Short Term Predictions of Traffic Flow Characteristics using ML Techniques

The intelligent transportation system seeks to reduce traffic and improve the driving experience. They give us a lot of data that we can use to improve services for both the public and transportation officials by feeding it into machine learning systems. Most importantly, Traffic environment refers to everything that might have an impact on how much traffic is moving down the road, including traffic signals, accidents, protests, and even road repairs that might result in a backup. A motorist or rider can make an informed choice if they have previous knowledge that is very close to approximate all the above and many more real-world circumstances that can affect traffic. Additionally, it aids in the development of driverless vehicles. Traffic data have been growing dramatically in recent decades, and we are moving toward big data concepts for transportation. The current approaches for predicting traffic flow use some traffic prediction models, however they are still inadequate to handle practical situations. We thus aimed to focus on the traffic flow forecast problem using the traffic data and prediction models. The proposed model called DRGNN, a dilated recurrent graph neural network framework aims to effectively analyze and predict the traffic pattern by considering the spatial (space) and temporal (time) aspects of the real-time traffic data considering social relationships between internet of vehicles which indeed produced accurate and valuable insights that could help in deploying the model in any suitable real-time traffic monitoring and prediction system.

As one of the most widely used applications of the Internet of Things (IoT), intelligent transportation system (ITS) is of great significance for urban traffic planning, traffic control, and traffic guidance. However, widespread traffic congestion occurs with the increased number of vehicles. The traffic flow prediction is a good idea for traffic congestion. Therefore, many schemes have been proposed for accurate and real-time traffic flow prediction, but there still exist many issues, including low accuracy, weak adaptability and inferior real-time. Meanwhile, the complex spatial and temporal dependencies in traffic flow are still challenging. To address the above issues, we propose a novel spatial-temporal Chebyshev graph neural network model (ST-ChebNet) for traffic flow prediction to capture the spatial-temporal features, which can ensure accurate traffic flow prediction. Concretely, we first add a fully connected layer to fuse the features of traffic data into a new feature to generate a matrix, and then the long short-term memory (LSTM) model is adopted to learn traffic state changes for capturing the temporal dependencies. Then, we use the Chebyshev graph neural network (ChebNet) to learn the complex topological structures in the traffic network for capturing the spatial dependencies. Eventually, the spatial features and the temporal features are fused to guarantee the traffic flow prediction. The experiments show that ST-ChebNet can make accurate and real-time traffic flow prediction compared with other eight baseline methods on real-world traffic data sets PeMS.

Transportation projects require an enormous amount of capital investment resulting from their tremendous size, complexity, and risk. Due to the limitation of public finances, the private sector is invited to participate in transportation project development. The private sector can entirely or partially invest in transportation projects in the form of Public-Private Partnership (PPP) scheme, which has been an attractive option for several developing countries, including Vietnam. There are many factors affecting the success of PPP projects. The accurate prediction of traffic volume is considered one of the key success factors of PPP transportation projects. However, only few research works investigated how to predict traffic volume over a long period of time. Moreover, conventional traffic volume forecasting methods are usually based on deterministic models which predict a single value of traffic volume but do not consider risk and uncertainty. This knowledge gap makes it difficult for concessionaires to estimate PPP transportation project revenues accurately. The objective of this paper is to develop a probabilistic traffic volume prediction model. First, traffic volumes were estimated following the Geometric Brownian Motion (GBM) process. Monte Carlo technique is then applied to simulate different scenarios. The results show that this stochastic approach can systematically analyze variations in the traffic volume and yield more reliable estimates for PPP projects.

Traffic prediction is crucial for transportation management and user convenience. With the rapid development of deep learning techniques, numerous models have emerged for traffic prediction. Recurrent Neural Networks (RNNs) are extensively utilized as representative predictive models in this domain. This paper comprehensively reviews RNN applications in traffic prediction, focusing on their significance and challenges. The review begins by discussing the evolution of traffic prediction methods and summarizing state-of-the-art techniques. It then delves into the unique characteristics of traffic data, outlines common forms of input representations in traffic prediction, and generalizes an abstract description of traffic prediction problems. Then, the paper systematically categorizes models based on RNN structures designed for traffic prediction. Moreover, it provides a comprehensive overview of seven sub-categories of applications of deep learning models based on RNN in traffic prediction. Finally, the review compares RNNs with other state-of-the-art methods and highlights the challenges RNNs face in traffic prediction. This review is expected to offer significant reference value for comprehensively understanding the various applications of RNNs and common state-of-the-art models in traffic prediction. By discussing the strengths and weaknesses of these models and proposing strategies to address the challenges faced by RNNs, it aims to provide scholars with insights for designing better traffic prediction models.

The paper validates an improved adaptive Kalman filter model (AKFM) for short-term traffic flow prediction on intersections in Shanghai, China. In this field, much research has been conducted in developed countries. However, less work has been done in China, a typical developing country, particularly dealing with the realtime prediction method with mixed traffic flow characteristics. This paper studies the adaptive mechanism method of time-window and the state transition parameters for improved model in detail, and carries out the characteristic and predictability analysis of the traffic flow volume using the detector data of an intersection in Shanghai, China. In addition, this paper has implemented the improved adaptive model in C++ and simulation results show it is effective, stable and self-adaptive. The findings of this study provide some useful insights into the short-term traffic flow prediction in urban intersections or other similar intersections in China.

Accurate traffic prediction is crucial to alleviating traffic congestion in cities. Existing physical sensor-based traffic data acquisition methods have high transmission costs, serious traffic information redundancy, and large calculation volumes for spatiotemporal data processing, thus making it difficult to ensure accuracy and real-time traffic prediction. With the increasing resolution of UAV imagery, the use of unmanned aerial vehicles (UAV) imagery to obtain traffic information has become a hot spot. Still, analyzing and predicting traffic status after extracting traffic information is neglected. We develop a framework for traffic speed extraction and prediction based on UAV imagery processing, which consists of two parts: a traffic information extraction module based on UAV imagery recognition and a traffic speed prediction module based on deep learning. First, we use deep learning methods to automate the extraction of road information, implement vehicle recognition using convolutional neural networks and calculate the average speed of road sections based on panchromatic and multispectral image matching to construct a traffic prediction dataset. Then, we propose an attention-enhanced traffic speed prediction module that considers the spatiotemporal characteristics of traffic data and increases the weights of key roads by extracting important fine-grained spatiotemporal features twice to improve the prediction accuracy of the target roads. Finally, we validate the effectiveness of the proposed method on real data. Compared with the baseline algorithm, our algorithm achieves the best prediction performance regarding accuracy and stability.

As the fundamental part of other Intelligent Transportation Systems (ITS) applications, short-term traffic volume prediction plays an important role in various intelligent transportation tasks, such as traffic management, traffic signal control and route planning. Although Neural-network-based traffic prediction methods can produce good results, most of the models can’t be explained in an intuitive way. In this paper, we not only proposed a model that increase the short-term prediction accuracy of the traffic volume, but also improved the interpretability of the model by analyzing the internal attention score learnt by the model. we propose a spatiotemporal attention mechanism-based multistep traffic volume prediction model (SAMM). Inside the model, an LSTM-based Encoder-Decoder network with a hybrid attention mechanism is introduced, which consists of spatial attention and temporal attention. In the first level, the local and global spatial attention mechanisms considering the micro traffic evolution and macro pattern similarity, respectively, are applied to capture and amplify the features from the highly correlated entrance stations. In the second level, a temporal attention mechanism is employed to amplify the features from the time steps captured as contributing more to the future exit volume. Considering the time-dependent characteristics and the continuity of the recent evolutionary traffic volume trend, the timestamp features and historical exit volume series of target stations are included as the external inputs. An experiment is conducted using data from the highway toll collection system of Guangdong Province, China. By extracting and analyzing the weights of the spatial and temporal attention layers, the contributions of the intermediate parameters are revealed and explained with knowledge acquired by historical statistics. The results show that the proposed model outperforms the state-of-the-art model by 29.51% in terms of MSE, 13.93% in terms of MAE, and 5.69% in terms of MAPE. The effectiveness of the Encoder-Decoder framework and the attention mechanism are also verified.

Proactive traffic management is a subset of smart mobility applications in which traffic control strategies are implemented in advance to respond to anticipated roadway conditions. Predicted traffic flows are a key input to proactive traffic control systems, such as proactive freeway ramp metering, proactive variable speed limits, and proactive incident management systems. This paper proposes a machine learning approach for short-term traffic flow prediction where prevailing conditions, such as the traffic volume, speed, and occupancy of roadway segments, are used to predict traffic flow in short-term intervals. Four categories of predictive methods for traffic flow prediction were investigated: deep neural networks, a distributed random forest, a gradient boosting machine, and a generalized linear model. Data from Interstate 64 in St. Louis, Missouri, in the United States were used to calibrate and evaluate the models. The results obtained by the four predictive methods were very similar, with the distributed random forest model slightly outperforming the models obtained by the other three methods. The case study showed that the inclusion of traffic flow, speed, occupancy, and time of day in the traffic prediction process reduces the traffic prediction error. However, the two-sample Kolmogorov-Smirnov test did not show a statistically significant benefit from the inclusion of upstream traffic data in the distributed random forest, and gradient boosting machine models.

Short-term traffic flow prediction plays an important role in intelligent transportation system. Numerous researchers have paid much attention to it in the past decades. However, the performance of traditional traffic flow prediction methods is not satisfactory, for those methods cannot describe the complicated nonlinearity and uncertainty of the traffic flow precisely. Neural networks were used to deal with the issues, but most of them failed to capture the deep features of traffic flow and be sensitive enough to the time-aware traffic flow data. In this paper, we propose a deep bi-directional long short-term memory (DBL) model by introducing long short-term memory (LSTM) recurrent neural network, residual connections, deeply hierarchical networks and bi-directional traffic flow. The proposed model is able to capture the deep features of traffic flow and take full advantage of time-aware traffic flow data. Additionally, we introduce the DBL model, regression layer and dropout training method into a traffic flow prediction architecture. We evaluate the prediction architecture on the dataset from Caltrans Performance Measurement System (PeMS). The experiment results demonstrate that the proposed model for short-term traffic flow prediction obtains high accuracy and generalizes well compared with other models.

This paper proposes a unified spatio-temporal model on the basis of STARIMA (Space-Time AutoRegressive Integrated Moving Average) for short-term road traffic prediction. The contributions of this paper are as follows. First, we develop a physically intuitive approach to traffic prediction that captures the time-varying spatio-temporal correlation between traffic at different measurement points. The spatio-temporal correlation is affected by the road network topology, time-varying speed, and time-varying trip distribution. Distinctly different from previous black-box approaches to road traffic modeling and prediction, parameters of the proposed approach have physically intuitive meanings which make them readily amenable to suit changing road and traffic conditions. Second, unlike some existing techniques which capture the variation of spatio-temporal correlation by a complete redesign and calibration of the model, the proposed approach uses a unified model which incorporates the physical factors potentially affecting the variation of spatio-temporal correlation into a series of parameters. These parameters are relatively easy to control and adjust when road and traffic conditions change, thereby greatly reducing the computational complexity. Experiments using two set of real traffic traces demonstrate that the proposed approach has superior accuracy compared with the widely used ARIMA (AutoRegressive Integrated Moving Average) and is only marginally inferior to that obtained by constructing multiple STARIMA models for different time of the day, however with a much reduced computational and implementation complexity.

Real-time traffic jams prediction inspired by Biham, Middleton and Levine (BML) model

In recent years, traffic flow prediction has attracted increasing interest from both academia and industry, and existing data-driven learning models for traffic flow prediction have achieved excellent success. However, this requires a large number of datasets for efficient model training, while it is difficult to acquire all the data from one agent, and thus data collaboration among different agents becomes an attracting trend. Moreover, with the increase in the number of agents, how to perform accurate multi-agent traffic forecasting while protecting privacy is an important issue. To address this challenge, we introduce a privacy-preserving federated learning framework. In this paper, we propose a novel Dynamic Spatio-Temporal traffic flow prediction model based on graph convolutional network (DST-GCN), which incorporates both dynamic spatial and temporal dependence of intersection traffic. In addition, we provide an improved federated learning framework with opportunistic client selection (FLoS). In the proposed FLoS protocol, we employ a FedAVG algorithm for secure parameter aggregation and design an optimal client selection algorithm to reduce the communication overhead during the transfer of model updates. Experiments based on real-world datasets demonstrate that our proposed DST-GCN traffic prediction model outperforms state-of-the-art baseline models. And our proposed FLoS can achieve superior results while reducing communication consumption. © 2022 IEEE.

Traffic flow prediction plays a vital role in the real-time control of intelligent transportation system. A number of prediction models are established and achieve good results. However, most of these models ignore the intrinsic characteristics of traffic flow data, which can hardly optimize prediction models accordingly. This paper analyzes the characteristics of traffic flow time series and proposes a mode decomposition based hybrid model for traffic prediction. Firstly, the original sequence is decomposed by a mode decomposition algorithm, and the periodic sequence and two-part random sequences are obtained. Then, according to the complexity of decomposed subsequences, a hybrid prediction model with BP, e-SVR and LSTM models is established to predict decomposed subsequences respectively. Finally, the final result is obtained by combining the prediction results of decomposed subsequences. Considering practical application scenario, the proposed model chooses to predict multi-prediction intervals instead of only predicting one single interval, but the predication flow data is still updated in accordance with one interval. The dataset from Caltrans Performance Measurement System is used in experiments. Comparing with typical single predicting models, experiment results show that the proposed hybrid model achieves higher accuracy.

Intelligent transportation systems can't function well without reliable data on current traffic conditions. As the volume of traffic data has increased in the last several years, we've entered the era of big data in transportation. Current methods for estimating traffic flow have been let down many real-world applications, which depend mostly on shallow traffic prediction models. Therefore, we'll review the difficulty of predicting traffic flow using detailed architectural models and a vast quantity of actual traffic data. Methods for traffic flow forecasting that consider both spatial and temporal correlations are given in this article. A layered auto encoder model is used to teach traffic flow characteristics since it builds up greedy layer by layer. Deep architecture models for traffic flow prediction have never before used auto encoders as building blocks. Researchers have also shown that the recommended method for estimating traffic flow is more accurate.

One of the main issues facing contemporary smart cities is urban traffic congestion, which causes delays, fuel waste, and elevated air pollution. This paper describes an intelligent traffic flow management system that combines machine learning models for real-time vehicle detection, classification, and traffic prediction with the YOLO (You Only Look Once) object detection algorithm. In order to predict congestion levels and optimize signal timings, the suggested system uses machine learning regression and clustering techniques, records live traffic video feeds, and uses YOLOv8 to detect and count vehicles. In comparison to conventional sensor-based techniques, experimental results show a detection accuracy of 95.7% and a traffic flow prediction accuracy of 93.2%. For next-generation smart cities, this combination of deep learning and machine learning guarantees effective, scalable, and adaptive traffic control.