Traffic Series Research Articles

KaTaGCN: Knowledge-Augmented and Time-Aware Graph Convolutional Network for efficient traffic forecasting

Dynamic spatio-temporal dependencies and temporal patterns in traffic series are critical factors affecting traffic forecasting accuracy. Due to the intrinsic challenges of incorporating explicit, logical knowledge into the implicit black-box learning process of neural networks, only a few methods effectively use prior knowledge to improve the learning of traffic forecasting. To tackle this problem, we introduce a new approach called Knowledge-augmented and Time-aware Graph Convolutional Network, namely KaTaGCN. At its core, we have created a knowledge-augmented module that boosts the diffusion weights between closely related adjacent nodes in graph learning. This is achieved by implementing a new loss function. Then, to learn the periodic implicit relationship between these timestamps and traffic signals, the weights and biases are chosen adaptively to be trained based on the timestamps of each sample. Finally, a gated spatio-temporal mapping module regresses high-dimensional embedded features from spatial and temporal dimensions. KaTaGCN is structured without any attention mechanisms or recurrent neural networks. Extensive experimental results on six real-world public traffic datasets demonstrate that KaTaGCN achieves an average improvement of 4.29% in forecasting performance compared with suboptimal results.

LSTTN: A Long-Short Term Transformer-based spatiotemporal neural network for traffic flow forecasting

Accurate traffic forecasting is a fundamental problem in intelligent transportation systems and learning long-range traffic representations with key information through spatiotemporal graph neural networks (STGNNs) is a basic assumption of current traffic flow prediction models. However, due to structural limitations, existing STGNNs can only utilize short-range traffic flow data; therefore, the models cannot adequately learn the complex trends and periodic features in traffic flow. Besides, it is challenging to extract the key temporal information from the long historical traffic series and obtain a compact representation. To solve the above problems, we propose a novel LSTTN (Long-Short Term Transformer-based Network) framework comprehensively considering the long- and short-term features in historical traffic flow. First, we employ a masked subseries Transformer to infer the content of masked subseries from a small portion of unmasked subseries and their temporal context in a pretraining manner, forcing the model to efficiently learn compressed and contextual subseries temporal representations from long historical series. Then, based on the learned representations, long-term trend is extracted by using stacked 1D dilated convolution layers, and periodic features are extracted by dynamic graph convolution layers. For the difficulties in making time-step level prediction, LSTTN adopts a short-term trend extractor to learn fine-grained short-term temporal features. Finally, LSTTN fuses the long-term trend, periodic features and short-term features to obtain the prediction results. Experiments on four real-world datasets show that in 60-minute-ahead long-term forecasting, the LSTTN model achieves a minimum improvement of 5.63% and a maximum improvement of 16.78% over baseline models. The source code is availble at https://github.com/GeoX-Lab/LSTTN.

Temporal-aware structure-semantic-coupled graph network for traffic forecasting

The spatial–temporal graph neural networks have been a critical approach to capturing the complicated spatial–temporal dependencies inherent in traffic series for more accurate forecasting. However, the issue of graph indistinguishability demands further attention, as graphs learned by existing methods tend to converge to implicit and indistinguishable representations, deviating from the genuine distribution. This issue can be attributed to the lack of three primary factors within graphs: the intrinsic graph features, the temporal-distinct features, and the node-distinct features. Aiming to address this problem, we propose a Temporal-Aware Structure-Semantic-Coupled Graph Network (TASSGN) in this paper. Firstly, we design a novel graph learning block to simultaneously learn the structural and semantic aspects of graphs, thereby capturing inherent graph features. Secondly, we propose an innovative Self-Sampling method to sample the relevant history series and present a Temporal-Aware Graphs Encoder to explicitly incorporate temporal information into graph learning and capture temporal-distinct features. Thirdly, sparse graphs are intentionally generated to capture node-distinct features. By combining these three key components together, our method is capable of overcoming the problem of graph indistinguishability and achieving state-of-the-art performances in traffic forecasting.

Spatio-temporal fusion graph convolutional network for traffic flow forecasting

In most recent research, the traffic forecasting task is typically formulated as a spatio-temporal graph modeling problem. For spatial correlation, they typically learn the shared pattern (i.e., the most salient pattern) of traffic series and measure the interdependence between traffic series based on a predefined graph. On the one hand, learning a specific traffic pattern for each node (traffic series) is crucial and essential for accurate spatial correlation learning. On the other hand, most predefined graphs cannot accurately represent the interdependence between traffic series because they are unchangeable while the prediction task changes. For temporal correlation, they usually concentrate on contiguous temporal correlation. Therefore, they are insufficient due to their lack of global temporal correlation learning. To overcome these aforementioned limitations, we propose a novel method named Spatio-Temporal Fusion Graph Convolutional Network (STFGCN). In the spatial aspect, we introduce a node-specific graph convolution operation to learn the node-specific patterns of each node (traffic series). Then, an adaptive adjacent matrix is introduced to represent the interdependence between traffic series. In the temporal aspect, a contiguous temporal correlation learning module is introduced to learn the contiguous temporal correlation of traffic series. Furthermore, a transformer-based global temporal correlation learning module is introduced to learn the global dependence of the traffic series. Experimental results show that our method significantly outperforms other competitive methods on two real-world traffic datasets (PeMSD4 and PeMSD8).

DMGAN: Dynamic Multi-Hop Graph Attention Network for Traffic Forecasting

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.

A spatio-temporal sequence-to-sequence network for traffic flow prediction

Spatio-temporal prediction has drawn much attention given its wide application, of which traffic flow prediction is a typical task. Within the vision of smart cities, traffic flow prediction plays a vital role in traffic control and optimization. The current approaches commonly use a graph convolutional network (GCN) to capture any spatial correlations and a recurrent neural network (RNN) to mine any temporal correlations. However, GCNs cannot detect spatial heterogeneity and time-varying spatial correlations, and RNNs cannot model the periodicity of traffic series data. Further, iterative training of RNNs may come at a high computational cost and result in problems with error propagation. To this end, we propose STSSN, a spatio-temporal sequence-to-sequence network, that not only explores heterogeneous and time-varying spatial correlations, but also efficiently exploits sequential and periodic temporal correlations. STSSN is based on an encoder-decoder framework. In the network, the model’s input is processed to extract the periodic daily and weekly patterns in traffic flows. Both the encoder and decoder mainly consist of an enhanced diffusion convolutional network (EDCN) and a temporal convolutional network (TCN). In the EDCN module, the diffusion convolution incorporates time-varying node representations so as to capture both node-specific patterns and time-varying spatial correlations. In the TCN module, we take full advantage of the parallel computing in the dilated causal convolution to mine local (short-term) temporal correlations. More importantly, global (long-term) temporal correlations are discovered through an encoder-decoder attention (EDA) module. This EDA mechanism directly models the relationship between the encoder and decoder to mitigate problems with error propagation. Experiments on two real-world datasets verify the superiority of STSSN, with STSSN’s MAE at between 3.85%-6.17% lower than the state-of-the-art baselines on the PEMS-BAY dataset.

Using support vector regression and K-nearest neighbors for short-term traffic flow prediction based on maximal information coefficient

The prediction of short-term traffic flow is critical for improving service levels for drivers and passengers as well as enhancing the efficiency of traffic management in the urban transportation system. For transportation departments, the issue remains of how to efficiently utilize the spatial and temporal information of traffic data for better prediction performance. As a means of improving traffic prediction accuracy, this paper proposes a method for screening spatial time-delayed traffic series based on the maximal information coefficient. The selected time-delayed traffic series are transformed into traffic state vectors, from which traffic flow is predicted by adopting the combination of support vector regression method and k-nearest neighbors method. We employ the proposed framework for real-world traffic flow prediction. Root Mean Squared Error (RMSE) and Mean Absolute Percent Error (MAPE) validate the superior performance of the proposed model compared to traditional methods. This new approach reduces the RMSE by 23.448% and the MAPE by 14.726% of the predicted results.

Augmented Multi-Component Recurrent Graph Convolutional Network for Traffic Flow Forecasting

Due to the periodic and dynamic changes of traffic flow and the spatial–temporal coupling interaction of complex road networks, traffic flow forecasting is highly challenging and rarely yields satisfactory prediction results. In this paper, we propose a novel methodology named the Augmented Multi-component Recurrent Graph Convolutional Network (AM-RGCN) for traffic flow forecasting by addressing the problems above. We first introduce the augmented multi-component module to the traffic forecasting model to tackle the problem of periodic temporal shift emerging in traffic series. Then, we propose an encoder–decoder architecture for spatial–temporal prediction. Specifically, we propose the Temporal Correlation Learner (TCL) which incorporates one-dimensional convolution into LSTM to utilize the intrinsic temporal characteristics of traffic flow. Moreover, we combine TCL with the graph convolutional network to handle the spatial–temporal coupling interaction of the road network. Similarly, the decoder consists of TCL and convolutional neural networks to obtain high-dimensional representations from multi-step predictions based on spatial–temporal sequences. Extensive experiments on two real-world road traffic datasets, PEMSD4 and PEMSD8, demonstrate that our AM-RGCN achieves the best results.

Directed hypergraph attention network for traffic forecasting

In traffic systems, traffic forecasting is a critical issue, which has attracted much interest from researchers. It is a challenging task due to the complex spatial-temporal patterns of traffic data. Previous works focus on designing complex graph-based neural networks to model spatial-temporal dependencies from data. By using graphs to represent road networks, these works capture spatial patterns with graph convolutions. However, graphs cannot fully represent spatial relations from road networks. It limits the performance of graph-based methods. In this paper, we propose a directed hypergraph neural network architecture, Directed Hypergraph Attention Network(DHAT), for traffic forecasting. Unlike previous works, DHAT introduces a directed hypergraph to represent road networks. Compared with graphs, directed hypergraphs could represent spatial information from graphs and outperform them in modeling complex directed relations among multiple nodes. Based on the directed hypergraph, a directed hypergraph convolution is proposed to exploit spatial relations among traffic series. By combining the proposed convolution and attention mechanisms, DHAT can effectively achieve promising predictions for traffic forecasting. To evaluate the performance of DHAT, we have conducted extensive experiments on four real-world traffic datasets. Compared with other baselines, experimental results show that DHAT reduces Mean Absolute Error by 0.03–0.64 on these datasets.

A Deep-Learning Model for Estimating the Impact of Social Events on Traffic Demand on a Cell Basis

In cellular networks, a deep knowledge of the traffic demand pattern in each cell is essential in network planning and optimization tasks. However, a precise forecast of the traffic time series per cell is hard to achieve, due to the noise originated by abnormal local events. In particular, mass social events (e.g., concerts, conventions, sport events…) have a strong impact on traffic demand. In this paper, a data-driven model to estimate the impact of local events on cellular traffic is presented. The model is trained with a large dataset of geotagged social events taken from public event databases and hourly traffic data from a live Long Term Evolution (LTE) network. The resulting model is combined with a traffic forecast module based on a multi-task deep-learning architecture to predict the hourly traffic series with scheduled mass events. Model assessment is performed over a real dataset created with geolocated social event information collected from public event directories and hourly cell traffic measurements during two months in a LTE network. Results show that the addition of the proposed model significantly improves traffic forecasts in the presence of massive events.

The Influence of Different Auditory Stimuli on Attentiveness and Responsiveness in Road Traffic in Simulated Traffic Situations.

The use of portable media has become an integral part of our increasingly mobile society. The use of digital audio books is also growing steadily in Germany. The connection between the psychological effect of music of different volumes and rhythms and the change in reaction in road traffic with a corresponding increase in risk behavior, especially when driving, has already been proven in previous studies. Only a few studies are available on the effects of listening to radio plays on reaction behavior and concentration in road traffic as well as on risk behavior among pedestrians and cyclists. In the present study, we have investigated the influences of pop music and a radio play on reaction behavior and thus driving ability during the execution of a traffic psychological test series from the “Wiener Test System”. The central topic deals with the performance of the test subjects in the individual tests. Conclusions are drawn on the reaction behavior and concentration during participation in road traffic and thus the risk of distraction and possible increased risk of accidents. Studies on the influence of auditory stimuli and their effects on concentration and reaction during participation in traffic are of great interest from the point of view of traffic psychology and occupational medicine, since a reduction in the risk of accidents can increase general traffic safety and lead to a decrease in sick leave and therefore fewer absences from work.

Optimising Self-Similarity Network Traffic for Better Performance

Given the ubiquity of the burstiness present across many networking facilities and services, predicting and managing self-similar traffic has become a key issue owing to new complexities associated with self-similarity which makes difficult the achievement of high network performance and quality of service (QoS). In this study ANN model was used to model and simulate FCE Okene computer network traffic. The ANN is a 2-39-1 Feed Forward Backpropagation network implemented to predict the bursty nature of network traffic. Wireshark tools that measure and capture packets of network traffic was deployed. Moreover, variance-time method is a log-log scale plot, representing variance versus a non-overlapping block of size m aggregate variance level engaged to established conformity of the ANN approach to self-similarity characteristic of the network traffic. The predicted series were then compared with the corresponding real traffic series. Suitable performance measurements used were the Means Square Error (MSE) and the Regression Coefficient. Our results showed that burstiness is present in the network across many time scales. The study also established the characteristic property of a long-range dependence (LRD). The work recommended that network traffic observation should be longer thereby enabling larger volume of traffic to be capture for better accuracy of traffic modelling and prediction.

Revisiting the relationship between traffic accidents, real economic activity and other factors in Spain

This paper analyzes the relationship between road traffic accidents and real economic activity in Spain, using data on accidents, fatalities and injuries from January 1975 to December 2016. Our results show the historical asymmetric cyclical behavior of traffic accidents variables. This relationship is more evident for accidents and injuries, while fatalities have shown a different pattern since 2002. Besides using aggregate data, we have analyzed urban and nonurban accidents separately. We analyze the effect of economic variables, public policy interventions and other potential factors affecting traffic series. Regarding policy interventions, we confirm a permanent reduction in all accident rates associated with the mandatory use of seatbelts on car passengers since 1992. However, the penalty points system introduced in July 2006 has only had temporary effects. We have also shown the effect of economic variables such as Industrial Production Index, gasoline and diesel consumption and registration of new vehicles and, as a novelty, the benefits of using the composite coincident and leading indicators of the Spanish economy.

A Gated Dilated Causal Convolution Based Encoder-Decoder for Network Traffic Forecasting

The accurate estimation of future network traffic is a key enabler for early warning of network degradation and automated orchestration of network resources. The long short-term memory neural network (LSTM) is a popular architecture for network traffic forecasting, and has been successfully used in many applications. However, it has been observed that LSTMs suffer from limited memory capacity problems when the sequence is long. In this paper, we propose a gated dilated causal convolution based encoder-decoder (GDCC-ED) model for network traffic forecasting. The GDCC-ED learns a vector representation in the encoder from historical network traffic series, in which gated dilated causal convolutions are adopted to expand the long-range memory capacity. Moreover, different types of features in various perspectives, including temporal-independent and temporal-related features, are incorporated. In the decoder, the GDCC-ED exploits an RNN with LSTM units to map the vector representation back to a variable-length target sequence. Besides, a sequence data augmentation technique is designed to solve the problem of data scarcity. Experimental results demonstrate that our model achieves superior performance than state-of-the-art algorithms by 11.6%.

Tourism Traffic Demand Prediction Using Google Trends Based on EEMD-DBN

Predicting tourism traffic demand accurately plays an important role in making effective policies for tourist administration. It helps to distribute the resources reasonably and avoid the tourism congestions. This paper considered the noise interference and proposed a hybrid model, combining ensemble empirical mode decomposition (EEMD), deep belief network (DBN) and Google trends, for tourism traffic demand prediction. This model firstly applied dislocation weighted synthesis method to combine Google trends into a search composite index, and then it denoised the series with EEMD. EEMD extracted the high frequency noise from the original series. The low frequency series of search composite index would be used to forecast the low frequency tourism traffic series. Taking the inbound tourism in Shanghai as an example, this paper trained the model and predicted the next 12 months tourism arrivals. The conclusion demonstrated that the forecast error of EEMD-DBN model is lower remarkably than the baselines of ARIMA, GM(1,1), FTS, SVM, CES and DBN model. This revealed that nosing processing is necessary and EEMD-DBN forecast model can improve the prediction accuracy.

Generation of Synthetic Network Traffic Series Using a Transformed Autoregressive Model Based Adaptive Algorithm

Modeling, testing and simulation of communications systems require to generate synthetic traffic series that present characteristics and behaviors as similar as possible to those of real network traffic traces. In this paper, we propose an adaptive algorithm to estimate the parameters of the Transformed Autoregressive Moving Average (TARMA) model in order to capture the autocorrelation function and the cumulative density function of the desired network traffic trace. Different from other works involving TARMA, we consider the adaptive estimation of its parameters. We compare the performance of the proposed on-line modeling approach to those of the Autoregressive Moving Average Model (ARMA) and of the on-batch Transformed Model in terms of mean, variance, moments, autocorrelation and probability density function. A transmission link composed of a single server with buffer is also simulated, which proves the efficiency of the proposed model in describing real traffic traces. The simulations carried out in this work show that the adaptive TARMA model outperforms in general the other considered autoregressive models.

Deep Learning with Long Short-Term Memory for Time Series Prediction

Time series prediction can be generalized as a process that extracts useful information from historical records and then determines future values. Learning long-range dependencies that are embedded in time series is often an obstacle for most algorithms, whereas Long Short-Term Memory (LSTM) solutions, as a specific kind of scheme in deep learning, promise to effectively overcome the problem. In this article, we first give a brief introduction to the structure and forward propagation mechanism of the LSTM model. Then, aiming at reducing the considerable computing cost of LSTM, we put forward the Random Connectivity LSTM (RCLSTM) model and test it by predicting traffic and user mobility in telecommunication networks. Compared to LSTM, RCLSTM is formed via stochastic connectivity between neurons, which achieves a significant breakthrough in the architecture formation of neural networks. In this way, the RCLSTM model exhibits a certain level of sparsity, which leads to an appealing decrease in the computational complexity and makes the RCLSTM model become more applicable in latency-stringent application scenarios. In the field of telecommunication networks, the prediction of traffic series and mobility traces could directly benefit from this improvement as we further demonstrate that the prediction accuracy of RCLSTM is comparable to that of the conventional LSTM no matter how we change the number of training samples or the length of input sequences.

Visualization of network traffic attack using time series radial axis and cylindrical coordinate system

Visualization of network traffic attack using time series radial axis and cylindrical coordinate system

STANN: A Spatio–Temporal Attentive Neural Network for Traffic Prediction

Recently, traffic prediction based on deep learning methods has attracted much attention. However, there still exist two major challenges, namely, dynamic spatio-temporal dependences among network-wide links and long-term traffic prediction for the next few hours. To address these two challenges, this paper proposes a spatio-temporal attentive neural network (STANN) for the network-wide and long-term traffic prediction. The STANN captures the spatial–temporal dependences based on the encoder–decoder architecture with the attention mechanisms. In the encoder, the STANN learns the spatio-temporal dependences from historical traffic series using a recurrent neural network (RNN) with long short-term memory (LSTM) units, in which a new spatial attention model is developed to consider the contribution of each link to the network-wide prediction. In the decoder, the STANN exploits another RNN with LSTM units and a temporal attention model to select the relevant and important historical spatio-temporal dependences from the encoder for long-term traffic prediction. Finally, we conduct extensive experiments to evaluate STANN on three real-world traffic datasets. The experimental results show that the STANN is significantly better than other state-of-the-art models.

Temporal‐spatial distribution nature of traffic and base stations in cellular networks

Recent years have witnessed the unprecedented surge of mobile traffic and base stations (BSs) deployment, which poses severe requirement for future communications systems. Understanding the distribution dynamics of traffic and BSs in time-space domain is of vital importance for better network design and resource management in cellular networks. In this study, a study on the statistical characteristics of cellular traffic series is carried out and α -stable distribution is verified to be valid for modelling the traffic series of each BS. On the other hand, inspired by the fact that BSs traffic series are spatially correlated, the authors study the statistical relationship between the correlation coefficient and the distance between BSs. Moreover, α -stable model is also suitable to describe the BSs deployment, thus conducing to prove the existence of self-similarity. In addition, both the traffic time series and the BSs spatial distribution are deeply associated with heterogeneity, so they come up with the density-based and distance-based methods to quantify their heterogeneous degree.