The paper presents a system that recognizes the make, colour and type of the vehicle. The classification has been performed using low quality data from real-traffic measurement devices. For detecting vehicles’ specific features three methods have been developed. They employ several image and signal recognition techniques, e.g. Mamdani Fuzzy Inference System for colour recognition or Scale Invariant Features Transform for make identification. The obtained results are very promising, especially because only on-site equipment, not dedicated for such application, has been employed. In case of car type, the proposed system has better performance than commonly used inductive loops. Extensive information about the vehicle can be used in many fields of Intelligent Transport Systems, especially for traffic supervision.

More than 16,500 people lose their lives each year due to traffic crashes in Iran, which reflects one of the highest road traffic fatality rates in the world. The aim of the present study is to investigate the factors structure of an extended Driver Behaviour Questionnaire (DBQ) and to examine the gender differences in the extracted factors among Iranian drivers. Further, the study tested the association between DBQ factors, demographic characteristics, and self-reported crashes. Based on Iranian driving culture, an extended (36 items) Internet-based version of the DBQ was distributed among Iranian drivers. The results of Exploratory Factor Analysis based on a sample of 632 Iranians identified a five-factor solution named “Speeding and Pushing Violations”, “Lapses and Errors”, “Violations Causing Inattention”, “Aggressive Violations” and “Traffic Violations” which account for 44.7 percent of the total variance. The results also revealed that females were more prone to Lapses and Errors, whereas males reported more violations than females. Logistic regression analysis identified Violations Causing Inattention, Speeding and Pushing Violations as predictors of self-reported crashes in a three-year period. The results were discussed in line with road traffic safety countermeasures suitable for the Iranian context.

With the aging of population in the world, understanding the travel demands of the elderly is important. In China, the aging society is in the process of forming. Meanwhile the urban motorization has just started. The aim of this paper is to investigate the dependence of the future elderly on private cars. The data used here come from a stated preference (SP) survey of the young and middle-aged residents in the capital of China, Beijing. The influencing factors on the car ownership and mode choices of the future elderly are analysed based on the ordered logit model and MNL model, respectively. The effect of uncertainty in respondents’ statements on the car usage has been also investigated. The results show that the future elderly in Beijing become increasingly dependent on private cars. It is also found that younger people have higher propensities to own private cars and to make use of driving after the age of 65. Moreover, improving public transport services contributes to an increased ridership of public transport by the future elderly. The findings in this paper can provide valuable references for the aging society when making transport policies in Beijing.

The paper integrates Rough Sets (RS) and Bayesian Networks (BN) for roadway traffic accident analysis. RS reduction of attributes is first employed to generate the key set of attributes affecting accident outcomes, which are then fed into a BN structure as nodes for BN construction and accident outcome classification. Such RS-based BN framework combines the advantages of RS in knowledge reduction capability and BN in describing interrelationships among different attributes. The framework is demonstrated using the 100-car naturalistic driving data from Virginia Tech Transportation Institute to predict accident type. Comparative evaluation with the baseline BNs shows the RS-based BNs generally have a higher prediction accuracy and lower network complexity while with comparable prediction coverage and receiver operating characteristic curve area, proving that the proposed RS-based BN overall outperforms the BNs with/without traditional feature selection approaches. The proposed RS-based BN indicates the most significant attributes that affect accident types include pre-crash manoeuvre, driver’s attention from forward roadway to centre mirror, number of secondary tasks undertaken, traffic density, and relation to junction, most of which feature pre-crash driver states and driver behaviours that have not been extensively researched in literature, and could give further insight into the nature of traffic accidents.

Level of service (LOS) is used as the main indicator of transport quality on urban roads and it is estimated based on the travel speed. The main objective of this study is to determine which of the existing models for travel speed calculation is most suitable for local conditions. The study uses actual data gathered in travel time survey on urban streets, recorded by applying second by second GPS data. The survey is limited to traffic flow in saturated conditions. The RMSE method (Root Mean Square Error) is used for research results comparison with relevant models: Akcelik, HCM (Highway Capacity Manual), Singapore model and modified BPR (the Bureau of Public Roads) function (Dowling - Skabardonis). The lowest deviation in local conditions for urban streets with standardized intersection distance (400-500 m) is demonstrated by Akcelik model. However, for streets with lower signal density (<1 signal/km) the correlation between speed and degree of saturation is best presented by HCM and Singapore model. According to test results, Akcelik model was adopted for travel speed estimation which can be the basis for determining the level of service in urban streets with standardized intersection distance and coordinated signal timing under local conditions.

This paper brings a proposal for a timetable optimization model for minimizing the passenger travel time and congestion for a single metro line under time-dependent demand. The model is an integer-programming model that systemically considers the passenger travel time, the capacity of trains, and the capacity of platforms. A multi-objective function and a recursive optimization method are presented to solve the optimization problem. Using the model we can obtain an efficient timetable with minimal passenger travel time and minimal number of congestion events on platforms. Moreover, by increasing the number of dispatches, the critical point from congestion state to free-flow state and the optimal timetable with minimal cost for avoiding congestion on platforms can be obtained. The effectiveness of the model is evaluated by a real example. A half-regular timetable with fixed headways in each operation period and an irregular timetable with unfixed headway are investigated for comparison.

Emerging info-communication and vehicle technologies (especially vehicle automation) facilitate evolvement of autonomous road freight transportation. The entire transport system and its operation undergo a major change. New service concepts are growing and the existing ones are being transformed. The changing is particularly significant in city logistics. However, there are debates about the ways of automation of processes targeting improvement of capacity utilisation and decrease of expenditures. The main research questions of the paper are therefore: what properties of the future autonomous freight transportation are presumed; what system structure is to be constructed and how the system is to be operated? After introducing the basic notions and reviews of the current systems and developments, the shifting from traditional freight transportation to autonomous system is investigated by several aspects. A system- and process-oriented analytical modelling method has been applied. The main system constituents and their connections are modelled. Finally, we elaborate the operational model of road freight transportation, which is applicable principally in metropolitan areas. In conclusion, the presented
results appoint the research and innovation trends towards the automation of freight transportation.

High-occupancy vehicle (HOV) lanes, which are designed so as to encourage more people to use high-capacity travel modes and thus move more people in a single roadway lane, have been implemented as a lane management measure to deal with the growing traffic congestion in practice. However, the implementation has shown that some HOV lanes are not able to achieve the expected effects without proper HOV lane settings. In this study, the tradable credits scheme (TCS) is introduced to improve the HOV lane management and an optimal capacity of HOV lanes in a multilane highway is investigated to match TCSs. To approach the investigation, a bilevel programming model is proposed. The upper-level represents the decision of the highway authority and the lower-level follows the commuters’ user equilibrium with deterministic demand. The potential influence of TCSs is further investigated within the proposed framework. A modified genetic algorithm is proposed to solve the bilevel programming model. Numerical examples demonstrate that combining TCSs with the HOV lane management can obviously mitigate traffic congestion.

The choice of a particular mode of transport as an alternative to another one is subjective and usually based on an individual passenger’s approach to the evaluation of advantages and disadvantages of some particular means of transport. The paper presents the methods of analysing the reasons for passengers’ choice of travelling by train as an alternative to using air transport and the results obtained in the research. The 16 criteria (sub-criteria), describing the advantages of travelling by rail over air travel, are defined. The data of the survey questionnaire filled by 52 passengers of the Vilnius–Moscow train and the ranks assigned by them to the considered criteria are described. The average ranks of all 16 criteria and their normalized subjective weights are calculated by using a new method of average rank transformation into weight (ARTIW). The average ranks assigned by the passengers of the train to sub-criteria and the calculated global weights show what criteria are most important. Using the inverse hierarchy model based on the sub-criteria weights, the most and the least important groups of criteria are determined. The institutions and companies engaged in passenger transportation by rail, which give priority to improving the services described by the most important criteria, can make this mode of transport more attractive to people.

Several factors affect the lane choices made by motorway drivers. According to the driving rules, the nearside lane is the one that is primarily used. The main reasons for lane changes are overtaking, congestion, or restrictions on other lanes. The empirical research presented in this paper presents comprehensive traffic characteristics observed in different traffic lanes on four-lane motorways in Slovenia. The research was focused on the influence of adverse weather conditions on the lane flow distribution, and on the speed of vehicles in different lanes. The lane flow and speed distributions both directly affect road capacity and safety; therefore, estimating these characteristics could improve the reliability of active traffic control when traffic flow perturbation is detected. Field test results show that lane flow distributions and lane speed distributions at a particular site vary depending on weather conditions, namely, dry, wet (rain), low-visibility, and snow conditions.

The delivery of the right product, at the right time to the retail store, only seems to be an easy process. The smallest problem can cause the out-of-stock (OOS) situation, which may prevent customers to buy products they were looking for. Consequently, it affects retailers and their suppliers through potential operational inefficiencies, sale losses and eventually the losses of their loyal customers. Starting from these problems, by using the data of a large Serbian retailer, this paper analyses out-of-stocks in the context of two alternative delivery systems, centralized and direct. For calculating OOS rates the perpetual inventory aggregation metrics was used, while the occurrence of out-of-stocks was modelled by the application of probit regression analysis. The results have shown that delivery system has a significant impact on the probability of a stock-out, indicating potential problems in the centralized system. In addition, the analysis included certain product and store characteristics that also significantly affect the average probability of stock-outs.

The transport policy of the European Union is based on the mission of restructuring road traffic into other and energy-favourable transport modes which have not been sufficiently represented yet. Therefore, the development of the inland waterway and rail transport, and connectivity in the intermodal transport network are development planning priorities of the European transport strategy. The aim of this research study was to apply the scientific methodology and thus analyse the factors that affect the distribution of the goods flows and by using the fuzzy logic to make an optimization model, according to the criteria of minimizing the costs and negative impact on the environment, for the selection of the optimal transport route. Testing of the model by simulation, was performed on the basis of evaluating the criteria of the influential parameters with unprecise and indefinite input parameters. The testing results show that by the distribution of the goods flow from road transport network to inland waterways or rail transport, can be predicted in advance and determine the transport route with optimal characteristics. The results of the performed research study will be used to improve the process of planning the transport service, with the aim of reducing the transport costs and environmental pollution.