Spatial-temporal Convolution Research Articles

MmSTCT: spatial–temporal convolution transformer network considering driving intention for multimodal vehicle trajectory prediction of highway

Due to the dynamic nature of traffic flow and the uncertainty of drivers' maneuvers, multimodal trajectory prediction remains challenging. In this paper, a multimodal vehicle trajectory prediction model is proposed based on the encoder-decoder structure, utilizing a spatial-temporal dilated causal convolutional transformer network for the hierarchical extraction of driving intention and spatial interaction features. Specifically, temporal information is extracted from the initial motion states by utilizing a bi-directional long short-term memory network. Subsequently, the social interaction module and spatial-temporal dependency module are introduced to model the interactive influences among surrounding vehicles and the target vehicle at the same timestamp as well as at different timestamps. Then adaptive fusion of driving intention is performed to generate multiple queries for accommodating the output of multimodal trajectory prediction module in a non-autoregressive manner. The effectiveness of the proposed model is demonstrated through experimental evaluations on the NGSIM, HighD and CitySim datasets.

Decomposition with feature attention and graph convolution network for traffic forecasting

Traffic forecasting is a crucial task for enhancing the quality and efficiency of intelligent transportation systems. In recent years, several neural networks have been proposed to tackle this challenge. However, traffic data itself has complex composition and intertwined temporal patterns. Currently, the absence of effective methods to capture the inherent properties and overall profile of traffic data has become a bottleneck in improving the traffic prediction capabilities of models. To address these issues, we introduce a novel model, Decomposition with Feature Attention and Graph Convolution Network (DFAGCN), for Traffic Forecasting. To highlight the inherent properties of complicated traffic data, we present a unique Decomposition with Feature Attention (DFA) method to decompose the traffic data into seasonality, trend, and remainder. On the one hand, we introduce a new method to filter out noise and possible outliers from time series data. On the other hand, we employ an attention mechanism to make our decomposition method adaptively extract the trend. Subsequently, we utilize spatial–temporal attention to simulate the dynamic spatial–temporal correlations of traffic data. Finally, we use spatial–temporal convolution to extract local dependencies of traffic data. Experiments conducted on four real-world traffic forecasting datasets demonstrate that DFAGCN achieves state-of-the-art performance. The results show that the application of time series decomposition to traffic data significantly enhances the accuracy of traffic prediction.

Traffic Flow Prediction Research Based on an Interactive Dynamic Spatial–Temporal Graph Convolutional Probabilistic Sparse Attention Mechanism (IDG-PSAtt)

Accurate traffic flow prediction is highly important for relieving road congestion. Due to the intricate spatial–temporal dependence of traffic flows, especially the hidden dynamic correlations among road nodes, and the dynamic spatial–temporal characteristics of traffic flows, a traffic flow prediction model based on an interactive dynamic spatial–temporal graph convolutional probabilistic sparse attention mechanism (IDG-PSAtt) is proposed. Specifically, the IDG-PSAtt model consists of an interactive dynamic graph convolutional network (IL-DGCN) with a spatial–temporal convolution (ST-Conv) block and a probabilistic sparse self-attention (ProbSSAtt) mechanism. The IL-DGCN divides the time series of a traffic flow into intervals and synchronously and interactively shares the captured dynamic spatiotemporal features. The ST-Conv block is utilized to capture the complex dynamic spatial–temporal characteristics of the traffic flow, and the ProbSSAtt block is utilized for medium-to-long-term forecasting. In addition, a dynamic GCN is generated by fusing adaptive and learnable adjacency matrices to learn the hidden dynamic associations among road network nodes. Experimental results demonstrate that the IDG-PSAtt model outperforms the baseline methods in terms of prediction accuracy. Specifically, on METR-LA, the mean absolute error (MAE) and root mean square error (RMSE) induced by IDG-PSAtt for a 60 min forecasting scenario are reduced by 0.75 and 1.31, respectively, compared to those of the state-of-the-art models. This traffic flow prediction improvement will lead to more precise estimates of the emissions produced by mobile sources, resulting in more accurate air quality forecasts. Consequently, this research will greatly support local environmental management efforts.

DSTCNN: Deformable spatial-temporal convolutional neural network for pedestrian trajectory prediction

Pedestrian trajectory prediction holds significant research value in service robots, autonomous driving, and intelligent monitoring. Currently, most pedestrian trajectory prediction methods focus on data-driven models based on recurrent neural networks, but there is insufficient research on data-driven models based on convolutional neural networks. In this study, we first analyze the two problems in pedestrian trajectory prediction methods based on convolutional neural networks: 1. Previous trajectory prediction methods based on convolutional neural networks have spatial-temporal entanglement problems; 2. These methods are limited by their fixed convolution kernels and cannot accurately model social and temporal interactions. Furthermore, we propose a deformable spatial-temporal convolutional neural network (DSTCNN) to better adapt to the pedestrian trajectory prediction task. The deformable spatial-temporal convolutional neural network models spatial and temporal interactions separately, overcoming the shortcomings of spatial-temporal entanglement. The deformable spatial-temporal convolution also gets rid of the fixed convolution kernel, making the modeling of spatial-temporal interactions more accurate. On the ETH and UCY datasets, the average displacement error and final displacement error of our method are 0.29 and 0.53 meters, respectively. In kernel density estimation, average Mahalanobis distance, and average maximum eigenvalue metrics, our method still achieves better performance compared to baseline methods. Moreover, the deformable spatial-temporal convolutional neural network is a memory-efficient model with only 4.1K parameters.

Spatial linear transformer and temporal convolution network for traffic flow prediction

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.

Optimization of spatial-temporal graph: A taxi demand forecasting model based on spatial-temporal tree

Taxi is one of the important means of transportation for people's daily travel activities, and it is one of the important research objects of intelligent transportation system. Taxi demand forecasting research can promote the application of urban transportation basic services and the transportation department to analyze and allocate transportation resources more reasonably. Graph structure is an important method for capturing spatial correlations among urban regions. However, it has certain limitations in capturing the hierarchical features and the local path features of regional nodes. Additionally, existing research has failed to capture multiple factors influencing changes in taxi demand. Therefore, this study proposes a spatial-temporal model based on capturing multi-factor features. The model innovatively uses the tree structure as a topology structure and proposes the tree convolution for constructing data spatial distribution features. The spatial-temporal convolution module with tree convolution as the core can effectively capture the hierarchical features and the local path features among area nodes. In this study, four factors affecting taxi demand are designed. The deep features of the four factors are further fused through the spatial-temporal convolution module. The model integrates multiple influencing factors affecting taxi demand from the spatial-temporal level and shows certain advantages in experiments. Compared with existing baselines, the model designed in this paper shows certain advantages in three real urban taxi datasets.

An IoT based smart water quality assessment framework for aqua-ponds management using Dilated Spatial-temporal Convolution Neural Network (DSTCNN)

Assuring the quality of water is crucial for the growth and survival of fish in aquaculture ponds. Traditional methods of water quality monitoring can be inefficient which makes real-time monitoring and decision is a challenging one. Some deep learning techniques have shown apparent in improving water quality monitoring and assessment process, but encounter some limitations like data-overfitting, interpretability, and finds difficulties in capturing complex spatial and temporal dynamics that have hindered their effectiveness. To overcome these challenges, we propose an enhanced Dilated Spatial-temporal Convolution Neural Network (DSTCNN) for water quality monitoring in aquaculture, which uses an IoT system setup for capturing real-time data inputs from aqua ponds. The water quality data captured through the IoT sensors is labeled as per the water quality index (WQI) standards for analysis. This labeled data is effectively classified into two categories by the proposed DSTCNN model based on their suitability for fish growth or potential to cause fish mortality. By the leveraging power of dilated convolutions, the DSTCNN architecture accurately handles the intricacies of both spatial and temporal data, enabling it to capture essential features and patterns across multiple snapshots. This capability empowers the model to truly comprehend the complex relationships inherent in spatiotemporal data. Furthermore, to address the concerns like overfitting due to complexity of data and enhance generalization, the proposed model employs a hybrid activation function that synergistically combines ReLU and sigmoid during the activation process. The proposed DSTCNN model has been implemented on real-time and public datasets and obtained 99.28% and 99.02% accuracy respectively, whereas the state-of-the-art PCR-GB model obtains 96.97% and 97.11% accuracy on real-time and public datasets respectively.

A task-unified network with transformer and spatial–temporal convolution for left ventricular quantification

Quantification of the cardiac function is vital for diagnosing and curing the cardiovascular diseases. Left ventricular function measurement is the most commonly used measure to evaluate the function of cardiac in clinical practice, how to improve the accuracy of left ventricular quantitative assessment results has always been the subject of research by medical researchers. Although considerable efforts have been put forward to measure the left ventricle (LV) automatically using deep learning methods, the accurate quantification is yet a challenge work as a result of the changeable anatomy structure of heart in the systolic diastolic cycle. Besides, most methods used direct regression method which lacks of visual based analysis. In this work, a deep learning segmentation and regression task-unified network with transformer and spatial–temporal convolution is proposed to segment and quantify the LV simultaneously. The segmentation module leverages a U-Net like 3D Transformer model to predict the contour of three anatomy structures, while the regression module learns spatial–temporal representations from the original images and the reconstruct feature map from segmentation path to estimate the finally desired quantification metrics. Furthermore, we employ a joint task loss function to train the two module networks. Our framework is evaluated on the MICCAI 2017 Left Ventricle Full Quantification Challenge dataset. The results of experiments demonstrate the effectiveness of our framework, which achieves competitive cardiac quantification metric results and at the same time produces visualized segmentation results that are conducive to later analysis.

Multi-task hybrid spectral–spatial temporal convolution networks for classification of agricultural crop types and growth stages using drone-borne hyperspectral and multispectral images

Multi-task hybrid spectral–spatial temporal convolution networks for classification of agricultural crop types and growth stages using drone-borne hyperspectral and multispectral images

Spectral-domain Spatial-temporal Convolution Graph Neural Network for Industrial Fault Diagnosis

In modern industrial production, once a fault occurs in the production process, it will affect the whole production and bring huge economic losses. There are a large number of device sensors in modern production, and there are complex interactions between them. But the existing methods can not efficiently and accurately mine the depth of information from mass production data. We proposed the Spectral-domain Spatial-Temporal Convolution Graph Neural Network model, which comprehensively considers the information of spatial and temporal dimensions in production data. The nodes and edges of the heterogeneous graph represent the sensor signals and their interactions. Each sensor data is converted to the spectral domain to extract the time domain features, and graph convolution is used to carry out the spatial relationship between input sequences. Finally, the proposed model is verified using the Three-Phase Flow Facility (TFF) dataset, and the overall accuracy rate reached 96.28%, showing better performance than other baseline models.

Dynamic Fall Detection Using Graph-Based Spatial Temporal Convolution and Attention Network

The prevention of falls has become crucial in the modern healthcare domain and in society for improving ageing and supporting the daily activities of older people. Falling is mainly related to age and health problems such as muscle, cardiovascular, and locomotive syndrome weakness, etc. Among elderly people, the number of falls is increasing every year, and they can become life-threatening if detected too late. Most of the time, ageing people consume prescription medication after a fall and, in the Japanese community, the prevention of suicide attempts due to taking an overdose is urgent. Many researchers have been working to develop fall detection systems to observe and notify about falls in real-time using handcrafted features and machine learning approaches. Existing methods may face difficulties in achieving a satisfactory performance, such as limited robustness and generality, high computational complexity, light illuminations, data orientation, and camera view issues. We proposed a graph-based spatial-temporal convolutional and attention neural network (GSTCAN) with an attention model to overcome the current challenges and develop an advanced medical technology system. The spatial-temporal convolutional system has recently proven the power of its efficiency and effectiveness in various fields such as human activity recognition and text recognition tasks. In the procedure, we first calculated the motion along the consecutive frame, then constructed a graph and applied a graph-based spatial and temporal convolutional neural network to extract spatial and temporal contextual relationships among the joints. Then, an attention module selected channel-wise effective features. In the same procedure, we repeat it six times as a GSTCAN and then fed the spatial-temporal features to the network. Finally, we applied a softmax function as a classifier and achieved high accuracies of 99.93%, 99.74%, and 99.12% for ImViA, UR-Fall, and FDD datasets, respectively. The high-performance accuracy with three datasets proved the proposed system’s superiority, efficiency, and generality.

Dual Graph Convolution Architecture Search for Travel Time Estimation

Travel time estimation (TTE) is a crucial task in intelligent transportation systems, which has been widely used in navigation and route planning. In recent years, several deep learning frameworks have been proposed to capture the dynamic features of road segments or intersections for travel time estimation. However, most existing works do not consider the joint features of the intersections and road segments. Moreover, most deep neural networks for TTE are designed based on empirical knowledge. Since the independent and joint features of intersections and road segments commonly vary with different datasets, the empirical deterministic neural architectures have limited adaptability to different scenarios. To tackle the above problems, we propose a novel automated deep learning framework, namely Automated Spatio-Temporal Dual Graph Convolutional Networks (Auto-STDGCN), for travel time estimation. Specifically, we propose to construct the node-wise graph and edge-wise graph to characterize the spatio-temporal features of intersections and road segments, respectively. In order to capture the joint spatio-temporal correlations of the dual graphs, a hierarchical neural architecture search approach is introduced, whose search space is composed of internal and external search space. In the internal search space, spatial graph convolution and temporal convolution operations are adopted to capture the respective spatio-temporal correlations of the dual graphs. Further, we design the external search space including the node-wise and edge-wise graph convolution operations from the internal architecture search to capture the interaction patterns between the intersections and road segments. We evaluate our proposed model Auto-STDGCN on three real-world datasets, which demonstrates that our model is significantly superior to the state-of-the-art methods. In addition, we also conduct case studies to visualize and explain the neural architectures learned by our model.

Attention-Based Spatial-Temporal Convolution Gated Recurrent Unit for Traffic Flow Forecasting.

Accurate traffic flow forecasting is very important for urban planning and traffic management. However, this is a huge challenge due to the complex spatial-temporal relationships. Although the existing methods have researched spatial-temporal relationships, they neglect the long periodic aspects of traffic flow data, and thus cannot attain a satisfactory result. In this paper, we propose a novel model Attention-Based Spatial-Temporal Convolution Gated Recurrent Unit (ASTCG) to solve the traffic flow forecasting problem. ASTCG has two core components: the multi-input module and the STA-ConvGru module. Based on the cyclical nature of traffic flow data, the data input to the multi-input module are divided into three parts, near-neighbor data, daily-periodic data, and weekly-periodic data, thus enabling the model to better capture the time dependence. The STA-ConvGru module, formed by CNN, GRU, and attention mechanism, can capture both temporal and spatial dependencies of traffic flow. We evaluate our proposed model using real-world datasets and experiments show that the ASTCG model outperforms the state-of-the-art model.

STA-GCN: Spatial-Temporal Self-Attention Graph Convolutional Networks for Traffic-Flow Prediction

As an important component of intelligent transportation-management systems, accurate traffic-parameter prediction can help traffic-management departments to conduct effective traffic management. Due to the nonlinearity, complexity, and dynamism of highway-traffic data, traffic-flow prediction is still a challenging issue. Currently, most spatial–temporal traffic-flow-prediction models adopt fixed-structure time convolutional and graph convolutional models, which lack the ability to capture the dynamic characteristics of traffic flow. To address this issue, this paper proposes a spatial–temporal prediction model that can capture the dynamic spatial–temporal characteristics of traffic flow, named the spatial–temporal self-attention graph convolutional network (STA-GCN). In terms of feature engineering, we used the time cosine decomposition and one-hot encoding methods to capture the periodicity and heterogeneity of traffic-flow changes. Additionally, in order to build the model, self-attention mechanisms were incorporated into the spatial–temporal convolution to capture the spatial–temporal dynamic characteristics of traffic flow. The experimental results indicate that the performance of the proposed model on two traffic-volume datasets is superior to those of several baseline models. In particular, in long-term prediction, the prediction error can be reduced by over 5%. Further, the interpretability and robustness of the prediction model are addressed by considering the spatial dynamic changes.

AutoSTG+: An automatic framework to discover the optimal network for spatio-temporal graph prediction

Spatio-temporal graphs (STGs) are important structures to describe urban sensory data, e.g., traffic speed and air quality. Predicting over spatio-temporal graphs enables many essential applications in intelligent cities, such as traffic management and environment analysis. Recently, many deep learning models have been proposed for spatio-temporal graph prediction and achieved significant results. However, manually designing neural networks requires rich domain knowledge and heavy expert efforts, making it impractical for real-world deployments. Therefore, we study automated neural architecture search for spatio-temporal graphs, which meets three challenges: 1) how to define search space for capturing complex spatio-temporal correlations; 2) how to jointly model the explicit and implicit relationships between nodes of an STG; and 3) how to learn network weight parameters related to meta graphs of STGs.To tackle these challenges, we propose a novel neural architecture search framework, entitled AutoSTG+, for automated spatio-temporal graph prediction. In our AutoSTG+, spatial graph convolution and temporal convolution operations are adopted in the search space of AutoSTG+ to capture complex spatio-temporal correlations. Besides, we propose to employ the meta-learning technique to learn the adjacency matrices of spatial graph convolution layers and kernels of temporal convolution layers from the meta knowledge of meta graphs. And specifically, such meta-knowledge is learned by graph meta-knowledge learners, which iteratively aggregate knowledge on the attributed graphs and the similarity graphs. Finally, extensive experiments have been conducted on multiple real-world datasets to demonstrate that AutoSTG+ can find effective network architectures and achieve up to about 20% relative improvements compared to human-designed networks.

Spatial–temporal dependence and similarity aware traffic flow forecasting

Traffic flow forecasting is the cornerstone of the development of intelligent transportation systems. Accurate forecasting is conducive to the control and management of urban traffic. However, it is still a challenge to extract the complex spatial–temporal relationships in the traffic flow. The existing methods based on Graph Convolutional Network (GCN) can effectively extract spatial–temporal dependence, but it is difficult to extract spatial–temporal similarity because of the limitation of the graph structure. In this paper, we propose a spatial–temporal dependence and similarity-aware method called Dependence and Similarity aware Temporal Graph Convolutional Network (DS-TGCN), which combines two modules to extract the complex spatial–temporal relationships and make traffic flow forecasting. One module is our Spatial–Temporal Similarity Feature module (STSF) newly designed for extracting the spatial–temporal similarity directly. Another module is the spatial–temporal convolution module with an attention mechanism, which can extract spatial–temporal dependence dynamically. The experiments on two types of datasets demonstrate that our proposed method outperforms the existing methods in terms of the effectiveness of traffic flow forecasting.

TC-Net: A Modest & Lightweight Emotion Recognition System Using Temporal Convolution Network

Speech signals play an essential role in communication and provide an efficient way to exchange information between humans and machines. Speech Emotion Recognition (SER) is one of the critical sources for human evaluation, which is applicable in many real-world applications such as healthcare, call centers, robotics, safety, and virtual reality. This work developed a novel TCN-based emotion recognition system using speech signals through a spatial-temporal convolution network to recognize the speaker’s emotional state. The authors designed a Temporal Convolutional Network (TCN) core block to recognize long-term dependencies in speech signals and then feed these temporal cues to a dense network to fuse the spatial features and recognize global information for final classification. The proposed network extracts valid sequential cues automatically from speech signals, which performed better than state-of-the-art (SOTA) and traditional machine learning algorithms. Results of the proposed method show a high recognition rate compared with SOTA methods. The final unweighted accuracy of 80.84%, and 92.31%, for interactive emotional dyadic motion captures (IEMOCAP) and berlin emotional dataset (EMO-DB), indicate the robustness and efficiency of the designed model.

Human Motion Recognition With Spatial-Temporal-ConvLSTM Network Using Dynamic Range-Doppler Frames Based on Portable FMCW Radar

As a noncontact and noninvasive sensor, radar offers attractive modality for human motion recognition in many fields, such as surveillance, smart homes, and assisted living. As a dynamic process, a comprehensive multidomain analysis in stream is crucial for human motion recognition. In this article, a novel spatial–temporal convolution long short-term memory (ST-ConvLSTM) network using dynamic range-Doppler frames (DRDF) based on portable frequency-modulated continuous-wave (FMCW) radar is proposed to address this problem. First, DRDF is introduced to characterize different human motions in time, range, Doppler, and radar cross section (RCS) domains with a time-sequenced range-Doppler maps. Then, ConvLSTM cell is investigated to extract continuous 2-D image features by combining both convolution operation and LSTM cell. Furthermore, a spatial attention module is utilized to emphasize the spatial distribution of human motion in the range-Doppler domain, while a temporal attention module is designed to obtain optimal temporal weights considering behavior continuity. Finally, an extensive radar dataset from 16 volunteers demonstrated its feasibility and superiority in the classification of six typical daily human motions. The contributions of attention modules and its robustness facing individual diversity are also investigated and discussed.

Attention enhanced hybrid model for spatiotemporal short-term forecasting of particulate matter concentrations

With ever-increasing global air pollution levels, researchers are exploring ways to forecast air pollutant concentrations to prevent the adverse effects of air pollution on humans. Powered by the data obtained from air pollution monitoring stations, we now have a chance to build sophisticated models to estimate the future concentration of various air pollutants. Previous researches show that deep learning models perform a better task of capturing the complex spatiotemporal dynamics from the data as compared to traditional statistical models. In this paper, a hybrid deep learning framework - AGCTCN (Attention based Graph Convolution and Temporal Convolution Network), based on spatial attention, graph convolution and temporal convolution is presented for short-term forecasting of particulate matter (PM) levels. Specifically, quarter-hourly PM10 and PM2.5 data aggregated from 27 ground air pollution monitoring stations in Delhi, India is used for training the AGCTCN model and our model forecasts the concentrations of these pollutants at these stations for a particular horizon in the future. The forecasts generated by our model are compared and contrasted to those generated by other state-of-the-art models like GC-LSTM and ConvLSTM with respect to four widely used evaluation metrics namely RMSE (root mean squared error), MAE (mean absolute error), correlation coefficient, and R2 (coefficient of determination). Our model shows more than 80% improvement over the GC-LSTM model in terms of the R2 metric, performs the best task of estimating the peak PM concentrations and shows variability and correlation close to that of the observed data. A carefully conducted ablation study shows the effectiveness of the individual components of our architecture. The graph convolution layer improves the model accuracy by approximately 34% on average on the PM datasets. Compared to other models, the AGCTCN framework shows the best performance in short-term forecasting of particulate matter concentrations.

Traffic Flow Prediction Based on Multi-Mode Spatial-Temporal Convolution of Mixed Hop Diffuse ODE

In recent years, traffic flow forecasting has attracted the great attention of many researchers with increasing traffic congestion in metropolises. As a hot topic in the field of intelligent city computing, traffic flow forecasting plays a vital role, since predicting the changes in traffic flow can timely alleviate traffic congestion and reduce the occurrence of accidents by vehicle scheduling. The most difficult challenges of traffic flow prediction are the temporal feature extraction and the spatial correlation extraction of nodes. At the same time, graph neural networks (GNNs) show an excellent ability in dealing with spatial dependence. Existing works typically make use of graph neural networks (GNNs) and temporal convolutional networks (TCNs) to model spatial and temporal dependencies respectively. However, how to extract as much valid information as possible from nodes is a challenge for GNNs. Therefore, we propose a multi-mode spatial-temporal convolution of mixed hop diffuse ODE (MHODE) for modeling traffic flow prediction. First, we design an adaptive spatial-temporal convolution module that combines Gate TCN and graph convolution to capture more short-term spatial-temporal dependencies and features. Secondly, we design a mixed hop diffuse ordinary differential equation(ODE) spatial-temporal convolution module to capture long-term spatial-temporal dependencies using the receptive field of the mixed hop diffuse ODE. Finally, we design a multi spatial-temporal fusion module to integrate the different spatial-temporal dependencies extracted from two different spatial-temporal convolutions. To capture more spatial-temporal features of traffic flow, we use the multi-mode spatial-temporal fusion module to get more abundant traffic features by considering short-term and long-term two different features. The experimental results on two public traffic datasets (METR-LA and PEMS-BAY) demonstrate that our proposed algorithm performs better than the existing methods in most of cases.