**1**-

**4**spośród

**4**dla zapytania:

*authorDesc:"Orken MAMYRBAYEV"*###
**Problem of placement of the minimal number of cameras at a given transport network**
DOI:10.15199/48.2017.06.31

Introduction Traffic jam is one of the most pressing problems of modern cities with supersaturated roads. Shortness of movement has become one of the essential features of big city life. Therefore, introduction of intelligent transport systems (ITS) is of interest for almost every industrialized city [1]. Such systems are designed to increase the capacity of streets and highways, to improve communication speed and traffic safety, to reduce delays at intersections, to reduce the consumption of fuel and lubricants, to improve environment. The basis of all intelligent transport systems is continuous collection of information about traffic conditions, flow rates, accidents and conditions for movement of cars, which is further processed and conveniently brought to the attention of drivers, or used for traffic control [1,2]. Video camera is one of the most simple, familiar and effective tools used in monitoring. Its advantage over other tracking systems is in capability to see directly everything that is in the camera's view. Modern specialized software for processing images from cameras is capable to measure the parameters of the moving stream (e.g., the vehicles movement speed, traffic flow density), to determine the state registration plates of vehicles, to detect violations of traffic rules [3]. Subsequently, this information may also be used for various purposes. Development of digital technology and cheapening of video cameras caused an opportunity to organize video surveillance (with the subsequent development of ITS) in cities with a minimum number of cameras providing the most complete monitoring of the city's transport network. This work involves the implementation of this particular approach. Preliminary analysis In order to build an adequate model it requires some initial information about problem areas in the city, the speed limit, the average occupancy of individual sites, dependence on the time of the day and on[...]

###
**Application of bayesian networks for estimation of individual psychological characteristics**
DOI:10.15199/48.2019.05.23

In this article we discuss applications of Bayesian network methods for solving typical and highly demanding tasks in psychology. We compute overall estimates of the psychological personality traits, based on given answers on offered psychological tests, as well as a comprehensive study of the social status of the individual, their religious beliefs, educational level, intellectual capabilities, the influence of a particular social environment, etc. We believe that the most optimal mathematical model for solving this problem is a graphical probabilistic model with strongly expressed cause-effect relations. Therefore, we chose the Bayesian network as our model. Advantages of the Bayesian network are as follows: 1) The Bayesian network reflects the causal-effect relationship very well. 2) The mathematical apparatus of Bayesian networks is well developed and thus, there are many software implementations of the Bayesian network methods available. Bayesian framework is very popular in various kinds of applications: parameter identification, Bayesian update, uncertainty quantification, inverse problems [1], and classification. Bayesian network is a graphical probabilistic model that represents a set of random variables and their conditional dependencies via a directed acyclic graph [2], [3], [4]. For example, a Bayesian network could represent the probabilistic connections between overall economical situations, average salaries and nationalism in society. It can give recommendations to local governments of which steps to undertake to decrease the level of political tensions. Other promising applications are in Human Resource (HR) departments and in marriage agencies. Bayesian networks, by analyzing psychological properties of each individual, and sociological connections between individuals, may help to select a better group for a certain task, prevent possible conflicts and increase performance. In this work we will apply Ba[...]

###
**Speech Recognizer-Based Non-Uniform Spectral Compression for Robust MFCC Feature Extraction**
DOI:10.15199/48.2018.06.17

The performance of speech recognition degrades dramatically in the presence of noise, due to spectral mismatch between the training and testing data. Therefore, robust speech recognition in noisy environment is still a challenging problem. To solve this problem, many compensation techniques have been proposed by researchers. In general, a compensation technique can be applied in the signal, feature or model space [1]. This paper focuses on the compensation in feature domain. Spectral compression is an effective robust feature extraction technique to reduce the mismatch between training and testing data in feature domain. In conventional Mel-frequency cepstral coefficients (MFCC) feature extraction, a logarithm function is applied to Mel filter bank energies in order to reduce their dynamic range. Root cepstral analysis [2] replace log function with a constant root function and yields RCC coefficients. RCC coefficients have shown better robustness against the noise. In RCC method compressed speech spectrum is computed as shown in (1): (1) PC (m) P(m) , 0 1 where PC (m) is the compressed spectrum, P(m) is the original spectrum, is the compression factor and m is the filter bank index. In (1), the compression factor is fixed for all the frequency bands under the assumption that the noise contamination is same throughout all frequency bands, although real world noise is mostly colored and does not affect the speech signal uniformly over the entire spectrum. Therefore, the compression factor should be adjusted for each band. Also, from the psychoacoustic point of view, using constant compression root for all frequencies is suboptimal [3]. Therefore, relation (1) is extended as follows: (2) P (m) P(m) (m) , 0 (m) 1 C where the compression factor is dependent on the frequency band and named non-uniform spectral compression. Even i[...]

###
**Further Results on Output Tracking for a Class of Uncertain High-Order Nonlinear Time-Delay Systems**
DOI:10.15199/48.2019.05.22

The control design is one of the most relevant topics in nonlinear system theory, so a number of researchers have paid particular attention to it, for example, it can be seen in references [1-11]. The fundamental problem is to construct a feedback control law making the controlled output track a given reference signal as much as possible. The problem of global practical tracking for nonlinear state feedback systems was solved by the method of adding a power integrator [3,4] and using the idea of universal control [1,2]. However, the above results do not take into account time delays and their impact on the system as a whole. For example, in three-dimensional systems, delay is determined by the fact that the signals propagate at a finite speed and they need time to overcome distances [12]. Delay of the reaction to the signal and feedback with delay are inherent in many physical [13], chemical [14], climatic [15] and biological [16] objects and processes. In the study of systems with delay, it is important to know the values of time delays, the value of which largely determines the dynamics and properties of the system. Since time-delay exists widely in many practical systems such as electrical networks, microwave oscillator, and hydraulic systems, etc., and usually makes the considered system instable, to achieve some control objectives such as stabilization and trajectory tracking, the influence of time delay phenomenon should be considered. In view of these facts, it is meaningful and necessary to study control problems of accidental nonlinear systems with unknown parameters and time-delays. In recent years, by employing the Lyapunov-Krasovskii method to deal with the time-delay, control theory, and techniques for stabilization problem of time-delay nonlinear systems were greatly developed and advanced methods have been made; see, for instance, [17-21] and reference therein. Compared with study the stabilization problem [...]

**Strona 1**