The purpose of this study is to develop a model for traffic volume forecasting of the road network in Anamorava Region. The description of the current traffic volumes is enabled using PTV Visum software, which is used as an input data gained through manual and automatic counting of vehicles and interviewing traffic participants. In order to develop the forecasting model, there has been the necessity to establish a data set relying on time series which enables interface between demographic, socio-economic variables and traffic volumes. At the beginning models have been developed by MLR and ANN methods using original data on variables. In order to eliminate high correlation between variables appeared by individual models, PCA method, which transforms variables to principal components (PCs), has been employed. These PCs are used as input in order to develop combined models PCA-MLR and PCA-RBF in which the minimization of errors in traffic volumes forecasting is significantly confirmed. The obtained results are compared to performance indicators such R2, MAE, MSE and MAPE and the outcome of this undertaking is that the model PCA-RBF provides minor errors in forecasting.

The main objective of this research is to develop a model and to calibrate it in order to apply it to transport forecasting for Anamorava region. The synthetic model has been developed, and it is composed of a transport network model and a demand model, which is enabled using PTV Visum software as well as using the following variables as input: number of residents, number of people employed, working places available as well as the volume of vehicles entering and leaving certain locations surrounding the Anamorava region at "peak hour". Required coefficients are used for converting the traffic volumes from 12 hours to 24 hours expressed, such as AADT. As a criterion, for initial verification R 2 , RMSPE, Percentage Deviation and Regression parameters are used. Then, a calibration of the demand model is conducted using the TFlowFuzzy algorithm by employed GEH test, comparing it with the observed data of traffic volumes accomplished simultaneously at some locations inside and in the vicinity of this region for time intervals of 12 hours on two different days in one week in May 2016. In order to fulfil all the criterions, it has been found out that the final model may be used for transport demand forecasting in the future in this region.

This paper presents the basics of autonomous vehicle as well as technologies that enable a vehicle to be self-driving. Taking into the consideration the fact the major causes of traffic accidents are by human errors, with the application of intelligent vehicle systems would be a great help to go to the "zero vision" of life losses in traffic accidents. According to traffic accident statistics, 75% or more of fatal accidents have been caused by human factors such as: lack of attention, stress, loss of orientation, fatigue, health condition, etc. In 24% of cases unexpected behaviors causes traffic accidents and only 0.7% of them are due to technological failures. For this reason, the potential of driver assistance and active safety systems that support the driver in complicated traffic situations is much higher when compared to passive safety. From this perspective it can be seen that with the construction of a self-driving vehicle, 75% of cases of fatality are likely to have a significant decrease in the percentage of life-loss in total number of traffic accidents. On the other side technological errors that affect the occurrence of fatal accidents may have a slight increase but all this based on the prejudice that in future there will be more vehicles with intelligent systems failures that may occur in disfunctional system.

No abstract

Abstract- Noise emitted by road traffic is one of the main causes that degrade the standard of the population lives in urban areas. In this paper, is developed a model for the estimating of continuous noise level (Leq) on the two-lane main urban road with medians in the city of Prishtina. Comparison of the results was done through performance indicators. It is found that independent variables have direct impact to dependent variable (Leq) and determination coefficient achieve accuracy close to 94 %. This approach could be applied for predicting traffic noise to different locations with the same category of roads through residential areas. Key words- Road urban traffic noise, Model, Multiple regression analysis.