Short-term Traffic Flow Research Articles

Intelligent Traffic Control System Based on Cloud Computing and Big Data Mining

This article aims at discussing problems such as complex object types, large amount of data collection, high demand for transmission and calculation, and weak real-time scheduling and control ability in the construction of modern intelligent traffic information physical fusion network, cloud-based control system theory, modern intelligent traffic control network as the research object, and the physical design of the intelligent transportation information fusion cloud control system scheme. The scheme includes intelligent transportation edge control technology and intelligent transportation network virtualization technology. Based on intelligent traffic flow data, in the center of the cloud control management server using deep learning and overrun learning machine intelligence study methods, such as the forecast of traffic flow data for training, to predict urban road short-term traffic flow and congestion. Further up in the air by using intelligent optimization scheduling algorithm for real-time traffic flow control strategy, the simulation results show the effectiveness of the proposed method.

A Short-Term Traffic Flow Prediction to Control Traffics in Large Scale Transportation using Internet of Things

Traffic congestion is the key problem that occurs across urban metropolises around the world. Due to the increase in transportation vehicles the fixed light time on traffic signals not able to solve the traffic congestion problem. In this paper, First, we develop an IoT based system which is capable of streaming the traffic surveillance footages to cloud storage, then the vehicle count is recorded every 30 sec interval and updated in the traffic flow dataset. Second the traffic flow is predicted using our CNN-LSTM residual learning model. Finally, the predicted value is classified and traffic density at each road section is identified, thereby passing this density value to green light time calculation to set an optimal green time to reduce the traffic congestion. The traffic flow dataset, China is used for training and testing to forecast the short time traffic flow across the road section. Experiment results shows that our model has best accuracy by lowering the RMSE value.

EnLSTM-WPEO: Short-Term Traffic Flow Prediction by Ensemble LSTM, NNCT Weight Integration, and Population Extremal Optimization

Accurate and stable short-term traffic flow prediction is an indispensable part in current intelligent transportation systems. In this paper, a novel short-term traffic flow forecasting model termed as EnLSTM-WPEO is proposed based on ensemble learning of long short term memory neural network (LSTM), no negative constraint theory (NNCT) weight integration and population extremal optimization (PEO) algorithm. In the first stage, a cluster of LSTMs is constructed to separately forecast with different time lag, which is a significant element to affect the prediction performance. In the second stage, the PEO-based NNCT weight integration strategy is introduced to determine the weight coefficients of the ensemble model. The simulation results for six different datasets from highways of Seattle have testified the superiority of the proposed EnLSTM-WPEO to other six popular traffic flow forecasting models in terms of two commonly used performance indices and three statistical tests.

A new grey model for traffic flow mechanics

Accurate and real-time short-term traffic flow prediction is the core technology of an intelligent transportation system. In this paper, the vehicle conservation principle of traffic flow mechanics is applied to study the differential equation of traffic flow is established by analysing traffic flow parameters. Using the principle of grey difference information, and a grey model of traffic flow in a road section is proposed. This model obtains traffic flow information about traffic flow inflow and congestion via matrix least squares technology and obtains the time response function and modelling steps of the model using a mathematical analysis method, which is applied to short-term traffic flow prediction. The results of three short-term traffic flow cases show that the simulation and prediction results of the new model are better than those of other grey models and two machine learning methods. Relevant information about the traffic flow parameters obtained by the new model is consistent with an actual situation of traffic flow.

Short-term traffic flow prediction based on faded memory Kalman Filter fusing data from connected vehicles and Bluetooth sensors

This paper proposes a Kalman Filter (KF) technique to predict the short-term flow at urban arterials based on the information of connected and Bluetooth equipped vehicles. Online traffic flow prediction using real-time data derived from different sensors is still an open research subject. To this end, a Kalman Filter model is developed to predict traffic flow based on two sources of real-time data, i.e. Connected Vehicles (CVs) and Bluetooth data. We also apply a Faded Memory Kalman Filter (FMKF) by considering more weights for new measurements to overcome the issue of inaccuracy in the prediction model and to predict the traffic flow with more resolution. At first, based on training data from Vissim traffic simulator, parameters of the KF's equations are calibrated using a machine learning based and big data processing. Performance of the conventional and faded memory KF models are then validated and compared using some test data pertaining to different rates of connected vehicles and Bluetooth-equipped vehicles (BVs). We use a pilot study of the city of Melbourne, Australia for numerical tests. The results indicate significant superiority of the FMKF over the KF in various traffic situations, as such the prediction error in some cases has reduced up to 60%. This paper contributes to the literature in three folds: (i) It uses a computationally efficient flow prediction algorithm based on synthesizing data from CVs and BVs (ii) It proposes to use an adaptive form of KF (i.e. FMKF) to compensate for the prediction error originating from modelling error. Hence, the model can perform well for a range of traffic conditions (iii) The proposed model works well even with low penetration rates (PRs) of the CVs or BVs (say 20%).

Research on GSTAR-SVM Traffic Prediction Model Based on Wavelet Transform

With the continuous advancement of urbanization in China, the number of urban vehicles has increased rapidly, and traffic congestion has become an urgent problem for modern cities. Therefore, accurate real-time traffic flow prediction is of great significance for solving this problem. However, traffic flow, as a special type of prediction object, has the characteristics of complexity, uncertainty and nonlinearity, which bring great difficulties to the prediction, and the external spatial correlation also has a great influence on the prediction results. In this paper, based on the above problems, the GSTAR-SVM traffic prediction model based on wavelet transform is constructed to predict the short-term traffic flow, and the model is verified based on the data. The experimental results show that the proposed model has higher prediction accuracy.

Fuzzy hybrid framework with dynamic weights for short‐term traffic flow prediction by mining spatio‐temporal correlations

Forecasting short-term traffic flows is crucial in designing intelligent transportation systems. There has been significant research on this topic; however, no single model can maintain optimality under all conditions. This study analysed the complementarity of non-parametric regression and deep learning in terms of prediction accuracy. Then, a mixed prediction method, combining two sub-models based on a fuzzy logic system, was constructed. First, the two sub-models based on long-short-term memory) and K-nearest neighbour were improved, by extracting more features that consider the spatial-temporal correlations of traffic flow and the influences of specific contextual factors to the traffic flow. Second, a fusion mechanism with dynamic weights was presented to optimise the mix predictor. A compensation term was added based on the deviations. Finally, the new method was tested using real data in Seattle, Washington. The results show that the proposed model predicts the flow for the next 5 min across the verification set, with a 6.42% mean absolute percentage error and 31.49 standard error. These results are more accurate and robust than those achieved with other state-of-the-art models.

Forecasting Short-Term Passenger Flow: An Empirical Study on Shenzhen Metro

Forecasting short-term traffic flow has been a critical topic in transportation research for decades, which aims to facilitate dynamic traffic control proactively by monitoring the present traffic and foreseeing its immediate future. In this paper, we focus on forecasting short-term passenger flow at subway stations by utilizing the data collected through an automatic fare collection (AFC) system along with various external factors, where passenger flow refers to the volume of arrivals at stations during a given period of time. Along this line, we propose a data-driven three-stage framework for short-term passenger flow forecasting, consisting of traffic data profiling, feature extraction, and predictive modeling. We investigate the effect of temporal and spatial features as well as external weather influence on passenger flow forecasting. Various forecasting models, including the time series model auto-regressive integrated moving average, linear regression, and support vector regression, are employed for evaluating the performance of the proposed framework. Moreover, using a real data set collected from the Shenzhen AFC system, we conduct extensive experiments for methods validation, feature evaluation, and data resolution demonstration.

Short Term Road Traffic Flow Forecasting using Artificial Neural Network

In recent days, road traffic management and congestion control has become major problems in any busy junction in Hyderabad city. Hence short term traffic flow forecasting has gained greater importance in Intelligent Transport System(ITS). Artificial Neural Network(ANN) models have been fruitfully applied for classification and prediction of time series. In this paper, an attempt has been made to model and forecast short-term traffic flow at 6.no. junction in Amberpet, Hyderabad, Telangana state, India applying Neural Network models. The traffic data has been considered for peak hours in the morning for 8A.M to 12 Noon, for 5 days. Multilayer Perceptron (MLP) network model is used in this study. These results can be considered to monitor traffic signals and explore methods to avoid congestion at that junction.

Traffic Flow Prediction using Combination of Support Vector Machine and Rough Set

Congestion is the primary issue related to traffic flow. Avoiding congestion after getting into is not possible. So the only way is to make the informed decision by knowing the traffic situation in advance. This can be achieved with the help of traffic flow prediction. In the proposed work, short term traffic flow prediction is performed using support vector machine in combination with rough set. Traffic data used for analysis is collected from three adjacent intersections of Nagpur city and traffic flow is predicted at downstream junction. The work has attempted to study the effect of aggregation intervals and past samples on the prediction performance using MSE threshold variation. Rough set is used as a post processor to validate the prediction result. Accurate and timely prediction can provide reliability for optimized traffic control and guidance.

A noise-immune Kalman filter for short-term traffic flow forecasting

This paper formulates the traffic flow forecasting task by introducing a maximum correntropy deduced Kalman filter. The traditional Kalman filter is based on minimum mean square error, which performs well under Gaussian noises. However, the real traffic flow data are fulfilled with non-Gaussian noises. The traditional Kalman filter may rot under this situation. The Kalman filter deduced by maximum correntropy criteria is insensitive to non-Gaussian noises, meanwhile retains the optimal state mean and covariance propagation of the traditional Kalman filter. To achieve this, a fix-point algorithm is embedded to update the posterior estimations of maximum correntropy deduced Kalman filter. Extensive experiments on four benchmark datasets demonstrate the outperformance of this model for traffic flow forecasting.

A novel learning method for multi-intersections aware traffic flow forecasting

Recent advances in machine learning have helped solve many challenges in artificial intelligence applications, such as traffic flow forecasting. Traffic flow forecasting models based on machine learning have recently been widely applied because of their great generalisation capability. This study aims to construct a multi-intersection-aware traffic flow prognostication architecture considering recent information of a nearby road, which is a significant indicator of the near-future traffic flow, and considering the selection of appropriate and essential sensors significantly correlated to the future traffic flow. To capture the inner correlation between sequential traffic flow data, a novel learning method involving the relevance vector machine is employed for the traffic flow forecasting. To optimise the kernel parameters of the relevance vector machine, a combination of the chaos theory and a simulated annealing algorithm is adopted. The proposed model is verified with the real-world data of six roads in a Minnesotan city. Then, the forecasting results of the new model are compared with those of some state-of-the-art models. These results indicate that the application of relevance vector regression to short-term traffic flow forecasting combined with a chaos-simulated annealing algorithm to optimise the corresponding parameters is a high-precision and -scalability short-term traffic flow forecasting method. The multi-intersection-aware mechanism helps improve the forecasting accuracy.

An inertia grey discrete model and its application in short-term traffic flow prediction and state determination

A traffic flow system is a complex dynamic system. Traffic flows data are the product of the velocity and density, and its data have dynamic and fluctuation characteristics. Therefore, three new inertia grey discrete models (IDGMs) were proposed and used to estimate short-term traffic flow based on traffic flow data mechanics and characteristics and traffic-state characteristics. The modelling process of the traditional grey DGM using the least square method may lead to a large parameter estimation deviation and a low model precision. The new model uses the mechanical characteristics of the data and applies the evolutionary process of the mechanical decomposition of the data to the modelling process. It has a more reasonable modelling process and a more stable structure and solves the shortcomings of the traditional grey DGM parameter estimation. Moreover, it uses matrix analysis to study the important characteristics of the IDGM, and it simplifies the forms of the parameter model and structural model. Then, the traffic flow of the Whitemud Drive City Expressway in Canada is analysed empirically, and the effect of the new model and the judgment of three-phase traffic flow state are analysed.

Deep belief network-based support vector regression method for traffic flow forecasting

Instability is a common problem in deep belief network–back propagation forecasting model, and the trend of traffic data will affect the forecasting results of the model. Therefore, this paper proposes a short-term traffic flow forecasting method based on deep belief network–support vector regression. Support vector regression classifier SVR is used at the top of the model. Data processing is from bottom to top. Firstly, at the bottom of the model, the input traffic flow data are processed differently; then, the DBN model is used to learn the traffic flow characteristics. Finally, SVR is used to predict the traffic flow at the top of the model. The average absolute error of the prediction is 9.57%, and the average relative error is 5.91%. The relationship between the predicted value and the actual traffic flow data is found through simulation experiments. The predicted value of the model proposed in this paper is in good agreement with the measured value, and the prediction accuracy is high. The model can effectively predict short-term traffic flow. Finally, compared with the traditional DBN prediction model and other common prediction models, the proposed prediction model has higher prediction accuracy.

Using Kalman filter algorithm for short-term traffic flow prediction in a connected vehicle environment

We develop a Kalman filter for predicting traffic flow at urban arterials based on data obtained from connected vehicles. The proposed algorithm is computationally efficient and offers a real-time prediction since it invokes the connected vehicle data just before the prediction period. Moreover, it can predict the traffic flow for various penetration rates of connected vehicles (the ratio of the number of connected vehicles to the total number of vehicles). At first, the Kalman filter equations are calibrated using data derived from Vissim traffic simulator for different penetration rates, different fluctuating arrival rates of vehicles and various signal settings. Then the filter is evaluated for a variety of traffic scenarios generated in Vissim simulator. We evaluate the performance of the algorithm for different penetration rates under several traffic situations using some statistical measures. Although many of the previous prediction methods depend highly on data from fixed sensors (i.e., loop detectors and video cameras), which are associated with huge installation and maintenance costs, this study provides a low-cost mean for short-term flow prediction only based on the connected vehicle data.

Short-term traffic flow prediction based on spatio-temporal analysis and CNN deep learning

Accurate short-term traffic flow forecasting facilitates active traffic control and trip planning. Most existing traffic flow models fail to make full use of the temporal and spatial features of traffic data. This study proposes a short-term traffic flow prediction model based on a convolution neural network (CNN) deep learning framework. In the proposed framework, the optimal input data time lags and amounts of spatial data are determined by a spatio-temporal feature selection algorithm (STFSA), and selected spatio-temporal traffic flow features are extracted from actual data and converted into a two-dimensional matrix. The CNN then learns these features to construct a predictive model. The effectiveness of the proposed method is evaluated by comparing the forecast results with actual traffic data. Other existing models are also evaluated for comparison. The proposed method outperforms baseline models in terms of accuracy.

Research on short-term traffic flow prediction method based on real-time traffic status

In order to improve the accuracy of short-term traffic flow prediction, this paper focuses on the influence of road traffic status division on the accuracy of short-term traffic flow prediction. When dividing the road traffic status, the improved road load coefficient is adopted, and the kalman filter method and ARMA algorithm are selected to predict the short-term road traffic flow.

Research on Urban Short-term Traffic Flow Forecasting Model

Short-term traffic flow forecasting is one of the key technologies of ITS, and it is also the basis of traffic control and road navigation. According to the characteristics of short-term traffic flow, combining with the actual traffic flow data of an intersection in Hefei City, a prediction model based on BP neural network is constructed. The experimental results show that the model reflects the change rule and trend of short-term traffic flow, and the prediction accuracy is high.

Short-Term Traffic Flow Prediction Based on the IMM-BP-UKF Model

This study aims to obtain satisfactory short-term traffic flow forecasting results in various traffic flow modes. Clustering analysis of traffic flow data is carried out using the Kohonen neural network. Then, different BP neural networks are trained using different classified traffic flow data. Different neural network models are combined with UKF to form multiple traffic estimators to realize the estimation function. Finally, the interactive method is used to fuse the prediction results of each estimator, and comprehensive traffic flow forecasting results are obtained. With the simulation example, a number of single estimators are obtained, and a joint estimator based on this method is constructed. The section flow of one given road is predicted to verify the performance of the estimator. Results show that the joint estimator has a higher prediction accuracy than the single estimator and has adaptive characteristics when traffic flow characteristics change.

Adaptive Multi-Kernel SVM With Spatial–Temporal Correlation for Short-Term Traffic Flow Prediction

Accurate estimation of the traffic state can help to address the issue of urban traffic congestion, providing guiding advices for people’s travel and traffic regulation. In this paper, we propose a novel short-term traffic flow prediction algorithm based on an adaptive multi-kernel support vector machine (AMSVM) with spatial–temporal correlation, which is named as AMSVM-STC. First, we explore both the nonlinearity and randomness of the traffic flow, and hybridize Gaussian kernel and polynomial kernel to constitute the AMSVM. Second, we optimize the parameters of AMSVM with the adaptive particle swarm optimization algorithm, and propose a novel method to make the hybrid kernel’s weight adjust adaptively according to the change tendency of real-time traffic flow. Third, we incorporate the spatial–temporal correlation information with AMSVM to predict the short-term traffic flow. We evaluate our algorithm by doing thorough experiment on real data sets. The results demonstrate that our algorithm can do a timely and adaptive prediction even in the rush hour when the traffic conditions change rapidly. At the same time, the proposed AMSVM-STC outperforms the existing methods.