The paper investigates a multi-stage investment problem under Conditional Value at Risk (CVaR) constraints with: a given security level for bankruptcy, short selling permission, a normal and an elliptical total return distribution models. The purpose of the work is to find a method of determining the optimal investment in this problem at each stage. As a result of the study, an optimal investment strategy is found and it is shown that the optimal investment portfolio at each stage does not depend on the value of the investor’s capital, but depends only on the number of stage. It is shown that the multi-stage problem can be reduced to a finite number of one-stage optimization problems, which are problems of conic programming. For the one-stage problem, conditions for the non-emptiness of the set of admissible portfolios are given and the Kuhn–Tucker theorem is applied. Additionally, this paper presents a numerical example of finding the optimal investment based on the open data on rates of assert prices of companies on the stock exchange.

Methods for constructing distributed automation systems for circuit design to calculate the instability of the coordinates of the operating points of the static mode of nonlinear electronic circuits were considered. Two-terminal networks of type R and transmission parameters of dependent sources, as well as characteristics of external influences (temperature, radiation, etc.) are taken as components that change under the influence of external factors. To solve the problem of calculating the instability of the coordinates of the operating points of the static mode of nonlinear electronic circuits, a technique is proposed based on the use of an auxiliary circuit, which is constructed by transposing the description of the original circuit. The features of the organization of serverless and microservice architecture for building circuit design automation systems are analyzed. The multitenant design of a microservice information system environment is described. The mechanism of operation of the service as a service is presented to ensure the operation of the business logic of the server component.

A relevant and highly demanded modern medicine problem in many of its areas is the timely detection and recognition of pathogenic microorganisms and microbial communities in the patient’s tissues for the speedy prescription and correct use of medicines from mutually exclusive tactics. The transition to a new level in the speed of visualization of the samples’ contents taken and the accuracy of diagnostics is possible because of the use of lanthanide staining in combination with scanning electron microscopy to retrieve a series of high-resolution images with subsequent automatic labelling and classification of microbiological objects. This paper presents the results of using the YOLOv5 neural network model to detect 15 different most common opportunistic classes of bacteria in 380 images. As a result, a 71.5% average accuracy and 69.8% recall were achieved by using the YOLOv5 base model without freezing layers.

The diagnosis of many diseases is largely possible thanks to MRI(Magnetic Resonance Imaging). This technology allows to study internal organs of the patient: the brain, spine, bones, joints, vessels and etc. The resolution of the MRI image is limited due to various factors: movement of the patient during the scan, the continuous movement of internal organs. The higher the quality of the MRI image, the longer it takes to scan. For more accurate diagnostics it is possible to increase resolution of the yielded images. This is achieved by using SISR(Single Image Super Resolution) algorithms, which allow you to obtain images with increased resolution from a single input image. In this paper the idea of the image super-resolution algorithms is presented, various forms of the problem and solutions to it are provided. The advantages of the SISR algorithms are described. The relevance of this task in the field of medical MRI images is explained. Metrics for comparing image quality PSNR and SSIM are given and described. A dataset for testing is presented. The stage of data preparation is described: the principle of selecting images from a set of datasets, converting data into the required format, compressing images to obtain input data for selected neural network models. The PSNR, SSIM metrics of two neural network models mDCSRN and FAWDN are measured on equally prepared input data. The comparison results are presented in the form of images and averaged data for the entire sample is stored in the table.

The main problems of configuring the dependences of software products built based on a microservice architecture are described. Examples of a description of the software dependency configuration based on a semantic versioning system are given. A technique to control the dependences of the components of the distributed information systems is considered. A technique for constructing mathematical support for the nonstationary states of nonlinear electronic circuits by the methods of diakoptics is described. It is noted that the absence of inductive connections between individual subcircuits, as well as the placement of control and controlled variables of each dependent source within each subcircuit, is a necessary condition for the possibility of using the proposed technique. It is shown that the practical implementation of the proposed methodology can significantly increase the productivity of the CAD circuit and solve a calculation problem faster, which is especially important in the development of distributed automation systems for designing a circuit.

AIM:To evaluate the possibilities of textural analysis of 3D models in differentiating the degree of nuclear dysplasia of the clear cell renal cell carcinoma (ccRCC).MATERIALS AND METHODS:The specimens after surgical treatment of 190 patients with ccRCC were analyzed. In all cases, nephron-sparing surgery (NSS) was performed through laparoscopic access. The clinical characteristics were evaluated, including age, gender, tumor localization (side, surface and segments), absolute tumor volume, Charlson comorbidity index, body mass index, nephrometry scores (RENAL, PADOVA, C-index). Patients were divided into 2 groups. In group 1, there were 119 patients with the ccRCC of Grade 1 or 2, while group 2 consisted of 71 patients with ccRCC of Grade 3 and 4. All patients underwent 3D virtual planning of procedure using the 3D modeling program "Amira". At the first stage, two experienced radiologists performed manual segmentation of 3D models of kidney parenchyma tumors. At the second stage, the tumor shape was analyzed with a mathematical calculation of three indicators and more than 300 textural features of statistics of types 1-2 were extracted. Further, an intellectual analysis was carried out. For the evaluation of tumor grade according to Furman system, the classification problem was solved using the machine learning algorithm Stochastic Gradient Descent and cross-validation k=5.RESULTS:The accuracy of classification for the two groups of Grade 1 or 2 and Grade 3 or 4 on the F1 metric was 72.2. To build the model, the following parameters were selected: the absolute tumor volume, the Charlson comorbidity index, "Energy", the first quartile and the second decile of the pixel intensity distribution.CONCLUSION:The texture analysis of 3D models for the prediction of Fuhrman grade in ccRCC demonstrated satisfactory quality for two groups of Grade 1 or 2 and Grade 3 or 4 nuclear dysplasia.

The problem of designing an optimal insurance strategy in a modification of the risk process with discrete time is investigated. This model introduces stage-by-stage probabilistic constraints (Value-at-Risk (VaR) constraints) on the insurer's capital increments during each stage. Also, the set of admissible insurances is determined by a safety level reflecting a 'good' or 'bad' capital increment at the previous stage. The mathematical expectation of the insurer's final capital is used as the objective functional. The total loss of the insurer at each stage is modeled by the Gaussian (normal) distribution with parameters depending on a seded loss function (or, in other words, an insurance policy) selected. In contrast to traditional dynamic optimization models for insurance strategies, the proposed approach allows to construct the value functions (and hence the optimal insurance policies) by simply solving a sequence of static insurance optimization problems. It is demonstrated that the optimal seded loss function at each stage depends on the prescribed value of the safety level: it is either a stop-loss insurance or conditional deductible insurance having a discontinuous point. In order to reduce ex post moral hazard, we also investigate the case, where both parties in an insurance contract are obligated to pay more for a larger realization of loss. This leads to that the optimal seeded loss functions are either stop-loss insurances or unconditional deductible insurances.

Currently, instrumental brain imaging plays a significant role in the examination of patients with cognitive impairment. It is important for diagnostic process, prognosis of the course of neurodegenerative, cerebrovascular and other diseases, clarification of the role of individual brain structures and systems in the development of cognitive and other neuropsychiatric disorders. The purpose of the study was to analyze the volumes of the medial temporal lobes (MTL), hippocampus and brain volume in middle-aged patients with pre-mild cognitive decline. Material and methods. 38 patients (33 women, 5 men) of middle age (60.77 ± 9.4 years) were examined. Patients were divided into two groups: with subjective cognitive decline (SCD) – 15 patients, aged 53.5 ± 6.94 years and subtle cognitive decline (StCD) – 23 people aged 63.35 ± 8.64 years (groups statistically did not differ in age). All patients underwent a neuropsychological examination with an assessment of the cognitive sphere, magnetic resonance imaging of the brain, including the assessment of the presence and degree of microangiopathy (MAP), morphometry of the medial temporal lobes, hippocampus, brain volume and a study for the presence of the allele of the apolyprotein E gene (ApoE4). Results. A decrease in the average and total hippocampal volume was found in patients with StCD compared to patients with SCD. Also, MAP was significantly more common in patients with StCD. There were no differences in the degree of MTL atrophy. A decrease in the volume of the left hippocampus was revealed in patients with aggravated heredity for dementia. The average and total volume of the hippocampus is reduced in carriers of the ApoE4 allele of the apolyprotein gene. Correlation analysis showed the relationship between the average volume of the hippocampus and the volume of the brain.

An approach to building automated control of multi-tenant components of information systems is described. The main advantages of using discretizing multi-tenant shells for building distributed information systems are reflected and justified. Methods for managing the infrastructure of a distributed system as a code are given. Technologies and their settings for automating management at different stages of the life cycle of a software system built on the basis of discretizing multi-tenant shells are presented. The solution to the problem of dual use of the process manager in a container based on the Linux operating system in a manual and automated version in the context of managing life cycle stages using the CI / CD approach is described. A technique for modeling weakly coupled electronic circuits based on the technology of calculating large electronic circuits in parts is proposed, by selecting weakly coupled subcircuits between which there are no inductive connections and the condition for the concentration of control and controlled variable dependent sources within a separate subcircuit is met. It is shown that the implementation of the diacoptic approach to modeling large loosely coupled circuits significantly increases the productivity of the computational process, which is especially important in the development of distributed computer-aided design systems. It is proposed to build and transform the description of the simulated circuit to use generalized signal graphs that display the equations of the circuit in a generalized cause-and-effect form.

The paper presents a constructive description of the set of all efficient (Pareto-optimal) investment portfolios in a new setting, where the risk measure named “shortfall probability” (SP) is understood as the probability of a shortfall of investor’s capital below a prescribed level. Under a normality assumption, it is shown that SP has a generalized convexity property, the set efficient portfolios is constructed. Relations between the set of mean-SP and the set of mean-variance efficient portfolios as well as between mean-SP and mean-Value-at-Risk (VaR) sets of efficient portfolios are studied. It turns out that mean-SP efficient set is a proper subset of the mean-variance efficient set; interrelation with the mean-VaR efficient set is more complicated, however, mean-SP efficient set is proved to be a proper subset of mean-VaR efficient set under a sufficiently high confidence level. Besides a normal distribution, elliptic distributions are considered as an alternative for modeling the investor’s total return distribution. The obtained results provides the investor with a risk measure, that is more vivid than the variance and Value-at-Risk, and with determination of the corresponding set of effective portfolios.

The article is devoted to the problem of diagnosing subclinical keratoconus (KK). The need to identify early signs of KK is primarily associated with the potential for the development of iatrogenic keratoectasia in cases of underdiagnosis of the disease when determining the conditions for laser keratorefractive surgery involving a decrease in the thickness of the cornea. Today generally accepted algorithms for early computer-assisted diagnosis of KK are mainly based on the analysis of various morphometric parameters of the cornea, reflecting changes in its shape and thickness induced by structural abnormalities. Direct detection of structural changes in the cornea characteristic of early KK requires the use of high-tech imaging methods that are not always applicable in everyday clinical practice. The promising approach proposed in this study is based on the fact that a digital image of a corneal «slice» obtained using serial analyzers such as the Scheimpflug camera widely used in clinical practice provides indirect information about the structure of the epithelial layer, the local thickening of which takes place in the initial stages KK. It is this criterion that underlies the proposed system of computer-assisted diagnosis of KK. The carried out studies have shown the high sensitivity of this algorithm, and its specificity can be increased by involving the known diagnostic indicators of KK.

As a result of a sharp popularity increase of artificial intelligence resource-intensive methods, a serious problem arises in the preliminary data preparation for the convolutional neural networks models effective training. The authors present an approach based on the training dataset iterative updating principle using the YOLO neural network model for areas of interest detection, objects selection, and the original images labeling process automation. The proposed approach was tested with various model configurations for bacteria labeling on images obtained using a scanning electron microscope and, on average, demonstrated ~90% precision on a training dataset increased by 1.75 times over the initial training dataset.

The principles of building information systems based on service-oriented architecture are considered. The advantages of using this architectural approach, as well as a model of the component composition of the system, are described. A description of various technologies for building software using a service-oriented approach based on web services is given. The main limitations of using the CORBA technology standard for writing distributed applications are determined. The technology of building web services based on the SOAP data exchange protocol is described in the context of using the ESB service bus for the interaction of heterogeneous services in a single information system. The architectural style of microservice organization of distributed software is considered as a way to increase the granularity of the system in order to ensure the best scalability and fault tolerance of the system. Methods for constructing the mathematical support of web services for distributed schematic CAD systems for calculating the influence of external influences (changes in temperature, radiation, etc.) on all output functions of the simulated circuit are presented. Parameters of two-terminal type R, L, and C and transmission parameters of dependent current or voltage sources controlled by potential or current variables are taken as variable values of the components.

The basic requirements for software for building distributed automation systems for circuit design have been determined. The distinctive features of the architectural style of building distributed systems based on RESTful web services are described. Methods for grouping the components of the simulated circuit based on the type of connected pole are described. A form of writing an equation for a modeled scheme is proposed with the possibility of using both explicit and implicit forms for describing component equations. Two methods are proposed for the implementation of the computational process of calculating the characteristics of an electronic circuit based on different principles. formation of mathematical description in complex and linear forms. The advantages and disadvantages of the described methods, as well as algorithms for the formation of a mathematical description are given.

A method of organizing iteration loops in calculating dynamic modes of large electronic circuits based on a decomposition of the modeled circuit into subcircuit components is considered. This method considerably reduces the time required for the interaction of system's users with the network, so the efficiency of the used software is improved significantly, which is especially important for the construction of service-oriented computer-aided design systems.

Расчет чувствительности схемных функций электронных схем в частотной области и анализ нестабильности режима работы компонентной базы, функционирующей в условиях внешних воздействий (изменение температуры, давления, радиации и т. д.) являются важнейшими этапами проектирования современной электронной аппаратуры. В докладе рассматриваются методы построения веб-сервисов для решения такой задачи при построении распределенных систем автоматизации схемотехнического проектирования.

The paper considers an integrated approach for constructing models for predicting the perioperative parameters of laparoscopic kidney resections, which include the duration of the operation, the time of thermal ischemia, and the glomerular filtration rate 24 hours after the operation. The approach is based on the principle of expanding the feature space, extracted from the analysis of the surgeon's "learning curve" data when mastering laparoscopic kidney resections. The aim of this work is to predict the main perioperative parameters that have the most significant impact on the surgical tactics of treatment at the stage of planning surgery. New methods have been developed for identifying significant parameters that take into account the complexity of the operation and the qualifications of the surgeon based on his “learning curve”. The parameters to be distinguished include: “complexity of the operation” based on nephrometric indices (RENAL, PADUA and C-index); the average value of the predicted perioperative parameters of surgical interventions depending on the complexity; slope and standard error based on the regression line of predicted perioperative parameters. Models were developed for predicting the perioperative parameters of laparoscopic organ-preserving kidney interventions using modern approaches based on machine learning, which are based on the algorithms “decision trees”, “multilayer perceptron”, “Naïve Bayes”, “logistic regression”. A comparative analysis of the quality of the developed models was carried out, as a result of which the best result was obtained using the “logistic regression” algorithm. The F-measure was used as a metric. A comparative analysis of the developed models was carried out to assess the impact on the final quality of the new selected features. For the predicted parameter “time of thermal ischemia” the increase was from 9.68% to 16.68%; for the predicted parameter “duration of surgery” the increase was from 2.76% to 4.08%. At the same time, for the predicted parameter “GFR in 24 hours” there was no significant increase, and for the “multilayer perceptron” algorithm it turned out to be negative. The obtained forecasting models can be used in applied software solutions that act as decision support systems in determining the surgical tactics of treating patients with localized formations of the renal parenchyma. Such software solutions can be implemented as a web service or as a separate program.

The progress of cognitive impairments at the initial stage is poorly researched and is difficult to be diagnosed. This paper proposes an integrated approach based on the initial data analysis and the subsystem construction to predict the progression of further complications in patients with cognitive impairment symptoms. The combined use of statistical analysis and machine learning methods made it possible to achieve 78% accuracy in diagnosing subtle cognitive impairments in a sample of 526 patients. Visualization methods helped to improve the created model’s interpretability.