Hardware and software complex for remote monitoring and control of a pregnant woman's health state

Introduction: The problem of remote monitoring of people's health has become especially urgent nowadays due to the rapid spread of dangerous infectious and viral diseases, such as COVID-19. This period was especially difficult for pregnant women. According to Rosstat statistics, in 2020, maternal mortality in Russia increased by 24.4% compared to 2019 and reached 11.2 per 100,000 newborns. This is the worst level since 2013. In the current conditions, there is a necessity for developing remote monitoring systems which allow you to check the health status of a pregnant woman remotely using tools outside a medical institution. Purpose: To develop the structure and validate the choice of elements for a hardware and software complex which would perform remote monitoring outside a medical institution and assess the condition of pregnant women during their active life. Results: An automated questionnaire for pregnant women has been developed in accordance with the methodological recommendations of the Ministry of Health of the Russian Federation, providing a quantitative assessment of the current state of a pregnant woman in order to study the dynamics of her health. Based on the results of instrumental studies, according to 30 factors of patient's body functioning and the questionnaire data, a set of diagnostically significant indicators was developed. For each of them, a range of values was specified (norm, alarm, pathology). We have developed an experimental sample of the hardware and software complex and tested its functioning, particularly the modes of taking biomedical data by urine tests. The algorithms for processing and analysis of biomedical data have been experimentally studied in order to confirm the validity of the proposed solutions. Practical relevance: The results of the studies allow us to affirmatively answer the question about the possibility of remote monitoring outside a medical institution and assessing the health state of a pregnant woman in order to predict pregnancy complications, as well as to validate the choice of measuring channels for recording a complex of biomedical signals and data, and the choice of algorithms for information processing and analysis.

Analysis of the probability of connectivity of a telecommunications network based on the reduction of several non-connectivity events to a union of independent events

Introduction: For large and structurally complex telecommunication networks, calculating the connectivity probability turns out to be a very cumbersome and time-consuming process due to the huge number of elements in the resulting expression. The most expedient way out of this situation is a method based on the representation of a network connectivity event in the form of sums of products of incompatible events. However, this method also requires performing additional operations on sets in some cases. Purpose: To eliminate the main disadvantages of the method using multi-variable inversion. Results: It is shown that the connectivity event of a graph should be interpreted as a union of connectivity events of all its subgraphs, which leads to the validity of the expression for the connectivity event of the network in the form of a union of connectivity events of typical subgraphs (path, backbone, and in general, a multi-pole tree) of the original random graph. An iterative procedure is proposed for bringing a given number of connectivity events to the union of independent events by sequentially adding subgraph disjoint events. The possibility of eliminating repetitive routine procedures inherent in methods using multi-variable inversion is proved by considering not the union of connectivity events (incoherence) degenerating into the sum of incompatible products, but the intersection of opposite events, which also leads to a similar sum. However, to obtain this sum, there is no need to perform a multi-variable inversion for each of the terms over all those previously analyzed. Practical relevance: The obtained analytical relations can be applied in the analysis of reliability, survivability or stability of complex telecommunications networks.

Analytical review of models and methods for automatic recognition of gestures and sign languages

Introduction: Currently, the recognition of gestures and sign languages is one of the most intensively developing areas in computer vision and applied linguistics. The results of current investigations are applied in a wide range of areas, from sign language translation to gesture-based interfaces. In that regard, various systems and methods for the analysis of gestural data are being developed. Purpose: A detailed review of methods and a comparative analysis of current approaches in automatic recognition of gestures and sign languages. Results: The main gesture recognition problems are the following: detection of articulators (mainly hands), pose estimation and segmentation of gestures in the flow of speech. The authors conclude that the use of two-stream convolutional and recurrent neural network architectures is generally promising for efficient extraction and processing of spatial and temporal features, thus solving the problem of dynamic gestures and coarticulations. This solution, however, heavily depends on the quality and availability of data sets. Practical relevance: This review can be considered a contribution to the study of rapidly developing sign language recognition, irrespective to particular natural sign languages. The results of the work can be used in the development of software systems for automatic gesture and sign language recognition.

On the convergence of bumping routes to their limit shapes in the RSK algorithm: numerical experiments

Introduction: The Robinson — Schensted — Knuth (RSK) algorithm transforms a sequence of elements of a linearly ordered set into a pair of Young tableaux P, Q of the same shape. This transformation is based on the process of bumping and inserting elements in tableau P according to special rules. The trajectory formed by all the boxes of the tableau P shifted in the RSK algorithm is called the bumping route. D. Romik and P. Śniady in 2016 obtained an explicit formula for the limit shape of the bumping route, which is determined by its first element. However, the rate of convergence of the bumping routes to the limit shape has not been previously investigated either theoretically or by numerical experiments. Purpose: Carrying out computer experiments to study the dynamics of the bumping routes produced by the RSK algorithm on Young tableaux as their sizes increase. Calculation of statistical means and variances of deviations of bumping routes from their limit shapes in the L2 metric for various values fed to the input of the RSK algorithm. Results: A series of computer experiments have been carried out on Young tableaux, consisting of up to 10 million boxes. We used 300 tableaux of each size. Different input values (0.1, 0.3, 0.5, 0.7, 0.9) were added to each such tableau using the RSK algorithm, and the deviations of the bumping routes built from these values from the corresponding limit shapes were calculated. The graphs of the statistical mean values and variances of these deviations were produced. It is noticed that the deviations decrease in proportion to the fourth root of the tableau size n. An approximation of the dependence of the mean values of deviations on n was obtained using the least squares method.

Methodology and information-measuring system for personalized synthesis of lower limb prostheses

Introduction: One of the methods for managing the quality of prosthetics is optimizing the composition of a modular prosthesis components. Mistakes in choosing models for functional modules of a prosthesis lead to a limited realization of the patient's potential capabilities, or to the choice of expensive highly functional models whose potential cannot be fully realized with the given body system disabilities. One of the most effective ways to solve this problem is to use the computer technology capabilities. Purpose: Substantiation of the methodology for the development of an innovative computer technology for personalized synthesis of a lower-limb prosthesis, including the development of the structure of an information-measuring system for its implementation. Methods: Analysis, synthesis, analogy; expert survey; analytic hierarchy process (Saaty method). The conceptual language of the International Classification of Functioning, Disability and Health was used to describe the factors influencing the requirements for the characteristics of prosthetic modules. Results: In order to choose models for prosthetic modules, we should use an extended system of factors, including both the basic factors associated with the purpose of the products and indicated in the catalogs, and additional factors: impairment indicators of the body functions and structures, the capacity and performance of the patient's activity and participation, the presence of barriers and facilitators environmental factors in which the prosthesis is planned to be used. Taking this system of factors into account, a structural diagram of an information-measuring system for examining a prosthetic patient has been developed. To select the components for the prosthesis, we have substantiated the necessity of creating a global electronic catalog, combining structured information on the models of prosthetic modules supplied by various manufacturers. A matrix representation form is proposed for the knowledge base, reflecting the rules for choosing models according to the correspondence of their characteristics to the estimates of the factors. The methodology of computerized selection of models from the electronic catalog has been substantiated. Practical relevance: The results of the work are a step towards the creation of a technology for a computerized multicriteria choice of components for a modular prosthesis, taking into account the personal needs and functional capabilities of the patient. The use of this technology will improve the patient's rehabilitation level and the quality of his or her life.

Intrusion detection in internet of things networks based on machine learning methods

Introduction: The growing amount of digital data generated, among others, by smart devices of the Internet of Things makes it important to study the application of machine learning methods to the detection of network traffic anomalies, namely the presence of network attacks. Purpose: To propose a unified approach to detecting attacks at different levels of IoT network architecture, based on machine learning methods. Results: It was shown that at the wireless sensor network level, attack detection is associated with the detection of anomalous behavior of IoT devices, when the deviation of an IoT device behavior from its profile exceeds a predetermined level. Smart IoT devices are profiled on the basis of statistical characteristics, such as the intensity and duration of packet transmission, the proportion of retransmitted packets, etc. At the level of a local or global wired IoT network, data is aggregated and then analyzed using machine learning methods. Trained classifiers can become a part of a network attack detection system, making decisions about compromising a node on the fly. Models of classifiers of network attacks were experimentally selected both at the level of a wireless sensor network and at the level of a local or global wired network. The best results in terms of completeness and accuracy estimates are demonstrated by the random forest method for a wired local and/or global network and by all the considered methods for a wireless sensor network. Practical relevance: The proposed models of classifiers can be used for developing intrusion detection systems in IoT networks.

Prediction of COVID-19 pandemic dynamics in Russia based on simple mathematical models of epidemics

Introduction: The COVID-19 pandemic which began in 2020 and has taken more than five million lives has become a threat to the very existence of mankind. Therefore, predicting the spread of COVID-19 in each individual country is a very urgent task. The complexity of its solution is due to the requirement for fast processing of large amounts of data and the fact that the data are mostly inaccurate and do not have the statistical properties necessary for the successful application of statistical methods. Therefore, it seems important to develop simple forecasting methods based on classical simple models of epidemiology which are only weakly sensitive to data inaccuracies. It is also important to demonstrate the feasibility of the approach in relation to the incidence data in Russia. Purpose: Obtaining forecast data based on classical simple models of epidemics, namely SIR and SEIR. Methods: For discrete versions of SIR and SEIR models, it is proposed to estimate the parameters of the models using a reduced version of the least squares method, and apply a scenario approach to the forecasting. The simplicity and a small number of parameters are the advantages of SIR and SEIR models, which is very important in the context of a lack of numerical input data and structural incompleteness of the models. Results: A forecast of the spread of COVID-19 in Russia has been built based on published data on the incidence from March 10 to April 20, 2020, and then, selectively, according to October 2020 data and October 2021 data. The results of the comparison between SIR and SEIR forecasts are presented. The same method was used to construct and present forecasts based on morbidity data in the fall of 2020 and in the fall of 2021 for Russia and for St. Petersburg. To set the parameters of the models which are difficult to determine from the official data, a scenario approach is used: the dynamics of the epidemic is analyzed for several possible values of the parameters. Practical relevance: The results obtained show that the proposed method predicts well the time of the onset of the peak incidence, despite the inaccuracy of the initial data.

Methodological approaches and algorithms for recognizing and counting animals in aerial photographs

Introduction: The complexity of recognition and counting of objects in a photographic image is directly related to variability of related factors: physical difference of objects from the same class, presence of images similar to objects to be recognized, non-uniform background, change of shooting conditions and position of the objects when the photo was taken. Most challenging are the problems of identifying people in crowds, animals in natural environment, cars from surveillance cameras, objects of construction and infrastructure on aerial photo images, etc. These problems have their own specific factor space, but the methodological approaches to their solution are similar. Purpose: The development of methodologies and software implementations solving the problem of recognition and counting of objects with high variability, on the example of reindeer recognition in the natural environment. Methods: Two approaches are investigated: feature-based recognition based on binary pixel classification and reference-based recognition using convolutional neural networks. Results: Methodologies and programs have been developed for pixel-by-pixel recognition with subsequent binarization, image clustering and cluster counting and image recognition using the convolutional neural network of Mask R-CNN architecture. The network is first trained to recognize animals as a class from the array of MS COCO dataset images and then trained on the array of aerial photographs of reindeer herds. Analysis of the results shows that feature-based methods with pixel-by-pixel recognition give good results on relatively simple images (recognition error 10–15%). The presence of artifacts on the image that are close to the characteristics of the reindeer images leads to a significant increase in the error. The convolutional neural network showed higher accuracy, which on the test sample was 82%, with no false positives. Practical relevance: А software prototype has been created for the recognition system based on convolutional neural networks with a web interface, and the program itself has been put into limited operation.

Signal power and energy-per-bit optimization problems in systems mMTC

Introduction: Currently, the issues of Internet of Things technology are being actively studied. The operation of a large number of various self-powered sensors is within the framework of a massive machine-type communication scenario, using random access methods. Topical issues in this type of communication are how to reduce the transmission signal power and to increase the device lifetime by reducing the consumed energy per bit. Purpose: Formulation and analysis of the problems of minimizing the transmission power and consumed energy per bit in systems with or without retransmissions in order to obtain the achievability bounds. Results: A model of the system is described, within which four problems are formulated and described, concerning the signal power minimization and energy consumption for given parameters (the number of information bits, the spectral efficiency of the system, and the Packet Delivery Ratio). The numerical results of solving these optimization problems are presented. They make it possible to obtain the achievability bounds for the considered characteristics in systems with or without losses. The lower bounds obtained by the Shannon formula are also presented, assuming that the message length is not limited. The obtained results showed that solving the minimization problem with respect to one of the parameters (signal power or consumed energy per bit) does not minimize the second parameter. This difference is most significant for information messages of a small length, which is common in IoT scenarios. Practical relevance: The results obtained allow you to assess the potential for minimizing the transmission signal power and consumed energy per bit in random multiple access systems with massive machine-type communication scenarios. Discussion: The presented problems were solved without taking into account the average delay of message transmission; the introduction of such a limitation should increase the transmitted signal power and consumed energy per bit.

Combined total variation of first and fractional orders for Poisson noise removal in digital images

Introduction: Many methods have been proposed to handle the image restoration problem with Poisson noise. A popular approach to Poissonian image reconstruction is the one based on Total Variation. This method can provide significantly sharp edges and visually fine images, but it results in piecewise-constant regions in the resulting images. Purpose: Developing an adaptive total variation-based model for the reconstruction of images contaminated by Poisson noise, and an algorithm for solving the optimization problem. Results: We proposed an effective way to restore images degraded by Poisson noise. Using the Bayesian framework, we proposed an adaptive model based on a combination of first-order total variation and fractional order total variation. The first-order total variation model is efficient for suppressing the noise and preserving the keen edges simultaneously. However, the first-order total variation method usually causes artifact problems in the obtained results. To avoid this drawback, we can use high-order total variation models, one of which is the fractional-order total variation-based model for image restoration. In the fractional-order total variation model, the derivatives have an order greater than or equal to one. It leads to the convenience of computation with a compact discrete form. However, methods based on the fractional-order total variation may cause image blurring. Thus, the proposed model incorporates the advantages of two total variation regularization models, having a significant effect on the edge-preserving image restoration. In order to solve the considered optimization problem, the Split Bregman method is used. Experimental results are provided, demonstrating the effectiveness of the proposed method. Practical relevance: The proposed method allows you to restore Poissonian images preserving their edges. The presented numerical simulation demonstrates the competitive performance of the model proposed for image reconstruction. Discussion: From the experimental results, we can see that the proposed algorithm is effective in suppressing noise and preserving the image edges. However, the weighted parameters in the proposed model were not automatically selected at each iteration of the proposed algorithm. This requires additional research.