Accuracy Of Traffic Forecasting Research Articles

An adaptive composite time series forecasting model for short-term traffic flow

Short-term traffic flow forecasting is a hot issue in the field of intelligent transportation. The research field of traffic forecasting has evolved greatly in past decades. With the rapid development of deep learning and neural networks, a series of effective methods have been proposed to address the short-term traffic flow forecasting problem, which makes it possible to examine and forecast traffic situations more accurately than ever. Different from linear based methods, deep learning based methods achieve traffic flow forecasting by exploring the complex nonlinear relationships in traffic flow. Most existing methods always use a single framework for feature extraction and forecasting only. These approaches treat all traffic flow equally and consider them contain same attribute. However, the traffic flow from different time spots or roads may contain distinct attributes information (such as congested and uncongested). A simple single framework usually ignore the different attributes embedded in different distributions of data. This would decrease the accuracy of traffic forecasting. To tackle these issues, we propose an adaptive composite framework, named Long-Short-Combination (LSC). In the proposed method, two data forecasting modules(L and S) are designed for short-term traffic flow with different attributes respectively. Furthermore, we also integrate an attribute forecasting module (C) to forecast the traffic attributes for each time point in future time series. The proposed framework has been assessed on real-world datasets. The experimental results demonstrate that the proposed model has excellent forecasting performance.

Adaptive Spatiotemporal Transformer Graph Network for Traffic Flow Forecasting by IoT Loop Detectors

Extensive traffic flow data are received from the loop detector networks every second, which requires us to develop an effective and efficient algorithm to predict future traffic flow. However, dynamic traffic conditions on a road are not just influenced by sequential patterns in the temporal dimension, but also by other roadways in the spatial dimension. Although many successful models have been developed in previous studies to forecast future traffic flows, most of them have shortcomings in modeling spatial and temporal dependencies. In this article, we focus on spatial-temporal factors and propose a new adaptive spatial-temporal transformer graph network (ASTTGN) to improve the accuracy of traffic forecasting by jointly modeling the spatial-temporal information of road networks. Specifically, we propose an adaptive spatial-temporal transformer module, which contains two developed adaptive transformer modules for capturing dynamic spatial dependence and temporal dependence across multiple time steps, respectively. Finally, feature fusion is performed through a gated feature aggregation layer to simulate the effect of complex spatial-temporal factors on traffic conditions. In particular, the multihead attention mechanism employed by the transformer can effectively explore the potential spatial-temporal dependence patterns in different subspaces. Experimental results on two real-world traffic data sets demonstrate the superiority of the proposed model compared to existing techniques.

Optimal Aggregate Size of Traffic Sequence Data Based on Fuzzy Entropy and Mutual Information

Before traffic forecasting, it is usually necessary to aggregate the information by a certain length of time. An aggregation size that is too short will make the data unstable and cause the forecast result to be too biased. On the other hand, if the aggregation size is too large, the data information will be lost, resulting in the forecast results tending towards an average or slow response. With the development of intelligent transportation systems, especially the development of urban traffic control systems, high requirements are placed on the real-time accuracy of traffic forecasting. Therefore, it is an essential topic of traffic forecasting research to determine aggregation sizes. In this paper, the mutual information between the forecast input information and the forecast result and the sequence complexity of the forecast result measured by approximate entropy, sample entropy, and fuzzy entropy are considered; then, the optimal data aggregation size is given. To verify the proposed method, the validated data obtained from the simulation is aggregated and calculated with different aggregation sizes, then used for forecasting. By comparing the prediction performance of different aggregate sizes, the optimal aggregate size was found to reduce MSE by 14–30%. The results show that the method proposed in this paper is helpful for selecting the optimal data aggregation size in forecasting and can improve the performance of prediction.

Impact of a Preliminary Feasibility Study on the accuracy of traffic forecasts in the case of Korea

• This study assesses the traffic forecasting accuracy of the Korean PFS. • Project manager and forecaster traits minimally affected traffic forecasting errors. • Political influence had a minimal effect on traffic forecasting errors. • PFS enhances the accuracy of traffic forecasts. • This study examines policy to increase traffic forecasting accuracy. The financial crisis that beset the Republic of Korea in late 1997 had a tremendous impact on the nation’s economy. In an effort to resolve the fundamental causes of this crisis, one fiscal reform, executed with the goal of improving the efficacy of government investment, was the introduction of the Preliminary Feasibility Study (PFS). PFS was initiated to determine which projects to fund in a transparent and fair way through preliminarily examinations and evaluation of the feasibility of large-scale government projects. This study assesses the achievements of PFS by investigating improvements in the accuracy of traffic forecasting results and analyzing the determinants of traffic forecasting errors in PFS. The traffic forecasting data include 42 road projects for which PFS were conducted and 113 road projects that were not subject to PFS and for which forecasts and actual out-turns were available. The results reveal that 41.3% of traffic forecasts were overestimated before the introduction of PFS. This statistic contrasts with the traffic forecasting error rate of 14.53% since PFS became mandatory. Moreover, traffic forecasts of PFS projects were also unbiased. By analyzing the determinants of traffic forecasting errors in PFS projects using the random forest approach, we also found that the characteristics of the project manager and forecaster, and the influence of politicians or political groups, had minimal effect on traffic forecasting errors. We conclude that PFS enhances the accuracy of traffic forecasts and prevents the initiation of inefficient transportation projects. Our study fills a gap in the existing literature because few studies have focused on the various factors affecting traffic forecasting error based on data and econometrics. This study also examines the effects of policy measures to mitigate overestimation and increase traffic forecasting accuracy. Our results emphasize the significant role of analysts, the need for credible guidelines and an independent evaluation institution, and the importance of a robust governance system in public investment management.

The changing accuracy of traffic forecasts.

Researchers have improved travel demand forecasting methods in recent decades but invested relatively little to understand their accuracy. A major barrier has been the lack of necessary data. We compiled the largest known database of traffic forecast accuracy, composed of forecast traffic, post-opening counts and project attributes for 1291 road projects in the United States and Europe. We compared measured versus forecast traffic and identified the factors associated with accuracy. We found measured traffic is on average 6% lower than forecast volumes, with a mean absolute deviation of 17% from the forecast. Higher volume roads, higher functional classes, shorter time spans, and the use of travel models all improved accuracy. Unemployment rates also affected accuracy—traffic would be 1% greater than forecast on average, rather than 6% lower, if we adjust for higher unemployment during the post-recession years (2008 to 2014). Forecast accuracy was not consistent over time: more recent forecasts were more accurate, and the mean deviation changed direction. Traffic on projects that opened from the 1980s through early 2000s was higher on average than forecast, while traffic on more recent projects was lower on average than forecast. This research provides insight into the degree of confidence that planners and policy makers can expect from traffic forecasts and suggests that we should view forecasts as a range of possible outcomes rather than a single expected outcome.Supplementary InformationThe online version contains supplementary material available at 10.1007/s11116-021-10182-8.

A Model for Traffic Management based on Text Mining Techniques

It is very important for traffic management to be able to correctly recognize traffic trends from large historical traffic data, particularly the congestion pattern and road collisions. This can be used to reduce congestion, improve protection, and increase the accuracy of traffic forecasting. Choosing the correct and effective text mining methodology helps speed up and reduces the time and effort needed to retrieve valuable knowledge and information for future prediction and decision-making processes. Modeling collisions or accident risk has also been an important aspect of traffic management and road safety, as it helps recognize problems and causes that contribute to a higher risk of accidents, promotes treatment delivery, and reduces crashes to save more lives and avoid road congestion. Therefore, this work-study proposed a model that relies on the different text mining methodology to determine clearly what circumstances affect and who is involved more in an accident. Using different classification and machine learning techniques applied to get the optimum classifiers used in this model. The experimental results on real-world datasets demonstrate that the proposed models outperform Prayag Tiwari’s Research Work related to the Leeds UK Dataset.

INFLUENCE OF A CARRIAGEWAY WIDTH ON THE CAR SPEED UNDER URBAN CONDITIONS

Problem. The car speed is the most important indicator of the traffic organization level. A priori it is obvious that the value of the car speed in a particular place and at a particular time is random. The randomness of speed is due to the influence on it of too many factors that cannot be taken into account analytically - from the driving style of each driver, which in itself is made up of individual actions, which are difficult to predict, to a large number and individual behavior of other road users. Establishing a car speed distribution in various conditions is an urgent task, whose solution is the basis for improving the accuracy of traffic forecasts that are formed using analytical or simulation models of transport networks and their elements. Goal. The goal is obtaining patterns of changes in the car speed in limited road conditions, with the narrow carriageway. Methodology. The methods include development of a valid hypothesis regarding the type of distribution of the car speed in limited road conditions and its experimental verification using the example of an urban street with parked cars. Results. The hypothesis about the possibility of using gamma distribution to describe the car speed in any driving conditions, i.e. for any average car speed, was not denied by experimental observations of the movement of vehicles on a narrow section of the urban street 5.45 m wide for two directions. Originality. New hypothesis was promoted and tested about the kind of car speed distribution, not in free, but in limited road conditions. Practical value. The obtained result is the basis for improving the accuracy of traffic forecasts that are formed using analytical or simulation models of transport networks and their elements in transport consulting.

Comparative Study of Aggregate and Disaggregate Traffic Forecasting Technique for Industrial Corridor: Case Study of Vadodara District

Abstract Transportation occupies a prominent place in modern life and its impact is spread in all domains of life. Transport planning is a discipline to study problems rising while planning transport facilities at urban, regional or national level and to prepare efficient basis for providing such facilities. Aim of transport planning at regional level is provision of connectivity and circuity with other regions as well as for expansion of existing facility for future needs. The key success for transportation planning is the accurate forecasting of vehicular movement. The accuracy of traffic forecasting is a point of substantial importance to the effective sharing of rationed resources. With this purpose, study was conducted to develop traffic flow prediction model by aggregate approach and disaggregate approach for industrial corridor (i.e., state highway 158) passing through Savali taluka in Vadodara, India. To accomplish this goal, traffic volume of past 10 years collected in two terms, pre-monsoon and port-monsoon from state Public Work Department. For aggregate approach, economic parameters such as investment and employment generated in the region while in disaggregate approach time series analysis using auto regressive technique were utilized for traffic prediction. The relation developed between existing traffic and investment as well as with employment was found to be linear. Precision of model was gauged, based on mean absolute percentage error (MAPE) rather only considering the coefficient of determination. Finally, the study highlights the effects of economic development on transport infrastructure and its future need in the region. The results and approaches adopted here can be useful for planners in implementation and development of a transportation system. Keywords: Traffic Flow Predictions, Econometric Models, Regional Transport Planning, Transport Infrastructure Cite this Article Rohit Galani, Devang P. Majithiya. Comparative Study of Aggregate and Disaggregate Traffic Forecasting Technique for Industrial Corridor- case study of Vadodara District. Trends in Transport Engineering and Applications . 2018; 5(1): 14–21p.

Transport safety and traffic forecasting: An economist's perspective

This paper is concerned with forecasting traffic accidents at a relatively aggregate level and over a long time period; the sort of information that is required as part of a comprehensive cost-benefit analysis of a major transportation investment or policy change. It is not so focused on appraising the social value of specific safety measures, although some of the points made seem germane. Whereas there has been much ex ante analysis at the meso- and macro-levels looking at the causes of accidents and ways of reducing both their number and severity, much less ex post has been done considering the accuracy of predictions of accident rates after an investment or policy initiative. Given the evidence that exists on the accuracy of traffic forecasts, especially involving oft over-optimistic predictions of public transit and rail use, there is at least a prima facie case for arguing that many investment and policy decisions are being based, in part, on over favorable assumptions with regard to their aggregate safety impacts.

Accuracy of Traffic Forecasts and Cost Estimates on Large Transportation Projects

Little research has been carried out on before-and-after studies of traffic and construction costs in large transportation infrastructure projects. The few studies that do exist show that forecasts of construction costs tend to be underestimated and those of traffic, overestimated. An examination of construction costs and traffic in seven large Danish bridge and tunnel projects indicates that, on average, construction costs were underestimated and traffic was overestimated in the initial phases of planning. This pattern is also found for similar projects in other countries. When the results of all the projects are pooled, it is seen that cost overruns of 50 to 100 percent are common and that overruns above 100 percent are not uncommon. Traffic forecasts that are off by 20 to 60 percent when compared with actual development are frequent in large transportation infrastructure projects. The result of this overoptimism in the initial planning phases is that decisions are based on misleading forecasts that may...

Accuracy of Traffic Forecasts and Cost Estimates on Large Transportation Projects

Little research has been carried out on before-and-after studies of traffic and construction costs in large transportation infrastructure projects. The few studies that do exist show that forecasts of construction costs tend to be underestimated and those of traffic, overestimated. An examination of construction costs and traffic in seven large Danish bridge and tunnel projects indicates that, on average, construction costs were underestimated and traffic was overestimated in the initial phases of planning. This pattern is also found for similar projects in other countries. When the results of all the projects are pooled, it is seen that cost overruns of 50 to 100 percent are common and that overruns above 100 percent are not uncommon. Traffic forecasts that are off by 20 to 60 percent when compared with actual development are frequent in large transportation infrastructure projects. The result of this overoptimism in the initial planning phases is that decisions are based on misleading forecasts that may lead to a misallocation of funds and underperforming projects.