All issues

This article solves the problem of vehicles drivers intoxication functional statedetermining. Its solution is relevant in the transport security field during pre-trip medical examination. The problem solution is based on the papillomometry method application, which allows to evaluate the driver state by his pupillary reaction to illumination change. The problem is to determine the state of driver inebriation by the analysis of the papillogram parameters values — a time series characterizing the change in pupil dimensions upon exposure to a short-time light pulse. For the papillograms analysis it is proposed to use a neural network. A neural network model for determining the drivers intoxication functional state is developed. For its training, specially prepared data samples are used which are the values of the following parameters of pupillary reactions grouped into two classes of functional states of drivers: initial diameter, minimum diameter, half-constriction diameter, final diameter, narrowing amplitude, rate of constriction, expansion rate, latent reaction time, the contraction time, the expansion time, the half-contraction time, and the half-expansion time. An example of the initial data is given. Based on their analysis, a neural network model is constructed in the form of a single-layer perceptron consisting of twelve input neurons, twenty-five neurons of the hidden layer, and one output neuron. To increase the model adequacy using the method of ROC analysis, the optimal cut-off point for the classes of solutions at the output of the neural network is determined. A scheme for determining the drivers intoxication state is proposed, which includes the following steps: pupillary reaction video registration, papillogram construction, parameters values calculation, data analysis on the base of the neural network model, driver’s condition classification as “norm” or “rejection of the norm”, making decisions on the person being audited. A medical worker conducting driver examination is presented with a neural network assessment of his intoxication state. On the basis of this assessment, an opinion on the admission or removal of the driver from driving the vehicle is drawn. Thus, the neural network model solves the problem of increasing the efficiency of pre-trip medical examination by increasing the reliability of the decisions made.

Multi-label classification models arise in various areas of life, which is explained by an increasing amount of information that requires prompt analysis. One of the mathematical methods for solving this problem is a plug-in approach, at the first stage of which, for each class, a certain ranking function is built, ordering all objects in some way, and at the second stage, the optimal thresholds are selected, the objects on one side of which are assigned to the current class, and on the other — to the other. Thresholds are chosen to maximize the target quality measure. The algorithms which properties are investigated in this article are devoted to the second stage of the plug-in approach which is the choice of the optimal threshold vector. This step becomes non-trivial if the $F$-measure of average precision and recall is used as the target quality assessment since it does not allow independent threshold optimization in each class. In problems of extreme multi-label classification, the number of classes can reach hundreds of thousands, so the original optimization problem is reduced to the problem of searching a fixed point of a specially introduced transformation $\boldsymbol V$, defined on a unit square on the plane of average precision $P$ and recall $R$. Using this transformation, two algorithms are proposed for optimization: the $F$-measure linearization method and the method of $\boldsymbol V$ domain analysis. The properties of algorithms are studied when applied to multi-label classification data sets of various sizes and origin, in particular, the dependence of the error on the number of classes, on the $F$-measure parameter, and on the internal parameters of methods under study. The peculiarity of both algorithms work when used for problems with the domain of $\boldsymbol V$, containing large linear boundaries, was found. In case when the optimal point is located in the vicinity of these boundaries, the errors of both methods do not decrease with an increase in the number of classes. In this case, the linearization method quite accurately determines the argument of the optimal point, while the method of $\boldsymbol V$ domain analysis — the polar radius.

We consider a mechanical system consisting of a rigid body and two masses that move inside the body along mutually perpendicular guides. The body has a flat face, which rests on a horizontal rough plane. The masses move inside the body in a vertical plane according to a harmonic law with the same period. It is assumed that the friction forces arising in the area of contact between the body and the supporting plane are described by the classical model of dry Coulomb friction, and the parameters of the problem are chosen so that the body can perform translationally rectilinearly motion. This mechanical system can serve as the simplest model of a capsule robot moving on a solid surface by moving internal elements.

We study the modes of motion of a body in which its velocity is periodic with a period equal to the period of motion of the internal masses. It is shown that if the body can starts to move from a state of rest by means of displacements of the masses, then for any permissible values of the problem parameters there is a periodic mode of motion. Depending on the parameter values, the nature of the periodic motion can be essentially different. In particular, both reversible and nonreversible driving modes are possible. In the non-reversion mode, the body moves in the same direction, and intervals of movement alternate with intervals of rest (body sticking). In the reversal mode, the body moves in both positive and negative directions over a time interval equal to one period. In this case, the body makes two stops during the period of movement. After stopping, the body either immediately continues moving in the opposite direction, or enters a sticking zone and rests for a finite period of time, and then stats moving in the opposite direction. It was also found that, at certain parameter values, a periodic reversal mode is possible, in which the body moves without sticking. A detailed classification of all possible types of periodic motion modes was carried out. Their complete qualitative description is given and the regions of their existence in the three-dimensional space of the parameters are constructed.

This article explores a method of machine learning based on the theory of random functions. One of the main problems of this method is that decision rule of a model becomes more complicated as the number of training dataset examples increases. The decision rule of the model is the most probable realization of a random function and it's represented as a polynomial with the number of terms equal to the number of training examples. In this article we will show the quick way of the number of training dataset examples reduction and, accordingly, the complexity of the decision rule. Reducing the number of examples of training dataset is due to the search and removal of weak elements that have little effect on the final form of the decision function, and noise sampling elements. For each $(x_i,y_i)$-th element sample was introduced the concept of value, which is expressed by the deviation of the estimated value of the decision function of the model at the point $x_i$, built without the $i$-th element, from the true value $y_i$. Also we show the possibility of indirect using weak elements in the process of training model without increasing the number of terms in the decision function. At the experimental part of the article, we show how changed amount of data affects to the ability of the method of generalizing in the classification task.

The different types of the reduced equations are known in the dynamics a heavy rigid body with a fixed point. Since the Euler−Poisson’s equations admit the three first integrals, then for the first approach the obtaining new forms of equations are usually based on these integrals. The system of six scalar equations can be transformed to a third-order system with them. However, in indicated approach the reduced system will have a feature as in the form of radical expressions a relatively the components of the angular velocity vector. This fact prevents the effective the effective application of numerical and asymptotic methods of solutions research. In the second approach the different types of variables in a problem are used: Euler’s angles, Hamilton’s variables and other variables. In this approach the Euler−Poisson’s equations are reduced to either the system of second-order differential equations, or the system for which the special methods are effective. In the article the method of finding the reduced system based on the introduction of an auxiliary variable is applied. This variable characterizes the mixed product of the angular momentum vector, the vector of vertical and the unit vector barycentric axis of the body. The system of four differential equations, two of which are linear differential equations was obtained. This system has no analog and does not contain the features that allows to apply to it the analytical and numerical methods. Received form of equations is applied for the analysis of a special class of solutions in the case when the center of mass of the body belongs to the barycentric axis. The variant in which the sum of the squares of the two components of the angular momentum vector with respect to not barycentric axes is constant. It is proved that this variant exists only in the Steklov’s solution. The obtained form of Euler−Poisson’s equations can be used to the investigation of the conditions of existence of other classes of solutions. Certain perspectives obtained equations consists a record of all solutions for which the center of mass is on barycentric axis in the variables of this article. It allows to carry out a classification solutions of Euler−Poisson’s equations depending on the order of invariant relations. Since the equations system specified in the article has no singularities, it can be considered in computer modeling using numerical methods.

Ultrasound examination of material properties is a precision method for determining their elastic and strength properties in connection with the small wavelength formed in the material after impact of a laser beam. In this paper, the wave processes arising during these measurements are considered in detail. It is shown that full-wave numerical modeling allows us to study in detail the types of waves, topological characteristics of their profile, speed of arrival of waves at various points, identification the types of waves whose measurements are most optimal for examining a sample made of a specific material of a particular shape, and to develop measurement procedures.

To carry out full-wave modeling, a grid-characteristic method on structured grids was used in this work and a hyperbolic system of equations that describes the propagation of elastic waves in the material of the thin plate under consideration on a specific example of a ratio of thickness to width of 1:10 was solved.

To simulate an elastic front that arose in the plate due to a laser beam, a model of the corresponding initial conditions was proposed. A comparison of the wave effects that arise during its use in the case of a point source and with the data of physical experiments on the propagation of laser ultrasound in metal plates was made.

A study was made on the basis of which the characteristic topological features of the wave processes under consideration were identified and revealed. The main types of elastic waves arising due to a laser beam are investigated, the possibility of their use for studying the properties of materials is analyzed. A method based on the analysis of multiple waves is proposed. The proposed method for studying the properties of a plate with the help of multiple waves on synthetic data was tested, and it showed good results.

It should be noted that most of the studies of multiple waves are aimed at developing methods for their suppression. Multiple waves are not used to process the results of ultrasound studies due to the complexity of their detection in the recorded data of a physical experiment.

Due to the use of full wave modeling and analysis of spatial dynamic wave processes, multiple waves are considered in detail in this work and it is proposed to divide materials into three classes, which allows using multiple waves to obtain information about the material of the plate.

The main results of the work are the developed problem statements for the numerical simulation of the study of plates of a finite thickness by laser ultrasound; the revealed features of the wave phenomena arising in plates of a finite thickness; the developed method for studying the properties of the plate on the basis of multiple waves; the developed classification of materials.

The results of the studies presented in this paper may be of interest not only for developments in the field of ultrasonic non-destructive testing, but also in the field of seismic exploration of the earth's interior, since the proposed approach can be extended to more complex cases of heterogeneous media and applied in geophysics.

The work is devoted to the description of the author’s formal statements of the clustering problem for a given number of clusters, algorithms for their solution, as well as the results of using this toolkit in medicine.

The solution of the formulated problems by exact algorithms of implementations of even relatively low dimensions before proving optimality is impossible in a finite time due to their belonging to the NP class.

In this regard, we have proposed a hybrid algorithm that combines the advantages of precise methods based on clustering in paired distances at the initial stage with the speed of methods for solving simplified problems of splitting by cluster centers at the final stage. In the development of this direction, a sequential hybrid clustering algorithm using random search in the paradigm of swarm intelligence has been developed. The article describes it and presents the results of calculations of applied clustering problems.

To determine the effectiveness of the developed tools for optimal clustering of multidimensional objects according to a variety of heterogeneous indicators, a number of computational experiments were performed using data sets including socio-demographic, clinical anamnestic, electroencephalographic and psychometric data on the cognitive status of patients of the cardiology clinic. An experimental proof of the effectiveness of using local search algorithms in the paradigm of swarm intelligence within the framework of a hybrid algorithm for solving optimal clustering problems has been obtained.

The results of the calculations indicate the actual resolution of the main problem of using the discrete optimization apparatus — limiting the available dimensions of task implementations. We have shown that this problem is eliminated while maintaining an acceptable proximity of the clustering results to the optimal ones. The applied significance of the obtained clustering results is also due to the fact that the developed optimal clustering toolkit is supplemented by an assessment of the stability of the formed clusters, which allows for known factors (the presence of stenosis or older age) to additionally identify those patients whose cognitive resources are insufficient to overcome the influence of surgical anesthesia, as a result of which there is a unidirectional effect of postoperative deterioration of complex visual-motor reaction, attention and memory. This effect indicates the possibility of differentiating the classification of patients using the proposed tools.

This article solves the problem of constructing a neuro-fuzzy model of fuzzy rules formation and using them for objects state evaluation in conditions of uncertainty. Traditional mathematical statistics or simulation modeling methods do not allow building adequate models of objects in the specified conditions. Therefore, at present, the solution of many problems is based on the use of intelligent modeling technologies applying fuzzy logic methods. The traditional approach of fuzzy systems construction is associated with an expert attraction need to formulate fuzzy rules and specify the membership functions used in them. To eliminate this drawback, the automation of fuzzy rules formation, based on the machine learning methods and algorithms, is relevant. One of the approaches to solve this problem is to build a fuzzy neural network and train it on the data characterizing the object under study. This approach implementation required fuzzy rules type choice, taking into account the processed data specificity. In addition, it required logical inference algorithm development on the rules of the selected type. The algorithm steps determine the number and functionality of layers in the fuzzy neural network structure. The fuzzy neural network training algorithm developed. After network training the formation fuzzyproduction rules system is carried out. Based on developed mathematical tool, a software package has been implemented. On its basis, studies to assess the classifying ability of the fuzzy rules being formed have been conducted using the data analysis example from the UCI Machine Learning Repository. The research results showed that the formed fuzzy rules classifying ability is not inferior in accuracy to other classification methods. In addition, the logic inference algorithm on fuzzy rules allows successful classification in the absence of a part of the initial data. In order to test, to solve the problem of assessing oil industry water lines state fuzzy rules were generated. Based on the 303 water lines initial data, the base of 342 fuzzy rules was formed. Their practical approbation has shown high efficiency in solving the problem.

This work analyzes the problem of traffic signs recognition in intelligent transport systems. The basic concepts of computer vision and image recognition tasks are considered. The most effective approach for solving the problem of analyzing and recognizing images now is the neural network method. Among all kinds of neural networks, the convolutional neural network has proven itself best. Activation functions such as Relu and SoftMax are used to solve the classification problem when recognizing traffic signs. This article proposes a technology for recognizing traffic signs. The choice of an approach for solving the problem based on a convolutional neural network due to the ability to effectively solve the problem of identifying essential features and classification. The initial data for the neural network model were prepared and a training sample was formed. The Google Colaboratory cloud service with the external libraries for deep learning TensorFlow and Keras was used as a platform for the intelligent system development. The convolutional part of the network is designed to highlight characteristic features in the image. The first layer includes 512 neurons with the Relu activation function. Then there is the Dropout layer, which is used to reduce the effect of overfitting the network. The output fully connected layer includes four neurons, which corresponds to the problem of recognizing four types of traffic signs. An intelligent traffic sign recognition system has been developed and tested. The used convolutional neural network included four stages of convolution and subsampling. Evaluation of the efficiency of the traffic sign recognition system using the three-block cross-validation method showed that the error of the neural network model is minimal, therefore, in most cases, new images will be recognized correctly. In addition, the model has no errors of the first kind, and the error of the second kind has a low value and only when the input image is very noisy.