A model for predicting travel times by mining spatio-temporal data acquired from vehicles equipped with Global Positioning System (GPS) receivers in urban traffic networks is presented. The proposed model, which uses k-nearest neighbour (kNN) non-parametric regression, is compared with models that use historical averages and the seasonal autoregressive integrated moving average (ARIMA) model. The main contribution is provision of a methodology for mining GPS data that involves examining areas that cannot be covered with conventional fixed sensors. The work confirms that the method that predicts traffic conditions most accurately on motorways and highways (namely seasonal ARIMA) is not optimal for travel time prediction in the context of GPS data from urban travel networks. In all the examined cases, kNN approach yields a mean absolute percentage error that is twice as good as ARIMA, while in some cases it even yields a mean absolute percentage error that is an order of magnitude better. The merit of the model is demonstrated using GPS data collected by vehicles travelling through the road network of the city of Zagreb. To evaluate the performance, the models mean absolute percentage error, mean error, and root mean square error are calculated. A non-parametric ranked Friedman ANOVA to test groups of three or more models, and the Wilcoxon matched pairs test to test significance between two models are used. The alpha levels are adjusted using the Bonferroni correction. Today’s commercial fastest-route guidance systems can readily incorporate the proposed model. Since the model yields travel times that are dependent on dynamic factors, these commercial systems can be made dynamic. Furthermore, the model can also be used to generate pre-trip information that will help users to save time. KEYWORDS: travel time prediction, urban traffic, GPS data, k-nearest neighbour, seasonal ARIMA, non-parametric regression

In August 1999 an exceptional transportation of two steamers of 666 tonnes was performed from the Port of Koper to the Nuclear power plant in Krško. The transport covered a distance of about 200km and represented one of the largest exceptional transports in Slovenia ever. Finding the best route represented one of the major issues, because the steamers had to cross more than 50 problematic sections and bridges, most of which have not been designed for such heavy loads. It was necessary to load-test almost all bridges on the route to determine whether those bridges need any extra supports or not. Consequently, a logistic operator has an important and indispensable role and becomes a co-modeller of logistic service. A deformation analysis or a polynomial interpolation of vertical displacements could also be used. Therefore, a laboratory load test of a concrete plate was made. The concrete plate was loaded with hydraulic cylinder PZ 100 with extensiometer up to 21kN. Every increase of load by 3kN was measured with Nikon Ser 800 total station. KEY WORDS: deformation analysis, exceptional transport, bridges in Slovenia

The main scope of this paper is to present the formulation and visualization of shortening travel time in road transport due to the improvement of road network in Hungary. The formulation of the travel time based model has been developed by the authors. The paper also presents the demonstration of the results. The approach followed is quite innovatory in terms of visualization. The travel times were taken into account as opposed to geographical distances. Also, graph theory is used in order to calculate the matrix of “travel time” distances. The data from more than 30 cities were included in the model so as to make it quite representative for Hungary. KEYWORDS: road transportation, reduction of travel time, positive external effect

The construction of railway infrastructure should be dealt with as a national strategic development programme, which — due to technical, geographical, logistical, and other requirements — is carried out through a number of projects and represents a complex multiple project operation for investors, contractors, and other influential players. The national strategic development programme for the construction of railway infrastructure is connected — through programmes in the neighbouring countries and EU member states — to Trans-European networks (TEN) that strategically regulate the construction within the community. In the Republic of Slovenia, the construction of railway infrastructure within TEN programmes is carried out on the pan-European traffic Corridors V and X within individual projects for the construction of sections and a number of supporting projects. The technical requirements, deadlines, and other TEN requirements as well as national strategic requirements and financial possibilities of the state represent the basic criteria that should be taken into consideration in setting up a strategic project plan, with optimal project classification achieved through the implementation project portfolio. The current paper has utilised the method of multiple-criteria decision analysis to prepare the portfolio, taking into account the macroeconomic and infrastructural criteria. Consequently, the results represent the basis for the preparation of an optimal financial plan with regard to financing possibilities of the Republic of Slovenia and the European Union. The paper also summarises the research results regarding the formation of the project implementation process of the TEN-T network construction in the Republic of Slovenia. KEY WORDS: national strategic development, railway infrastructure construction, railway Corridors V and X, project portfolio, multiple-criteria decision analysis, Republic of Slovenia

The management of a container terminal is a complex process that involves many decisions. Among the problems to be solved, there are the spatial allocation of containers on the terminal yard, allocation of ships to berths and cranes, scheduling priorities and operations in order to maximize performances based on some economic indicators. Since the container port facilities are very expensive, it is desirable to optimize their performance, making better management decisions. This paper wants to present the contribution of the simulation and optimization techniques with the aim of improving the cooperation between different types of equipments, increasing the productivity of the terminal and helping in minimizing costs. In particular, the Petri net is used to present berth operations, and the genetic algorithm is used for scheduling container loading/unloading operations by cranes in order to minimize the maximum time it takes to serve a given set of vessels. KEYWORDS: transportation, berth management, scheduling, simulation, optimization

From the aspect of the Republic of Croatia, short-sea shipping has multiple significance. Primarily, the short-sea shipping between the Croatian and Italian coast, diverting of a part of cargo that is transported from the European Union into the countries of south-eastern Balkan via Croatia, reduction in harmful emissions in traffic and increase of traffic in the domestic ports. From the aspect of Europe short-sea shipping refers to the movement of goods and passengers by sea between the ports located in Europe or between these ports and the ports outside Europe that have a joint sea border with Europe. The aim of introducing short-sea shipping are: relief of the burden on the European road routes and shift of transport of cargo and passengers to the maritime transport, improvement of traffic connections and competitiveness of Croatia with the European Union, as well as the connection of the Danube and the Adriatic. KEY WORDS: short-sea shipping, Republic of Croatia, maritime routes, traffic corridors

Modern approach to transportation system research is based on the system theory. System analysis is relevant. Constant transportation technique and technology devel-opment caused by the need of conformation to the new market conditions is the basis for such an approach. The model approach for resolving the problems of public pas-senger transport is provided in a scientific report. The model of quality of passenger transport comprises the submodels which define relevant measures for the provi-sion of passenger transport quality. The synthesis of sub-model for adoption of quality standards, submodel of pas-senger demands, submodel of operation safety and securi-ty and economic submodel construct the model of quality of public passenger transport (PPT). Its evaluation has been carried out using SWOT analysis. KEY WORDS: public passenger transport, traffic, lines, network, quality, mobility

The objective of this paper is to analyse road traffic safety in the Republic of Croatia based on the selected indicators which were used by the legislator in bringing the Law on Road Traffic Safety which has been in force since 28 July 2004, and the achieved effects in reaching the desired safety level in the three-year period from 2005 to 2007. The aim of the research is to establish a prognostic trend of the values of the studied indicators in the time period following the enforcement of new legal regulations. Adequate safety indicator values for the respective period were analyzed using the methods of analysis and synthesis, mathematical statistics as well as trend assessment based on the found mathematical prognostic models. Based on the results of this research it was found that the basic hypothesis according to which the implementation of new legal guidelines had to result in positive change in the condition of road traffic safety, failed to be confirmed. A change in the road traffic safety improvement strategy has been proposed as well as a more significant participation and recognition of the profession and science in this field which is of great significance for the society. KEY WORDS: influence of legal regulations, road traffic safety, effects and tendencies