Accurate and timely traffic flow information is important for the successful deployment of intelligent transportation systems. Over the last few years, traffic data have been exploding, and we have truly entered the era of big data for transportation. Existing traffic flow prediction methods mainly use shallow traffic prediction models and are still unsatisfying for many real-world applications. This situation inspires us to rethink the traffic flow prediction problem based on deep architecture models with big traffic data. In this paper, a novel deep-learning-based traffic flow prediction method is proposed, which considers the spatial and temporal correlations inherently. A stacked autoencoder model is used to learn generic traffic flow features, and it is trained in a greedy layerwise fashion. To the best of our knowledge, this is the first time that a deep architecture model is applied using autoencoders as building blocks to represent traffic flow features for prediction. Moreover, experiments demonstrate that the proposed method for traffic flow prediction has superior performance.

Traffic Flow Prediction With Big Data: A Deep Learning Approach

Highway Capacity Manual改訂の動向--テイラ-教授の講演より

Accurate and real-time traffic forecasting plays an important role in the intelligent traffic system and is of great significance for urban traffic planning, traffic management, and traffic control. However, traffic forecasting has always been considered an “open” scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time. To capture the spatial and temporal dependences simultaneously, we propose a novel neural network-based traffic forecasting method, the temporal graph convolutional network (T-GCN) model, which is combined with the graph convolutional network (GCN) and the gated recurrent unit (GRU). Specifically, the GCN is used to learn complex topological structures for capturing spatial dependence and the gated recurrent unit is used to learn dynamic changes of traffic data for capturing temporal dependence. Then, the T-GCN model is employed to traffic forecasting based on the urban road network. Experiments demonstrate that our T-GCN model can obtain the spatio-temporal correlation from traffic data and the predictions outperform state-of-art baselines on real-world traffic datasets. Our tensorflow implementation of the T-GCN is available at https://www.github.com/lehaifeng/T-GCN .

T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction

Since the early 1980s, short-term traffic forecasting has been an integral part of most Intelligent Transportation Systems (ITS) research and applications; most effort has gone into developing methodologies that can be used to model traffic characteristics and produce anticipated traffic conditions. Existing literature is voluminous, and has largely used single point data from motorways and has employed univariate mathematical models to predict traffic volumes or travel times. Recent developments in technology and the widespread use of powerful computers and mathematical models allow researchers an unprecedented opportunity to expand horizons and direct work in 10 challenging, yet relatively under researched, directions. It is these existing challenges that we review in this paper and offer suggestions for future work.

Short-term traffic forecasting: Where we are and where we’re going

Accurate and real-time traffic flow prediction is important in Intelligent Transportation System (ITS), especially for traffic control. Existing models such as ARMA, ARIMA are mainly linear models and cannot describe the stochastic and nonlinear nature of traffic flow. In recent years, deep-learning-based methods have been applied as novel alternatives for traffic flow prediction. However, which kind of deep neural networks is the most appropriate model for traffic flow prediction remains unsolved. In this paper, we use Long Short Term Memory (LSTM) and Gated Recurrent Units (GRU) neural network (NN) methods to predict short-term traffic flow, and experiments demonstrate that Recurrent Neural Network (RNN) based deep learning methods such as LSTM and GRU perform better than auto regressive integrated moving average (ARIMA) model. To the best of our knowledge, this is the first time that GRU is applied to traffic flow prediction.

Using LSTM and GRU neural network methods for traffic flow prediction

In this paper, we discuss three problems that occur within short-term traffic prediction when the information from only a single point loop detector is used. First, we analyze the retrieval of intra-day trend for traffic flow series and determine whether this retrieval process improves traffic prediction. We compare different highway traffic prediction models that use either the original traffic flow series or the residual time series with the intra-day trend removed. Test results indicate that the prediction performance MAY be significantly improved in the latter scenario. Second, we address two other related questions: the influence of missing data and traffic breakdown prediction. We show that the Probabilistic Principal Component Analysis (PPCA) method, which also utilizes the intra-day trend of traffic flow series, can be a useful tool in imputing the missing data. It can simultaneously ensure that the prediction error remains at an acceptable level, especially when the missing ratio is relatively low. We also show that almost all the known predictors have hidden assumptions of smoothness and, thus, cannot predict the burst points that deviate too far from the intra-day trend. As a result, traffic breakdown points can only be identified but not predicted.

The retrieval of intra-day trend and its influence on traffic prediction

The rapid growth of internet based ride-sharing brings great changes to residents' travel and city traffic. However, few studies had employed empirical data to examine the unique travel patterns of internet based ride-sharing trips. In this paper, we compare taxi trip records and internet based ride-sharing trip records provided by DiDi company. Results reveal many interesting findings that had never been reported before. From the viewpoint of service patterns, ride-sharing mainly increases supplies in hot areas and peak hours. By applying a non-negative matrix factorization method, we find that ride-sharing principally serves as an approach for commuting. So, as an effective supplement to traditional taxi service, it regulates spatial and temporal supply-demand imbalance, especially during morning and evening rush periods. From the viewpoint of individual behavior patterns, we use a clustering method to identify two kinds of internet based ride-sharing drivers. The first kind of drivers usually provides ride-sharing along daily home-work commuting. Trips served by these drivers have relatively constant origin-designation (OD) pairs. The second kind of drivers does not serve regularly and roams around the city even in working hours. Therefore, there are no constant OD pairs in their ride-sharing trips. Counterintuitively, we find that home-work commuting drivers account for only a small part of total drivers and they only serve a small number of commuting trips. In addition, internet based ride-sharing is not just traditional hitchhiking worked through mobile internet. We find that internet based ride-sharing drivers intend to make long distance trips, and they intend to detour further to pick up or drop off passengers than traditional hitchhike drivers since they are paid. All these findings are helpful for policy makers at all levels to make informed decisions about deployment of internet based ride-sharing service. This paper also verifies that big data analytics is particularly useful and powerful in the analysis of ride-sharing and taxi service patterns.

An empirical study on travel patterns of internet based ride-sharing

This paper introduces a novel model—Generalized Space-Time Autoregressive Integrated Moving Average (GSTARIMA) methodology—into the field of short-term traffic flow forecasting in urban network. Compared to traditional STARIMA, GSTARIMA is a more flexible model class where parameters are designed to vary per location. Having proposed the model, a forecasting experiment based on actual traffic flow data in urban network in Beijing, China is constructed to verify the practicability of GSTARIMA model. After analysis and comparison with the traditional STARIMA model, the prediction results prove meritorious and the application of GSTARIMA improves the performance of urban network modeling.

Urban traffic network modeling and short-term traffic flow forecasting based on GSTARIMA model

In this paper, we propose a detrending based and deep learning based many-to-many traffic prediction model called DeepTrend 2.0 that accepts information collected from multiple sensors as input and simultaneously generates the prediction for all the sensors as output. First, we demonstrate that detrending brings advantages to traffic prediction, even when deep learning models are considered. Second, the proposed model strikes a delicate balance between model complexity and accuracy. In contrast to the existing models that view a sensor network as a weighted graph and use graph convolutional neural networks (GCNN) to model spatial dependency, we represent a sensor network as an image and propose a convolutional neural network (CNN) as the prediction model. The image is generated by the correlation coefficient between the flow series of sensors, which is different from other CNN based prediction approaches that convert the transportation network into an image by the spatial location of sensors or regions. Compared with the GCNN based model, the CNN based DeepTrend 2.0 can achieve much faster convergence during training, and it guarantees similar prediction quality. Test results indicate that the proposed light-weighted model is efficient and easy to transfer and deploy.

Zuo Zhang

Papers

Using LSTM and GRU neural network methods for traffic flow prediction

The retrieval of intra-day trend and its influence on traffic prediction

An empirical study on travel patterns of internet based ride-sharing

Urban traffic network modeling and short-term traffic flow forecasting based on GSTARIMA model

DeepTrend 2.0: A light-weighted multi-scale traffic prediction model using detrending