Deep Autoencoder Neural Networks for Short-Term Traffic Congestion Prediction of Transportation Networks

FASTNN: A Deep Learning Approach for Traffic Flow Prediction Considering Spatiotemporal Features

Traffic flow forecasting is a critical input to intelligent transportation systems. Accurate traffic flow forecasting can provide an effective reference for implementing traffic management strategies, developing travel route planning, and public transportation risk assessment. Recent deep learning approaches of spatiotemporal neural networks to predict traffic flow show promise, but could be difficult to separately model the spatiotemporal aggregation in traffic data and intrinsic correlation or redundancy of spatiotemporal features extracted by the filter of the convolutional network. This can introduce biases in the predictions that interfere with subsequent planning decisions in transportation. To solve the mentioned problem, the filter attention-based spatiotemporal neural network (FASTNN) was proposed in this paper. First, the model used 3-dimensional convolutional neural networks to extract universal spatiotemporal dependencies from three types of historical traffic flow, the residual units were employed to prevent network degradation. Then, the filter spatial attention module was constructed to quantify the spatiotemporal aggregation of the features, thus enabling dynamic adjustment of the spatial weights. To model the intrinsic correlation and redundancy of features, this paper also constructed a lightweight module, named matrix factorization based resample module, which automatically learned the intrinsic correlation of the same features to enhance the concentration of the model on information-rich features, and used matrix factorization to reduce the redundant information between different features. The FASTNN has experimented on two large-scale real datasets (TaxiBJ and BikeNYC), and the experimental results show that the FASTNN has better prediction performance than various baselines and variant models.

Time-Series-Based Queries on Stable Transportation Networks Equipped with Sensors

In this paper, we propose a formalism to query transportation networks that are equipped with sensors that produce time-series data. The core of the proposed query mechanism is a logic-based language that is capable to return time, value, and time-series outputs, as well as Boolean queries. We can also use the language for node selection and path selection. Furthermore, we propose an implementation of this language in a graph database system and evaluate its working on a fragment of the Flemish river system that is equipped with sensors that measure the water height at regular moments in time.

Scalable Data Model for Traffic Congestion Avoidance in a Vehicle to Cloud Infrastructure

Traffic congestion experience in urban areas has negative impact on our daily lives by consuming our time and resources. Intelligent Transportation Systems can provide the necessary infrastructure to mitigate such challenges. In this paper, we propose a novel and scalable solution to model, store and control traffic data based on range query data structures (K-ary Interval Tree and K-ary Entry Point Tree) which allows data representation and handling in a way that better predicts and avoids traffic congestion in urban areas. Our experiments, validation scenarios, performance measurements and solution assessment were done on Brooklyn, New York traffic congestion simulation scenario and shown the validity, reliability, performance and scalability of the proposed solution in terms of time spent in traffic, run-time and memory usage. The experiments on the proposed data structures simulated up to 10,000 vehicles having microseconds time to access traffic information and below 1.5 s for congestion free route generation in complex scenarios. To the best of our knowledge, this is the first scalable approach that can be used to predict urban traffic and avoid congestion through range query data structure traffic modelling.

Large-Scale Road Network Congestion Pattern Analysis and Prediction Using Deep Convolutional Autoencoder

The transportation system, especially the road network, is the backbone of any modern economy. However, with rapid urbanization, the congestion level has surged drastically, causing a direct effect on the quality of urban life, the environment, and the economy. In this paper, we propose (i) an inexpensive and efficient Traffic Congestion Pattern Analysis algorithm based on Image Processing, which identifies the group of roads in a network that suffers from reoccurring congestion; (ii) deep neural network architecture, formed from Convolutional Autoencoder, which learns both spatial and temporal relationships from the sequence of image data to predict the city-wide grid congestion index. Our experiment shows that both algorithms are efficient because the pattern analysis is based on the basic operations of arithmetic, whereas the prediction algorithm outperforms two other deep neural networks (Convolutional Recurrent Autoencoder and ConvLSTM) in terms of large-scale traffic network prediction performance. A case study was conducted on the dataset from Seoul city.

BwimNet: A Novel Method for Identifying Moving Vehicles Utilizing a Modified Encoder-Decoder Architecture

Traffic loading monitoring plays an important role in bridge structural health monitoring, which is helpful in overloading detection, transportation management, and safety evaluation of transportation infrastructures. Bridge weigh-in-motion (BWIM) is a method that treats traffic loading monitoring as an inverse problem, which identifies the traffic loads of the target bridge by analyzing its dynamic strain responses. To achieve accurate prediction of vehicle loads, the configuration of axles and vehicle velocity must be obtained in advance, which is conventionally acquired via additional axle-detecting sensors. However, problems arise from additional sensors such as fragile stability or expensive maintenance costs, which might plague the implementation of BWIM systems in practice. Although data-driven methods such as neural networks can estimate traffic loadings using only strain sensors, the weight data of vehicles crossing the bridge is difficult to obtain. In order to overcome these limitations, a modified encoder-decoder architecture grafted with signal-reconstruction layer is proposed in this paper to identify the properties of moving vehicles (i.e., velocity, wheelbase, and axle weight) using merely the bridge dynamic response. Encoder-decoder is an unsupervised method extracting higher features from original data. The numerical bridge model based on vehicle-bridge coupling vibration theory is established to illustrate the applicability of this new encoder-decoder method. The identification results demonstrate that the proposed approach can predict traffic loadings without using additional sensors and without requiring vehicle weight labels. Parametric studies also show that this new approach achieves better stability and reliability in identifying the properties of moving vehicles, even under the circumstances of large data pollution.

A Survey of Road Traffic Congestion Measures towards a Sustainable and Resilient Transportation System

Traffic congestion is a perpetual problem for the sustainability of transportation development. Traffic congestion causes delays, inconvenience, and economic losses to drivers, as well as air pollution. Identification and quantification of traffic congestion are crucial for decision-makers to initiate mitigation strategies to improve the overall transportation system’s sustainability. In this paper, the currently available measures are detailed and compared by implementing them on a daily and weekly traffic historical dataset. The results showed each measure showed significant variations in congestion states while indicating a similar congestion trend. The advantages and disadvantages of each measure are identified from the data analysis. This study summarizes the current road traffic congestion measures and provides a constructive insight into the development of a sustainable and resilient traffic management system.

Short-Term Traffic Flow Forecasting Based on Data-Driven Model

Short-term traffic flow forecasting is the technical basis of the intelligent transportation system (ITS). Higher precision, short-term traffic flow forecasting plays an important role in alleviating road congestion and improving traffic management efficiency. In order to improve the accuracy of short-term traffic flow forecasting, an improved bird swarm optimizer (IBSA) is used to optimize the random parameters of the extreme learning machine (ELM). In addition, the improved bird swarm optimization extreme learning machine (IBSAELM) model is established to predict short-term traffic flow. The main researches in this paper are as follows: (1) The bird swarm optimizer (BSA) is prone to fall into the local optimum, so the distribution mechanism of the BSA optimizer is improved. The first five percent of the particles with better fitness values are selected as producers. The last ten percent of the particles with worse fitness values are selected as beggars. (2) The one-day and two-day traffic flows are predicted by the support vector machine (SVM), particle swarm optimization support vector machine (PSOSVM), bird swarm optimization extreme learning machine (BSAELM) and IBSAELM models, respectively. (3) The prediction results of the models are evaluated. For the one-day traffic flow sequence, the mean absolute percentage error (MAPE) values of the IBSAELM model are smaller than the SVM, PSOSVM and BSAELM models, respectively. The experimental analysis results show that the IBSAELM model proposed in this study can meet the actual engineering requirements.

Freeway Short-Term Travel Speed Prediction Based on Data Collection Time-Horizons: A Fast Forest Quantile Regression Approach

Short-term traffic speed prediction is vital for proactive traffic control, and is one of the integral components of an intelligent transportation system (ITS). Accurate prediction of short-term travel speed has numerous applications for traffic monitoring, route planning, as well as helping to relieve traffic congestion. Previous studies have attempted to approach this problem using statistical and conventional artificial intelligence (AI) methods without accounting for influence of data collection time-horizons. However, statistical methods have received widespread criticism concerning prediction accuracy performance, while traditional AI approaches have too shallow architecture to capture non-linear stochastics variations in traffic flow. Hence, this study aims to explore prediction of short-term traffic speed at multiple time-ahead intervals using data collected from loop detectors. A fast forest quantile regression (FFQR) via hyperparameters optimization was introduced for predicting short-term traffic speed prediction. FFQR is an ensemble machine learning model that combines several regression trees to improve speed prediction accuracy. The accuracy of short-term traffic speed prediction was compared using the FFQR model at different data collection time-horizons. Prediction results demonstrated the adequacy and robustness of the proposed approach under different scenarios. It was concluded that prediction performance of FFQR was significantly enhanced and robust, particularly at time intervals larger than 5 min. The findings also revealed that speed prediction error (in terms of quantiles loss) ranged between 0.58 and 1.18.

TrafficWave: Generative Deep Learning Architecture for Vehicular Traffic Flow Prediction

Vehicular traffic flow prediction for a specific day of the week in a specific time span is valuable information. Local police can use this information to preventively control the traffic in more critical areas and improve the viability by decreasing, also, the number of accidents. In this paper, a novel generative deep learning architecture for time series analysis, inspired by the Google DeepMind’ Wavenet network, called TrafficWave, is proposed and applied to traffic prediction problem. The technique is compared with the most performing state-of-the-art approaches: stacked auto encoders, long–short term memory and gated recurrent unit. Results show that the proposed system performs a valuable MAPE error rate reduction when compared with other state of art techniques.

Traffic Speed Prediction: An Attention-Based Method

Short-term traffic speed prediction has become one of the most important parts of intelligent transportation systems (ITSs). In recent years, deep learning methods have demonstrated their superiority both in accuracy and efficiency. However, most of them only consider the temporal information, overlooking the spatial or some environmental factors, especially the different correlations between the target road and the surrounding roads. This paper proposes a traffic speed prediction approach based on temporal clustering and hierarchical attention (TCHA) to address the above issues. We apply temporal clustering to the target road to distinguish the traffic environment. Traffic data in each cluster have a similar distribution, which can help improve the prediction accuracy. A hierarchical attention-based mechanism is then used to extract the features at each time step. The encoder measures the importance of spatial features, and the decoder measures the temporal ones. The proposed method is evaluated over the data of a certain area in Hangzhou, and experiments have shown that this method can outperform the state of the art for traffic speed prediction.