Accurate Traffic Flow Prediction Research Articles

Short-term traffic flow prediction based on optimised support vector regression

In order to provide accurate and reliable prediction of short-term traffic flow to realise intelligent transportation control, support vector machine (SVM) regression method is established to predict short-term traffic flow. Then, parameter selection optimisation model for SVM is studied. Support vector penalty coefficient and the parameters of the kernel function play an important role in learning precision and generalisation ability of regression model. So, a kind of improved artificial fish swarm algorithm is used to optimise the SVM regression to select the optimal parameters. The experiment results show that the proposed scheme can effectively reduce mean absolute percentage error and mean square error in the real traffic flow forecasting. The proposed scheme can improve the prediction precision of the short-term traffic flow.

Pruned Fast Learning Fuzzy Approach for Data-Driven Traffic Flow Prediction

Traffic flow prediction plays an important role in intelligent transportation systems. With the rapid growth of traffic flow data, fast and accurate traffic flow prediction methods are now required. In this paper, we propose a novel fast learning data-driven fuzzy approach for the traffic flow prediction problem. In the proposed approach, to achieve fast learning, an extreme learning machine is utilized to optimize the consequent parameters of the fuzzy rules. Further, a fuzzy rule pruning strategy that involves measuring the firing levels of the fuzzy rules is presented to obtain reduced fuzzy inference systems. To evaluate the performance of the proposed approach, it was experimentally applied to traffic flow prediction and its results compared with those of widely used methods. The experimental results verify that the proposed approach can achieve satisfactory performance. The comparisons show that the proposed approach can obtain better (sometimes similar) performances, but with a simpler structure, fewer parameters, and much faster learning speed than the other methods.

PERFORMANCE OF SELF-ORGANIZED AND METACOGNITIVE NEUROFUZZY SYSTEM FOR TRAFFIC FLOW PREDICTION

Accurate prediction of traffic flow is an important step needed in urban traffic management systems. While several neurofuzzy approaches have been used in literature for this particular problem, most of them need manual intervention in the formulation of the fuzzy rule base and also in determining the architecture of the neurofuzzy system. This paper evaluates two recent neurofuzzy algorithms that are capable of automatically determining the rule base and architecture in a purely data driven approach. An open source traffic data has been evaluate and compare the performance of these neurofuzzy systems.

Monte Carlo simulation-based traffic speed forecasting using historical big data

Because the traffic patterns on roads vary according to the roads’ specific spatio-temporal behavior, if we would like to forecast the traffic speed by day of the week, it is necessary to determine an optimal set of the highly related historical patterns to achieve high prediction accuracy. The goal of our paper is to suggest a new statistical modeling method that finds the best historical dataset according to various analyses for each link and provides a more accurate prediction of traffic flow by day of the week. First, we suggest a three-step filtering algorithm based on changepoint analysis, correlation analysis, and Monte Carlo simulation to simultaneously find and remove historical data outliers. Second, we determine the optimal historical data range by using decision factors such as the Mean Squared Error (MSE) and Akaike Information Criterion. Moreover, to verify our statistical model, we use various prediction accuracy measures such as Mean Absolute Percentage Error (MAPE), R-squared value, and Root MSE (RMSE). Finally, we construct a big data processing framework to handle the overall prediction process and calculate large amounts of traffic data. The forecasting results show that the proposed model can achieve a high prediction accuracy for each road by using three measures: less than 20% for MAPE, more than 80% for R-squared value, and less than 1 on average for RMSE.

Short-term traffic flow prediction using seasonal ARIMA model with limited input data

Accurate prediction of traffic flow is an integral component in most of the Intelligent Transportation Systems (ITS) applications. The data driven approach using Box-Jenkins Autoregressive Integrated Moving Average (ARIMA) models reported in most studies demands sound database for model building. Hence, the applicability of these models remains a question in places where the data availability could be an issue. The present study tries to overcome the above issue by proposing a prediction scheme using Seasonal ARIMA (SARIMA) model for short term prediction of traffic flow using only limited input data. A 3-lane arterial roadway in Chennai, India was selected as the study stretch and limited flow data from only three consecutive days was used for the model development using SARIMA. After necessary differencing to make the input time series a stationary one, the autocorrelation function (ACF) and partial autocorrelation function (PACF) were plotted to identify the suitable order of the SARIMA model. The model parameters were found using maximum likelihood method in R. The developed model was validated by performing 24 hrs. ahead forecast and the predicted flows were compared with the actual flow values. A comparison of the proposed model with historic average and naive method was also attempted. The effect of increase in sample size of input data on prediction results was studied. Short term prediction of traffic flow during morning and evening peak periods was also attempted using both historic and real time data. The mean absolute percentage error (MAPE) between actual and predicted flow was found to be in the range of 4–10, which is acceptable in most of the ITS applications. The prediction scheme proposed in this study for traffic flow prediction could be considered in situations where database is a major constraint during model development using ARIMA.

Robust causal dependence mining in big data network and its application to traffic flow predictions

In this paper, we focus on a special problem in transportation studies that concerns the so called “Big Data” challenge, which is: how to build concise yet accurate traffic flow prediction models based on the massive data collected by different sensors? The size of the data, the hidden causal dependence and the complexity of traffic time series are some of the obstacles that affect making reliable forecast at a reasonable cost, both time-wise and computation-wise. To better prepare the data for traffic modeling, we introduce a multiple-step strategy to process the raw “Big Data” into compact time series that are better suited for regression and causality analysis. First, we use the Granger causality to define and determine the potential dependence among data, and produce a much condensed set of times series who are also highly dependent. Next, we deploy a decomposition algorithm to separate daily-similar trend and nonstationary bursts components from the traffic flow time series yielded by the Granger test. The decomposition results are then treated by two rounds of Lasso regression: the standard Lasso method is first used to quickly filter out most of the irrelevant data, followed by a robust Lasso method to further remove the disturbance caused by bursts components and recover the strongest dependence among the remaining data. Test results show that the proposed method significantly reduces the costs of building prediction models. Moreover, the obtained causal dependence graph reveals the relationship between the structure of road networks and the correlations among traffic time series. All these findings are useful for building better traffic flow prediction models.

Short-term Traffic Flow Prediction Based on Multivariable Phase Space Reconstruction and LSSVM

Real-time and accurate short-term traffic flow prediction is the premise and key of intelligent traffic control and guidance system. According to this problem, this paper put forward a prediction model based on multivariable phase space reconstruction and least squares support vector machine (LSSVM). First, the model confirms embedding dimension and delay time of the traffic flow, occupancy and average speed time series by analyzing their chaotic characteristics, and reconstructs multivariable state space. Second, the phase points obtained after reconstruction are as input, and the last traffic flow parameters came from the following phase points are as output. Finally, the LSSVM which be trained is adapted to realize short-term traffic flow prediction. This research compares this model with a model based on univariate phase space reconstruction and LSSVM, and the results show that the model proposed in this paper predicts better.

Public Bicycle Traffic Flow Prediction based on a Hybrid Model

In China, Hangzhou is the first city to set up the Public Bicycle System. Now, the system has been the largest bike sharing program in the world. The software of Hangzhou Public Bicycle System was developed by our team. Accurate and precise prediction of public bicycle traffic flow is important in traffic planning, design, operation s, etc. According to the highly complexity, nonlinearity and uncertainty of traffic flow, a single prediction model is difficult to ensure th e prediction accuracy and efficiency. To overcome the lack of the single prediction method, this paper uses a hybrid model that combining clustering with support vector machine, by exploiting complementary advantages of both approaches. Firstly, this method uses improved k-means algorithm to cluster the original sample set. Secondly, the subset whose character is the most similar to the sample set to be forecasted is chosen. Finally, a polynomial smooth support vector machine uses the subset to forecast the public bicycle tr affic flow. The experimental results show that the hybrid model performs higher forecasting accuracy and better generalization ability.

Accurate Multisteps Traffic Flow Prediction Based on SVM

Accurate traffic flow prediction is prerequisite and important for realizing intelligent traffic control and guidance, and it is also the objective requirement for intelligent traffic management. Due to the strong nonlinear, stochastic, time-varying characteristics of urban transport system, artificial intelligence methods such as support vector machine (SVM) are now receiving more and more attentions in this research field. Compared with the traditional single-step prediction method, the multisteps prediction has the ability that can predict the traffic state trends over a certain period in the future. From the perspective of dynamic decision, it is far important than the current traffic condition obtained. Thus, in this paper, an accurate multi-steps traffic flow prediction model based on SVM was proposed. In which, the input vectors were comprised of actual traffic volume and four different types of input vectors were compared to verify their prediction performance with each other. Finally, the model was verified with actual data in the empirical analysis phase and the test results showed that the proposed SVM model had a good ability for traffic flow prediction and the SVM-HPT model outperformed the other three models for prediction.

Dynamical functional prediction and classification, with application to traffic flow prediction

Motivated by the need for accurate traffic flow prediction in transportation management, we propose a functional data method to analyze traffic flow patterns and predict future traffic flow. In this study we approach the problem by sampling traffic flow trajectories from a mixture of stochastic processes. The proposed functional mixture prediction approach combines functional prediction with probabilistic functional classification to take distinct traffic flow patterns into account. The probabilistic classification procedure, which incorporates functional clustering and discrimination, hinges on subspace projection. The proposed methods not only assist in predicting traffic flow trajectories, but also identify distinct patterns in daily traffic flow of typical temporal trends and variabilities. The proposed methodology is widely applicable in analysis and prediction of longitudinally recorded functional data.

Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions

Most literature on short-term traffic flow forecasting focused mainly on normal, or non-incident, conditions and, hence, limited their applicability when traffic flow forecasting is most needed, i.e., incident and atypical conditions. Accurate prediction of short-term traffic flow under atypical conditions, such as vehicular crashes, inclement weather, work zone, and holidays, is crucial to effective and proactive traffic management systems in the context of intelligent transportation systems (ITS) and, more specifically, dynamic traffic assignment (DTA). To this end, this paper presents an application of a supervised statistical learning technique called Online Support Vector machine for Regression, or OL-SVR, for the prediction of short-term freeway traffic flow under both typical and atypical conditions. The OL-SVR model is compared with three well-known prediction models including Gaussian maximum likelihood (GML), Holt exponential smoothing, and artificial neural net models. The resultant performance comparisons suggest that GML, which relies heavily on the recurring characteristics of day-to-day traffic, performs slightly better than other models under typical traffic conditions, as demonstrated by previous studies. Yet OL-SVR is the best performer under non-recurring atypical traffic conditions. It appears that for deployed ITS systems that gear toward timely response to real-world atypical and incident situations, OL-SVR may be a better tool than GML.