All issues

We suggested some approaches for solving image processing tasks in the decision support system (DSS) of the Center for Automated Recording of Administrative Offenses of the Road Traffic (CARAO). The main task of this system is to assist the operator in obtaining accurate information about the vehicle registration plate and the vehicle brand/model based on images obtained from the photo and video recording systems. We suggested the approach for vehicle registration plate recognition and brand/model classification on the images based on modern neural network models. LPRNet neural network model supplemented by Spatial Transformer Layer was used to recognize the vehicle registration plate. The ResNeXt-101-32x8d neural network model was used to classify for vehicle brand/model. We suggested the approach to construct the training set for the neural network of vehicle registration plate recognition. The approach is based on computer vision methods and machine learning algorithms. The SIFT algorithm was used to detect and describe local features on images with the vehicle registration plate. DBSCAN clustering was used to detect and delete outliers in such local features. The accuracy of vehicle registration plate recognition was 96% on the testing set. We suggested the approach to improve the efficiency of using the ResNeXt-101-32x8d model at additional training and classification stages. The approach is based on the new architecture of convolutional neural networks with “freezing” weight coefficients of convolutional layers, an additional convolutional layer for parallelizing the classification process, and a set of binary classifiers at the output. This approach significantly reduced the time of additional training of neural network when new vehicle brand/model classification was needed. The final accuracy of vehicle brand/model classification was 99% on the testing set. The proposed approaches were tested and implemented in the DSS of the CARAO of the Republic of Tatarstan.

The numerical methods used to simulate the evolution of hydrodynamic systems require the considerable use of computational resources thus limiting the number of possible simulations. The data-driven simulation technique is one promising approach to the development of heuristic models, which may speed up the study of such models. In this approach, machine learning methods are used to tune the weights of an artificial neural network that predicts the state of a physical system at a given point in time based on initial conditions. This article describes an original neural network architecture and a novel multi-stage training procedure which create a heuristic model of a two-phase flow in a heterogeneous porous medium. The neural network-based model predicts the states of the grid cells at an arbitrary timestep (within the known constraints), taking in only the initial conditions: the properties of the heterogeneous permeability of the medium and the location of sources and sinks. The proposed model requires orders of magnitude less processor time in comparison with the classical numerical method, which served as a criterion for evaluating the effectiveness of the trained model. The proposed architecture includes a number of subnets trained in various combinations on several datasets. The techniques of adversarial training and weight transfer are utilized.

Formation of adequate behavioral patterns in condition of the unknown environment carried out through exploratory behavior. At the same time the rapid formation of an acceptable pattern is more preferable than a long elaboration perfect pattern through repeat play learning situation. In extreme situations, phenomenon of imprinting is observed — instant imprinting of behavior pattern, which ensure the survival of individuals. In this paper we propose a hypothesis and imprint model when trained on a single successful pattern of virtual robot's neural network demonstrates the effective functioning. Realism of the model is estimated by checking the stability of playback behavior pattern to perturbations situation imprint run.

Transport of respiratory gases by respiratory and circulatory systems is one of the most important processes associated with living conditions of the human body. Significant and/or long-term deviations of oxygen and carbon dioxide concentrations from the normal values in blood can be a reason of significant pathological changes with irreversible consequences: lack of oxygen (hypoxia and ischemic events), the change in the acidbase balance of blood (acidosis or alkalosis), and others. In the context of a changing external environment and internal conditions of the body the action of its regulatory systems aimed at maintaining homeostasis. One of the major mechanisms for maintaining concentrations (partial pressures) of oxygen and carbon dioxide in the blood at a normal level is the regulation of minute ventilation, respiratory rate and depth of respiration, which is caused by the activity of the central and peripheral regulators.

In this paper we propose a mathematical model of the regulation of pulmonary ventilation parameter. The model is used to calculate the minute ventilation adaptation during hypoxia and hypercapnia. The model is developed using a single-component model of the lungs, and biochemical equilibrium conditions of oxygen and carbon dioxide in the blood and the alveolar lung volume. A comparison with laboratory data is performed during hypoxia and hypercapnia. Analysis of the results shows that the model reproduces the dynamics of minute ventilation during hypercapnia with sufficient accuracy. Another result is that more accurate model of regulation of minute ventilation during hypoxia should be developed. The factors preventing from satisfactory accuracy are analysed in the final section.

Respiratory function is one of the main limiting factors of the organism during intense physical activities. Thus, it is important characteristic of high performance sport and extreme physical activity conditions. Therefore, the results of this study have significant application value in the field of mathematical modeling in sport. The considered conditions of hypoxia and hypercapnia are partly reproduce training at high altitude and at hypoxia conditions. The purpose of these conditions is to increase the level of hemoglobin in the blood of highly qualified athletes. These conditions are the only admitted by sport committees.

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.

This work provides a new approach for constructing high-precision routes based on data from transport detectors inside the SUMO traffic modeling package. Existing tools such as flowrouter and routeSampler have a number of disadvantages, such as the lack of interaction with the network in the process of building routes. Our rlRouter uses multi-agent reinforcement learning (MARL), where the agents are incoming lanes and the environment is the road network. By performing actions to launch vehicles, agents receive a reward for matching data from transport detectors. Parameter Sharing DQN with the LSTM backbone of the Q-function was used as an algorithm for multi-agent reinforcement learning.

Since the rlRouter is trained inside the SUMO simulation, it can restore routes better by taking into account the interaction of vehicles within the network with each other and with the network infrastructure. We have modeled diverse traffic situations on three different junctions in order to compare the performance of SUMO’s routers with the rlRouter. We used Mean Absoluter Error (MAE) as the measure of the deviation from both cumulative detectors and routes data. The rlRouter achieved the highest compliance with the data from the detectors. We also found that by maximizing the reward for matching detectors, the resulting routes also get closer to the real ones. Despite the fact that the routes recovered using rlRouter are superior to the routes obtained using SUMO tools, they do not fully correspond to the real ones, due to the natural limitations of induction-loop detectors. To achieve more plausible routes, it is necessary to equip junctions with other types of transport counters, for example, camera detectors.

The rheological behavior of aqueous suspensions based on nanoscale silicon dioxide particles strongly depends on the dynamic viscosity, which affects directly the use of nanofluids. The purpose of this work is to develop and validate models for predicting dynamic viscosity from independent input parameters: silicon dioxide concentration SiO₂, pH acidity, and shear rate $\gamma$. The influence of the suspension composition on its dynamic viscosity is analyzed. Groups of suspensions with statistically homogeneous composition have been identified, within which the interchangeability of compositions is possible. It is shown that at low shear rates, the rheological properties of suspensions differ significantly from those obtained at higher speeds. Significant positive correlations of the dynamic viscosity of the suspension with SiO₂ concentration and pH acidity were established, and negative correlations with the shear rate $\gamma$. Regression models with regularization of the dependence of the dynamic viscosity $\eta$ on the concentrations of SiO₂, NaOH, H₃PO₄, surfactant (surfactant), EDA (ethylenediamine), shear rate γ were constructed. For more accurate prediction of dynamic viscosity, the models using algorithms of neural network technologies and machine learning (MLP multilayer perceptron, RBF radial basis function network, SVM support vector method, RF random forest method) were trained. The effectiveness of the constructed models was evaluated using various statistical metrics, including the average absolute approximation error (MAE), the average quadratic error (MSE), the coefficient of determination $R^2$, and the average percentage of absolute relative deviation (AARD%). The RF model proved to be the best model in the training and test samples. The contribution of each component to the constructed model is determined. It is shown that the concentration of SiO₂ has the greatest influence on the dynamic viscosity, followed by pH acidity and shear rate γ. The accuracy of the proposed models is compared to the accuracy of models previously published. The results confirm that the developed models can be considered as a practical tool for studying the behavior of nanofluids, which use aqueous suspensions based on nanoscale particles of silicon dioxide.

The paper considers the application of swarm intelligence technology to build agent-based simulation models. As an example, a minimal model is constructed illustrating the influence of information influences on the rules of behavior of agents in the simplest model of competition between two populations, whose agents perform the simplest task of transferring a resource from a mobile source to their territory. The algorithm for the movement of agents in the model space is implemented on the basis of the classical particle swarm algorithm. Agents have a life cycle, that is, the processes of birth and death are taken into account. The model takes into account information processes that determine the target functions of the behavior of newly appeared agents. These processes (training and poaching) are determined by information influences from populations. Under certain conditions, a third population arises in the agent system. Agents of such a population informatively influence agents of other populations in a certain radius around themselves, changing.

As a result of the conducted simulation experiments, it was shown that the following final states are realized in the system: displacement of a new population by others, coexistence of a new population and other populations and the absence of such a population. It has been shown that with an increase in the radius of influence of agents, the population with changed rules of behavior displaces all others. It is also shown that in the case of a hard-to-access resource, the strategy of luring agents of a competing population is more profitable.

This scientific work is dedicated to applying of two-layer interval weighted graphs in nonstationary time series forecasting and evaluation of market risks. The first layer of the graph, formed with the primary system training, displays potential system fluctuations at the time of system training. Interval vertexes of the second layer of the graph (the superstructure of the first layer) which display the degree of time series modeling error are connected with the first layer by edges. The proposed model has been approved by the 90-day forecast of steel billets. The average forecast error amounts 2,6 % (it’s less than the average forecast error of the autoregression models).

Here we demonstrate the results of kinetic modeilng of DNA double-strand breaks induction and repair and phosphorilated histone H2AX ($\gamma$-H2AX) and Rad51 foci formation in primary human fibroblasts exposed to low-LET ionizing radiation (IR). The model describes two major paths of DNA double-strand breaks repair: non-homologous end joining (NHEJ) and homologous recombination (HR) and considers interactions between DNA and several repair proteins (DNA-PKcs, ATM, Ku70/80, XRCC1, XRCC4, Rad51, RPA, etc.) using mass action equations and Michaelis–Menten kinetics. Experimental data on DNA rejoining kinetics and $\gamma$-H2AX and Rad51 foci formation in vicinity of double strand breaks in primary human fibroblasts exposed to low-LET IR with various dose rates and exposure times was utilized for training and statistical validation of the model.