeling complex high-dimensional physical systems. However, due to these models ignoring the temporal dependence, they inevitably suffer from the effects of error accumulation. To capture the spatial and temporal dependence simultaneously, we propose a temporal graph network (TGN) to predict the long-term dynamics of complex physical systems. Specifically, we introduce an Encode-Process-Decode architecture to capture spatial dependence and create low-dimensional vector representations of system states. Additionally, a temporal model is introduced to learn the dynamic changes in the low-dimensional vector representations to capture temporal dependence. Our model can capture spatiotemporal correlations within physical systems. On some complex long-term prediction tasks in fluid dynamics, such as airfoil flow and cylinder flow, the prediction error of our method is significantly lower than the competitive GNN baseline. We show accurate phase predictions even for very long prediction sequences.

Traffic flow forecasting is the basis for the dynamic control and application of Intelligent Transport Systems (ITS), which is of great practical importance in reducing road congestion. Accurately predicting traffic flow remains a significant obstacle due to the intricate spatial and temporal dependencies associated with traffic movement. To capture the simultaneous dynamics of traffic flow’s spatiotemporal features, this paper suggests a novel Spatiotemporal Interactive Dynamic Synchronous Graph Convolution Network (STIDSG) for traffic flow forecasting, which is composed of the Interactive Dynamic Graph Convolution Network (IDGCN) and the Spatiotemporal Synchronous Graph Convolution Layer (STSGCL). IDGCN learns and shares features using an interactive learning strategy that is based on Dynamic Graph Convolution (DGCN). By incorporating DGCN into the interactive learning structure, it is possible to learn dynamic spatial features of traffic flow in an interactive manner while also capturing temporal dependencies. STSGCL effectively captures the intricate local and dynamic correlations of traffic flows by designing numerous Spatiotemporal Synchronization Graph Convolution Modules (STSGCM) for different time periods. The results of the experiment demonstrate that the STIDSG model suggested in this paper can proficiently extract the changing spatiotemporal features of the traffic flow and outperforms the commonly used baseline methods for prediction. The results of the experiment demonstrate that the STIDSG model suggested in this paper can proficiently extract the changing spatiotemporal features of the traffic flow and outperforms the commonly used baseline methods for prediction.

In the intelligent transportation system, traffic forecasting, which is generally characterized as a graph spatial-temporal prediction task, plays a crucial role. It is challenging to generate reliable forecast results due to the complexity of traffic topological information and the inherent uncertainty of road traffic circumstances. Existing works generally focus on modeling spatial dependency on static graph structures, but ignore dynamic relations between road segments and cannot extract long-range traffic dependencies in spatial-temporal domains. To bridge the above gaps, we present a novel framework, called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Dynamic Multi-Hop Graph Attention Network</i> (DMGAN). Specifically, we leverage dynamic graph modeling to capture time-varying relations across road sections and introduce the multi-hop operation in each message propagation layer to extract long-range spatial dependency. Meanwhile, we develop a fusion-attention module, preserving both local and global hidden layer outputs of the encoder, to capture both long- and short-term temporal dependencies jointly. In this way, our method can fully model complex time-varying traffic topology information and capture the internal patterns of traffic series by integrating dynamic graph structure and temporal attention component. DGMAN achieves state-of-the-art performance in three metrics, as demonstrated by experimental findings on four real-world public traffic datasets, METR-LA, PEMS-BAY, PEMS03, and PEMS07. This code and data are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/EEHITer/2022-TKDE-DMGAN-Pytorch/tree/main</uri> for reproducibility and further studies.

CPNet: Conditionally parameterized graph convolutional network for traffic forecasting

Knee segmentation and landmark localization from 3D MRI are two significant tasks for diagnosis and treatment of knee diseases. With the development of deep learning, Convolutional Neural Network (CNN) based methods have become the mainstream. However, the existing CNN methods are mostly single-task methods. Due to the complex structure of bone, cartilage and ligament in the knee, it is challenging to complete the segmentation or landmark localization alone. And establishing independent models for all tasks will bring difficulties for surgeon's clinical using. In this paper, a Spatial Dependence Multi-task Transformer (SDMT) network is proposed for 3D knee MRI segmentation and landmark localization. We use a shared encoder for feature extraction, then SDMT utilizes the spatial dependence of segmentation results and landmark position to mutually promote the two tasks. Specifically, SDMT adds spatial encoding to the features, and a task hybrided multi-head attention mechanism is designed, in which the attention heads are divided into the inter-task attention head and the intra-task attention head. The two attention head deal with the spatial dependence between two tasks and correlation within the single task, respectively. Finally, we design a dynamic weight multi-task loss function to balance the training process of two task. The proposed method is validated on our 3D knee MRI multi-task datasets. Dice can reach 83.91% in the segmentation task, and MRE can reach 2.12 mm in the landmark localization task, it is competitive and superior over other state-of-the-art single-task methods.

Predicting traffic conditions is tremendously challenging since every road is highly dependent on each other, both spatially and temporally. Recently, to capture this spatial and temporal dependency, specially designed architectures such as graph convolutional networks and temporal convolutional networks have been introduced. While there has been remarkable progress in traffic forecasting, we found that deep-learning-based traffic forecasting models still fail in certain patterns, mainly in event situations (e.g., rapid speed drops). Although it is commonly accepted that these failures are due to unpredictable noise, we found that these failures can be corrected by considering previous failures. Specifically, we observe autocorrelated errors in these failures, which indicates that some predictable information remains. In this study, to capture the correlation of errors, we introduce ResCAL, a residual estimation module for traffic forecasting, as a widely applicable add-on module to existing traffic forecasting models. Our ResCAL calibrates the prediction of the existing models in real time by estimating future errors using previous errors and graph signals. Extensive experiments on METR-LA and PEMS-BAY demonstrate that our ResCAL can correctly capture the correlation of errors and correct the failures of various traffic forecasting models in event situations.