Artificial intelligence is employed for solving complex scientific, technical, and practical problems. Such artificial intelligence techniques as neural networks, fuzzy systems, and genetic and evolutionary algorithms are widely used for communication systems management, optimization, and prediction. Artificial intelligence approach provides optimized results in a challenging task of call admission control, handover, routing, and traffic prediction in cellular networks. 5G mobile communications are designed as heterogeneous networks, whose important requirement is accommodating great numbers of users and the quality of service satisfaction. Call admission control plays a significant role in providing the desired quality of service. An effective call admission control algorithm is needed for optimizing the cellular network system. Many call admission control schemes have been proposed. The paper proposes a methodology for developing a genetic neurofuzzy controller for call admission in 5G networks. Performance of the proposed admission control is evaluated through computer simulation.

Inertial evaluation of the tyre-road interaction during emergency braking An improved method of evaluation of the parameters of braking efficiency in vehicles of M1 category has been proposed for expert examination of motor vehicle accidents. This method is based on the control of parameters which are able to significantly influence the friction processes in the contact tyre-road area. These parameters were discovered in the course of analysis of theoretical approaches to the evaluation of the quality of tyre-road interaction, analytical formulas used for evaluation of the main braking parameters (deceleration, stopping distance) as well as for experimental evaluation of parameters of inertia braking efficiency. The generalization of study results showed that existing expert methods of evaluation of the parameters of vehicle motion during emergency braking do not take into account the design of modern braking systems, tyres and psychological aspects of control of the braking process by a human operator. After processing experimental data, recommendations have been formed to improve the existing approaches and eliminate the discovered defects. The verification of the proposed recommendations allowed to establish the areas of their efficiency for M1 category vehicles on dry bituminous concrete and confirmed the need to conduct further studies for vehicles of other categories and other types and conditions of road surface within the framework of the developed general approach.

The paper proposes a method of conversion additive and multiplicative errors, mathematical models are obtained by a Taylor expansion of the transformation equations used measuring instruments in the instrumental component of the measurement uncertainty.

This paper offers an upgraded method for estimating the magnitude of friction between tyres of a motor vehicle and a road surface while investigating road accidents. The above-mentioned method is based on the resultant data of tyre-and-road interworking field tests in case of emergency braking. Such estimation of the magnitude of friction is to be carried out with a focus on the factors affecting the friction processes in the tyreand-road contact. The most important factors, which are included in the synthesized adaptive system used for friction coefficient estimation, have been defined based on the theoretical analysis of the data of deceleration and braking length of motor vehicles. The study of the existing expert methods used for estimating the level of tyre-and-road engagement and the effect of such level on the motional parameters of a motor vehicle has demonstrated the need for upgrading of the existing approaches. Unlike the existing practices, the friction coefficient estimation adaptive system offered by the authors hereof is a self-trainable system. Such system reduces any simulation uncertainty and the probability of occurrence of Type 1 and Type 2 errors. Such result is achieved owing to the fact that the system takes into account the upgraded design of the present-day brake systems and tyres, as well as the speed of motor vehicles and load of their wheels; the system is also efficient because it makes use of the up-to-date mathematical methods which are able to process raw (initial) data under conditions of stochastic and fuzzy uncertainty. The approach offered hereby has demonstrated its efficiency for motor vehicles belonging to categories М1 and N1 and has proven its potential applicability for other categories of motor vehicles.

Computer-measuring system of the induction motor's dynamical torque-speed characteristics In the article an efficient method of determining the dynamic torque-speed characteristic of induction motors and the computer-measuring system for its realization is considered. In this method, the additional flywheel is used, the dynamic measurements of the angular speed as a function of time are taken at the start, after the end of the transition process, and at during the self-braking mode of the induction motor. For approximating the data that are obtained as a result of the measurements, the moving average algorithm is used. Also, with the help of this system, the inertia moment, angular speed dependence on time, electromagnetic dynamic moment dependence on time, electromagnetic dynamic power dependence on time, mechanical dynamic power dependence on time, and dynamic loss in rotor winds dependence on time are measured. In the article, the results of experimental measurements of the induction motor characteristics using a proposed computermeasuring system are given. The proposed system is experimental; in the future, it can be used to test induction motors during their production processes.