Traffic Volume Prediction Research Articles

Short-Term Traffic Volume Prediction for Sustainable Transportation in an Urban Area

AbstractAccurate short-term traffic volume prediction is essential for the realization of sustainable transportation as providing traffic information is widely known as an effective way to alleviate congestion. In practice, short-term traffic predictions require a relatively low computation cost to perform calculations in a timely manner and should be tolerant to noise. Traffic measurements of variable quality also arise from sensor failures and missing data. There is no optimal prediction model so far fulfilling these challenges. This paper proposes a so-called absorbing Markov chain (AMC) model that utilizes historical traffic database in a single time series to carry out predictions. This model can predict the short-term traffic volume of road links and determine the rate in which traffic eases once congestion has occurred. This paper uses two sets of measured traffic volume data collected from the city of Enschede, Netherlands, for the training and testing of the model, respectively. The main advantag...

Annual Average Daily Traffic Estimation using Co-kriging

Annual average daily traffic (AADT) serves the important basic data in transportation sector. Despite of its importance, AADT is estimated through permanent traffic counts (PTC) at limited locations because of constraints in budget and so on. At most of locations, AADT is estimated using short-term traffic counts (STC). Though many studies have been carried out at home and abroad in an effort to enhance the accuracy of AADT estimate, the method to simplify average STC data has been adopted because of application difficulty. A typical model for estimating AADT is an adjustment factor application model which applies the monthly or weekly adjustment factors at PTC points (or group) with similar traffic pattern. But this model has the limit in determining the PTC points (or group) with similar traffic pattern with STC. Because STC represents usually 24-hour or 48-hour data, it`s difficult to forecast a 365-day traffic variation. In order to improve the accuracy of traffic volume prediction, this study used the geostatistical approach called co-kriging and according to their reports. To compare results, using 3 methods : using adjustment factor in same section(method 1), using grouping method to apply adjustment factor(method 2), cokriging model using previous year`s traffic data which is in a high spatial correlation with traffic volume data as a secondary variable. This study deals with estimating AADT considering time and space so AADT estimation is more reliable comparing other research.

交叉口流量分析技术在路段交通量预测中的应用研究

文章在国省道干线公路大规模升级改造的时代背景下，基于观测站的统计数据结合相邻交叉口的流量观测，提出了路段交通量的反推方法，并对其在交通量预测和公路改建项目技术标准论证上的适应性进行了分析。最后，文章以G105阜阳四十铺至南照段一级公路改建工程为例，详细介绍了该方法在工程实践中的应用情况，并对其具体应用中应注意的问题进行了总结和说明。 This article proposed a method to calculate the traffic volume of some given highway segment based on the statistic data from fixed observation point and observation data of some adjacent intersection. Then the applicability of this method was verified in traffic volume prediction and technical standard demonstration. At last, the reconstruction project of some special section of G105 was taken as an example to illustrate how this method was used in practice.

Sensitivity Analysis of Wavelet Neural Network Model for Short-Term Traffic Volume Prediction

In order to achieve a more accurate and robust traffic volume prediction model, the sensitivity of wavelet neural network model (WNNM) is analyzed in this study. Based on real loop detector data which is provided by traffic police detachment of Maanshan, WNNM is discussed with different numbers of input neurons, different number of hidden neurons, and traffic volume for different time intervals. The test results show that the performance of WNNM depends heavily on network parameters and time interval of traffic volume. In addition, the WNNM with 4 input neurons and 6 hidden neurons is the optimal predictor with more accuracy, stability, and adaptability. At the same time, a much better prediction record will be achieved with the time interval of traffic volume are 15 minutes. In addition, the optimized WNNM is compared with the widely used back-propagation neural network (BPNN). The comparison results indicated that WNNM produce much lower values of MAE, MAPE, and VAPE than BPNN, which proves that WNNM performs better on short-term traffic volume prediction.

Short-Term Forecasting of Traffic Volume

Although several methods for short-term forecasting of traffic volume have recently been developed, the literature lacks studies that focus on how to choose the appropriate prediction method on the basis of the statistical characteristics of the data set. This study first diagnosed the predictability of four traffic volume data sets on the basis of various statistical measures, including (a) complexity analysis methods, such as the delay time and embedding dimension method and the approximate entropy method; (b) nonlinearity analysis methods, such as the time reversibility of surrogate data; and (c) long-range dependency analysis techniques, such as the Hurst exponent. After the data sets were diagnosed, three models for short-term prediction of traffic volume were applied: (a) seasonal autoregressive integrated moving average (SARIMA), (b) k nearest neighbor (k-NN), and (c) support vector regression (SVR). The results from the statistical data diagnosis methods were then correlated to the performance results of the three prediction methods on the four data sets to determine the means for choosing the appropriate prediction method. The results revealed that SVR was more suitable for nonlinear data sets, while SARIMA and k-NN were more appropriate for linear data sets. The data diagnosis results were also used to devise a selection process for the parameters of the prediction models, such as the length of the training data set for SARIMA and SVR, the average number of nearest neighbors for k-NN, and the input vector length for k-NN and SVR.

Linear Spatial Interpolation and Analysis of Annual Average Daily Traffic Data

Transportation planning requires the use of accurate traffic data to produce estimates of traffic volume predictions over time and space. The annual average daily traffic (AADT) data is an important component of transportation design, operation, policy analysis, and planning. The use of traffic volume forecasting models for the characterization, analysis, and estimation of transportation data has proven to be a useful method for reducing high costs, overcoming spatial constraints, and limiting the errors associated with data collection and analysis in transportation planning. The geostatistical kriging technique is a viable method for modeling and forecasting AADT. The degree to which the technique of kriging can be useful in forecasting AADT depends highly on an understanding of the decision-making variables, the relationship between the variables, and the practical limitations of the various kriging techniques and variogram models. This paper applied three different linear kriging techniques [simple kriging (SK), ordinary kriging (OK), and universal kriging (UK)] and five variogram models (nugget effect, spherical, exponential, Gaussian, and power) to characterize and interpolate the annual average daily traffic of Washington State. The statistical errors (i.e., mean error, root-mean-square error, average standard error, mean standardized error, and root-mean-square standardized error) of the resulting output were then compared to determine the most suitable combination of linear spatial interpolation and variogram algorithms for each of the data sets. Ordinary and/or universal kriging combined with the exponential variogram were the most appropriate methods for the 2008 AADT data set, whereas ordinary kriging combined with the spherical variogram and simple kriging combined with the spherical variogram were the most suitable methods for the 2009 and 2010 data sets, respectively. Results from this study suggest that using the same combination of kriging and variogram algorithms to characterize and interpolate different AADT data sets (2008, 2009, and 2010) could lead to suboptimal results. One reason for the lack of optimal results is for instance, the directional variation in the 2009 and 2010 data sets which undermine the assumption of mean stationarity in the use of ordinary kriging for modeling.

Paratactic Spatial-Temporal Two Dimension Data Fusion Based on Support Vector Machines for Traffic Flow Prediction of Abnormal State

This paper presents a paratactic spatial-temporal 2dimension data fusion model based on support vector machines (SVM) for traffic volume prediction of the abnormal state. Time and space SVM operates respectively in two parallel operating system models to reduce the time cost. By comparing the prediction results with which obtained by the multiple regression prediction method, the prediction accuracy is greatly improved by utilizing the paratactic spatial-temporal dimension data fusion model. Especially in the abnormal state caused by unexpected events (such as: traffic accidents, traffic jam etc), the proposed method can also significantly avoid structural system error of one-dimensional time source data fusion.

Prediction of Traffic Volume in Bridge Load Random Process Based on Grey Markov Chain

AbstractIn order to overcome the deficiencies of the grey prediction method, based on grey model prediction, an improved grey Markov chain model for prediction of the traffic volume in bridge random load process was proposed. The grey prediction curve of the model reflects the historical development trend of the traffic volume, and Markov prediction reflects the impact of random fluctuation on traffic volume. So this method takes into account the trend and fluctuation factors to predict the outcome, it can overcome the limitation of the traffic volume prediction by a single prediction model. Combined with the actual situation, the traffic volume can be predicted accurately and comprehensively. Based on the existing traffic volume statistics, the accuracy of the model was tested, and the traffic volume of 2007 was predicted by the model. Examples of calculation and analysis show that the model is of high precision and the predicted outcome meets the actual status basically. It is effective to predict traff...

Dynamic near-term traffic flow prediction: system-oriented approach based on past experiences

Short-term prediction is one of the essential elements of intelligent transportation systems (ITS). Although fine prediction methodologies have been reported, most prediction methods with current time-series data lead to inefficient predictions when current or future time-series data either exhibit fluctuations or abruptly change. In order to deal with this problem, a dynamic multi-interval traffic volume prediction model, based on the k-nearest neighbour non-parametric regression (KNN-NPR), is introduced in this study. In an empirical study with real-world data, the input parameters of the proposed model including the k-values for the nearest neighbours in the neighbourhood and the dm-values for the number of lags were optimised according to the multi-interval prediction horizon in order to immediately capture the directionality of the future states and to minimise the prediction errors. The presented model performed effectively in terms of prediction accuracy, despite multi-interval schemes, to the same degree as applications of the real ITS, even if the time-series data abruptly varied or exhibited wide fluctuations. It can clearly be seen that the proposed methodology is one of the promising system-oriented approaches in the area of multi-interval traffic flow forecasting.

Modeling Traffic Volume Based on Highway Toll Database Using GM (1,1)

To circumvent the poor prediction accuracy of traffic volume models available due to the lack of traffic data and inaccurate judgments on the traffic influence factors, in this paper we established a traffic volume prediction model using grey forecasting model GM(1,1) based on the real traffic data from the highway toll database. The GM(1,1) method has advantage of the strong adaptiveness to Complex system, thus getting a great advantage over other methods for modeling such a complex nonlinear traffic volume system with many uncertain influence factors. Simulation results show that our GM(1,1) model has mean relative prediction error of 3.9%, which accomplishes our intended prediction accuracy.

MBFP generalized association rule mining and classification in traffic volume prediction

AbstractGenetic network programming (GNP)‐based time‐related association rules mining method provides a useful mean to investigate future traffic volume of road networks and hence helps us to develop traffic navigation system. Further improvements have been proposed in this paper about the time‐related association rule mining using generalized GNP with multibranches and full‐paths (MBFP) algorithm. For fully utilizing the potential ability of GNP structure, the mechanism of generalized GNP with MBFP is studied. The aim of this algorithm is to better handle association rule extraction from the databases with high efficiency in a variety of time‐related applications, especially in the traffic volume prediction problems. The generalized algorithm which can find the important time‐related association rules is described, and experimental results are presented considering a traffic prediction problem. © 2011 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

전자상거래 시스템의 트래픽량 예측에 관한 연구

네트워크 기반의 적절한 컴퓨팅은 네트워크 대역폭의 가용성에 의존한다. 백본 네트워크 용량과 액세스 네트워크 상에 심각한 버틀넥이 발생하여 ISP 사업자와 고객 간의 갭이 발생된다면 그만큼 ISP 사업자는 사업에 불이익을 초래할 수 있다. 이러한 상황이 발생되기 이전 ISP 사업자가 트래픽량 예측과 종단간 오버로드가 높은 링크 구간을 감지할 수 있다면 ISP 사업자와 고객 간의 갭은 그만큼 줄어 들 수 있을 것으로 판단된다. 따라서 본 논문은 트래픽량 예측과 종단간 오버로드가 높은 링크 구간을 감지 가능한 소프트웨어로 ACE, ADM, Flow Analysis를 소개한다. 이들 툴을 이용하여 전자상거래의 연속적인 트랜잭션을 실망에서 측정한 후 측정된 네트워크 데이터를 가상 망 환경에 임포트하고 백그라운드 트래픽을 생성한다. 이와 같은 가상 망 환경을 토대로 점차적인 사용자 수 증가에 따른 트래픽량 예측과 링크 로드가 높은 구간을 시뮬레이션 결과로 알 수 있었다. The applicability of network-based computing depends on the availability of the underlying network bandwidth. Such a growing gap between the capacity of the backbone network and the end users' needs results in a serious bottleneck of the access network in between. As a result, ISP incurs disadvantages in their business. If this situation is known to ISP in advance, or if ISP is able to predict traffic volume end-to-end link high-load zone, ISP and end users would be able to decrease the gap for ISP service quality. In this paper, simulation tools, such as ACE, ADM, and Flow Analysis, were used to be able to perceive traffic volume prediction and end-to-end link high-load zone. In using these simulation tools, we were able to estimate sequential transaction in real-network for e-Commerce. We also imported virtual network environment estimated network data, and create background traffic. In a virtual network environment like this, we were able to find out simulation results for traffic volume prediction and end-to-end link high-load zone according to the increase in the number of users based on virtual network environment.

Random Process Model for Urban Traffic Flow Using a Wavelet-Bayesian Hierarchical Technique

The existing well-known short-term traffic forecasting algorithms require large traffic flow data sets, including information on current traffic scenarios to pre- dict the future traffic conditions. This article proposes a random process traffic volume model that enables esti- mation and prediction of traffic volume at sites where such large and continuous data sets of traffic condi- tion related information are unavailable. The proposed model is based on a combination of wavelet analysis (WA) and Bayesian hierarchical methodology (BHM). The average daily trend of urban traffic flow obser- vations can be reliably modeled using discrete WA. The remaining fluctuating parts of the traffic volume observa- tions are modeled using BHM. This BHM modeling con- siders that the variance of the urban traffic flow observa- tions from an intersection vary with the time-of-the-day. A case study has been performed at two busy junctions at the city-centre of Dublin to validate the effectiveness of the strategy.

A Hybrid Model of Neural Network and Grey Theory for Air Traffic Passenger Volume Forecasting

Chinese air traffic passenger volumes have experienced phenomenal growth during the past years. The air traffic volume prediction plays a key role in air traffic flow management system. This paper develops a hybrid model of Neural and Grey Theory for air traffic passenger volume forecasting. The Grey theory is adopted to fit the air traffic data patterns and make the data a higher regularity, and Radical basis function is combined to raise the forecasting accuracy. The model is tested with the Chinese civil aviation passenger volume data from 1998 to 2007 and the result shows that the model is feasible for practical implementations.

Nonparametric Method to Examine Changes in Traffic Volume Pattern during Holiday Periods

Rising standards of living and the trend toward shorter working weeks have led to significant changes in traffic volume during holiday periods. The challenge of holiday traffic has been reported worldwide in the literature. A comprehensive understanding of the changes in traffic volume pattern associated with holiday events is critical to many transportation engineering aspects such as traffic control; signal timing; road safety; and traffic volume monitoring, imputation, and prediction. However, existing research focusing on holiday traffic has been very limited to date, and the efforts made have generally been limited to a particular holiday period or a specific recreational area. A nonparametric hypothesis test method was used to examine the changes in traffic volume patterns caused by holidays. The data used in this study were traffic volumes collected from Canadian highway networks over the past 20 years. To illustrate the application and effectiveness of the proposed method, in-depth investigations were carried out with respect to the variation of both weekly and daily volumes during 12 Canadian holiday periods. The test results showed that, for various types of roads, this method is effective and easy to understand. Moreover, the outputs were informative and reasonable. This method also may be a useful tool to examine the variation characteristics of traffic during other special time periods.

RAILWAY PASSENGER TRAFFIC VOLUME PREDICTION BASED ON NEURAL NETWORK

In order to overcome the shortcomings of the methods in railway passenger traffic volume prediction, an improved BP neural network method is adopted to predict railway passenger traffic volume. By analyzing the improved BP neural network theory, the neural network prediction model of railway passenger traffic volume is set up. The network learning and training simulation experiment is carried out on the data of railway passenger traffic volume from 1980–1998. Comparing with standard BP neural network, the improved BP neural network presents more accurate and reliable prediction results and faster learning speed. The improved BP neural network provides a new and feasible thought to predict railway passenger traffic volume, which can also be used to predict other relative problems.

Forecasting of Short-Term Freeway Volume with v-Support Vector Machines

Predictions for short-term traffic volume provide important inputs for traveler information and traffic management. Traffic volumes in the near future are often estimated based on historical volumes. Because of the complicated nonlinear relationship between historical and future traffic volume data, many previous studies used neural networks to predict short-term traffic volumes. In this research, a v-support vector machine (v-SVM) model, which has the particular strength of overcoming local minima and overfitting common to neural network models, is proposed for short-term traffic volume prediction. The v-SVM model is compared with a widely used multilayer feed-forward neural network (MLFNN) model using four data sets collected from three interstate freeways. Testing results show that for both one-step and two-step forecasting, the v-SVM model outperforms the MLFNN model for all data sets in terms of mean absolute percentage error and root-mean-square error. Key issues in applying both models are also discussed in this article.

Research on the Method Used in Predicting the Traffic Volume of Non-Detector Single-Signal Controlled Intersections

Based on the relative relationships between the traffic volumes at intersections, we study the traffic volume of non-detector single signal controlled intersections prediction and the results are examined by the traffic volume data of the road network of Nanjing city. The problem of the lanes' traffic volume prediction of non-detector single signal controlled intersections is resolved by this achievement. Some theoretical basis for macroscopic management is also provided by these methods. For the covering abstract see ITRD E129315.

Classification and prediction of road traffic using application-specific fuzzy clustering

In the field of road traffic management, fuzzy techniques have already been used for traffic control. In this paper, we use fuzzy methods for traffic data analysis. The results of the data analysis are classification and prediction systems. Our work is focused on fuzzy clustering methods. The known clustering models are extended to: constrained prototypes, the use of a mix of different prototypes for one data set, partial supervision of the clustering, and the estimation of the number of clusters by cluster merging. Two successful application examples are given. The first one is the classification of traffic jam on a German autobahn, and the second application is a long-term prediction of traffic volume.

Traffic Volume Time‐Series Analysis According to the Type of Road Use

Problems related to highway traffic operation and congestion management can be alleviated with the use of modern intelligent transportation systems (ITSs). Advanced Traveler Information Systems (ATIS) is one of the emerging technologies that will help travelers plan routes and schedules of their trips so as to redistribute the traffic over the highway network. Such redistribution will try to maximize the use of available highway capacity. Collections of real‐time data and short‐term predictions of traffic volumes are among the critical needs of an ATIS. This article studies characteristics of different traffic volume time series. In particular, time‐series analysis is applied to the prediction of daily traffic volumes. The daily traffic volume is estimated by using the previous 13 daily traffic volumes. The study involves a comparison of statistical and neural network techniques for time series analysis. The analysis is applied to different types of road groups according to the trip purpose and trip length distribution. It is hoped that this study will provide a better understanding of various issues involved in the short‐term prediction of traffic volumes on different types of highways.