Modern methods of image recognition are sensitive to various types of disturbances, which actualize the development of resilient intelligent algorithms for safety-critical applications. The current article develops a model and method of training a classifier that exhibits characteristics of resilience to adversarial attacks, fault injection, and concept drift. The proposed model has a hierarchical structure of prototypes and hyperspherical boundaries of classes formed in the space of high-level features. Class boundaries are optimized during training and provide perturbation absorption and graceful degradation. The proposed learning method involves the use of a combined loss function, which allows the use of both labeled and unlabeled data, implements the compression of the feature representation to a discrete form and ensures the compactness of the distribution of classes and the maximization of the buffer zone between classes. The main component of the loss function is the value of the normalized modification of Shannon's information measure, averaged over the alphabet of the classes, expressed as a function of accuracy characteristics. Simultaneously, accuracy characteristics are calculated on the basis of smoothed versions of the distribution of statistical hypothesis testing results. It is experimentally confirmed that the proposed approach provides a certain level of disturbance absorption, graceful degradation and recovery. During testing of the proposed algorithm on the Cifar10 data set, it was established that the integral metric of resilience to tensor damage by inversion of one randomly selected bit is about 0.95 if the share of damaged tensors does not exceed 30%. Also, during testing of the proposed algorithm, it was established that an adversarial attack with a disturbance that does not exceed the L∞-norm threshold equal to 3 provides resilience that exceeds the value of 0.95 according to the integral metric. Additionally, the integral metric of resilience during adaptation to the appearance of two new classes is 0.959. The integral metric of resilience to the real drift of concepts between the two classes is 0.973. The ability to adapt to the appearance of new classes or the concept drift has been confirmed 8 times faster than learning from scratch.
{"title":"Neural network based image classifier resilient to destructive perturbation influences – architecture and training method","authors":"V. Moskalenko, A. Moskalenko","doi":"10.32620/reks.2022.3.07","DOIUrl":"https://doi.org/10.32620/reks.2022.3.07","url":null,"abstract":"Modern methods of image recognition are sensitive to various types of disturbances, which actualize the development of resilient intelligent algorithms for safety-critical applications. The current article develops a model and method of training a classifier that exhibits characteristics of resilience to adversarial attacks, fault injection, and concept drift. The proposed model has a hierarchical structure of prototypes and hyperspherical boundaries of classes formed in the space of high-level features. Class boundaries are optimized during training and provide perturbation absorption and graceful degradation. The proposed learning method involves the use of a combined loss function, which allows the use of both labeled and unlabeled data, implements the compression of the feature representation to a discrete form and ensures the compactness of the distribution of classes and the maximization of the buffer zone between classes. The main component of the loss function is the value of the normalized modification of Shannon's information measure, averaged over the alphabet of the classes, expressed as a function of accuracy characteristics. Simultaneously, accuracy characteristics are calculated on the basis of smoothed versions of the distribution of statistical hypothesis testing results. It is experimentally confirmed that the proposed approach provides a certain level of disturbance absorption, graceful degradation and recovery. During testing of the proposed algorithm on the Cifar10 data set, it was established that the integral metric of resilience to tensor damage by inversion of one randomly selected bit is about 0.95 if the share of damaged tensors does not exceed 30%. Also, during testing of the proposed algorithm, it was established that an adversarial attack with a disturbance that does not exceed the L∞-norm threshold equal to 3 provides resilience that exceeds the value of 0.95 according to the integral metric. Additionally, the integral metric of resilience during adaptation to the appearance of two new classes is 0.959. The integral metric of resilience to the real drift of concepts between the two classes is 0.973. The ability to adapt to the appearance of new classes or the concept drift has been confirmed 8 times faster than learning from scratch.","PeriodicalId":36122,"journal":{"name":"Radioelectronic and Computer Systems","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44833563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Dovbysh, Volodymyr Liubchak, I. Shelehov, J. Simonovskiy, Alona Tenytska
The study aims to increase the functional efficiency of a machine learning cyber attack detection system. An information-extreme machine learning method of the cyberattack detection system with optimization of control tolerances for recognition features that reflect the traffic properties of the info-communication system has been developed. The method is developed within the framework of the functional approach to modeling of cognitive processes of natural intelligence at the formation and acceptance of classification decisions. This approach, in contrast to known methods of data mining, including neuron-like structures, allows giving the recognition system adaptability to arbitrary initial conditions of the learning matrix and flexibility in retraining the system by expanding the recognition classes alphabet. The method idea is to maximize the information capacity of the attack detection system in the machine learning process. A modified Kullback information measure is used as a criterion for optimizing machine learning parameters. According to the proposed categorical functional model, algorithmic software for attack detection system in the mode of machine learning with the depth of the second level has been developed and implemented. However, the depth level is determined by the number of machine learning parameters, which were optimized. The geometric parameters of the recognition hyperspherical containers classes and the control tolerances on the recognition features were considered as optimization parameters, which played the role of input data quantization levels in the transformation of the input Euclidean learning matrix of the type "object-property" into a working binary learning matrix given in the Hamming space. Admissible transformations of the working training matrix of the offered method allow adapting the input mathematical description of the attacks detection system to the maximum full probability of the correct classification decisions acceptance. Based on the results of information-extreme machine learning within the geometric approach, decisive rules are constructed as practically invariant to the multidimensionality of the recognition features space. The computer simulation results of information-extreme machine learning of the attack detection system to recognize four host traffic of different profiles confirm the developed method's efficiency.
{"title":"Information-extreme machine learning of a cyber attack detection system","authors":"A. Dovbysh, Volodymyr Liubchak, I. Shelehov, J. Simonovskiy, Alona Tenytska","doi":"10.32620/reks.2022.3.09","DOIUrl":"https://doi.org/10.32620/reks.2022.3.09","url":null,"abstract":"The study aims to increase the functional efficiency of a machine learning cyber attack detection system. An information-extreme machine learning method of the cyberattack detection system with optimization of control tolerances for recognition features that reflect the traffic properties of the info-communication system has been developed. The method is developed within the framework of the functional approach to modeling of cognitive processes of natural intelligence at the formation and acceptance of classification decisions. This approach, in contrast to known methods of data mining, including neuron-like structures, allows giving the recognition system adaptability to arbitrary initial conditions of the learning matrix and flexibility in retraining the system by expanding the recognition classes alphabet. The method idea is to maximize the information capacity of the attack detection system in the machine learning process. A modified Kullback information measure is used as a criterion for optimizing machine learning parameters. According to the proposed categorical functional model, algorithmic software for attack detection system in the mode of machine learning with the depth of the second level has been developed and implemented. However, the depth level is determined by the number of machine learning parameters, which were optimized. The geometric parameters of the recognition hyperspherical containers classes and the control tolerances on the recognition features were considered as optimization parameters, which played the role of input data quantization levels in the transformation of the input Euclidean learning matrix of the type \"object-property\" into a working binary learning matrix given in the Hamming space. Admissible transformations of the working training matrix of the offered method allow adapting the input mathematical description of the attacks detection system to the maximum full probability of the correct classification decisions acceptance. Based on the results of information-extreme machine learning within the geometric approach, decisive rules are constructed as practically invariant to the multidimensionality of the recognition features space. The computer simulation results of information-extreme machine learning of the attack detection system to recognize four host traffic of different profiles confirm the developed method's efficiency.","PeriodicalId":36122,"journal":{"name":"Radioelectronic and Computer Systems","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49059231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Subject matter: Early software size estimation is one of the project managers' significant problems in evaluating app development efforts because software size is the major determinant of software project effort. Function points (FPs) and lines of code (LOC) are most commonly used as measures of size in existing software effort estimation methods and models. As is known, both these metrics have their advantages and disadvantages when used for software effort estimation. Although the FPs-based measure has the advantage over the LOC in that it does not depend on the technologies used, however, the assessment of efforts requires considering such factors (environmental factors). Considering the above factors can be ensured by appropriate models for estimating the LOC-based effort. Nowadays, many Web apps are created using PHP frameworks making the app development faster. CodeIgniter is one such powerful framework. However, there are no regression models for estimating the software size of Web apps created using the CodeIgniter framework. This requires the construction of the appropriate models. The task of this paper is to develop a nonlinear regression model for estimating the software size (in KLOC, kilo lines of code) of Web apps created using the CodeIgniter framework. Method: We apply the technique for constructing nonlinear regression models based on the multivariate normalizing transformations and prediction intervals. The result is three nonlinear regression models with three predictors: the total number of classes, the average number of methods per class, and the DIT (Depth of Inheritance Tree) average per class. To build these models for estimating the size of Web apps created using the CodeIgniter framework, we used three well-known normalizing transformations: two univariate transformations (the decimal logarithm and the Box-Cox transformation) and the Box-Cox four-variate transformation. Conclusions. The nonlinear regression model constructed by the Box-Cox four-variate transformation has better size prediction results than other regression models based on the univariate transformations.
{"title":"Early size estimation of web apps created using codeigniter framework by nonlinear regression models","authors":"S. Prykhodko, I. Shutko, A. Prykhodko","doi":"10.32620/reks.2022.3.06","DOIUrl":"https://doi.org/10.32620/reks.2022.3.06","url":null,"abstract":"Subject matter: Early software size estimation is one of the project managers' significant problems in evaluating app development efforts because software size is the major determinant of software project effort. Function points (FPs) and lines of code (LOC) are most commonly used as measures of size in existing software effort estimation methods and models. As is known, both these metrics have their advantages and disadvantages when used for software effort estimation. Although the FPs-based measure has the advantage over the LOC in that it does not depend on the technologies used, however, the assessment of efforts requires considering such factors (environmental factors). Considering the above factors can be ensured by appropriate models for estimating the LOC-based effort. Nowadays, many Web apps are created using PHP frameworks making the app development faster. CodeIgniter is one such powerful framework. However, there are no regression models for estimating the software size of Web apps created using the CodeIgniter framework. This requires the construction of the appropriate models. The task of this paper is to develop a nonlinear regression model for estimating the software size (in KLOC, kilo lines of code) of Web apps created using the CodeIgniter framework. Method: We apply the technique for constructing nonlinear regression models based on the multivariate normalizing transformations and prediction intervals. The result is three nonlinear regression models with three predictors: the total number of classes, the average number of methods per class, and the DIT (Depth of Inheritance Tree) average per class. To build these models for estimating the size of Web apps created using the CodeIgniter framework, we used three well-known normalizing transformations: two univariate transformations (the decimal logarithm and the Box-Cox transformation) and the Box-Cox four-variate transformation. Conclusions. The nonlinear regression model constructed by the Box-Cox four-variate transformation has better size prediction results than other regression models based on the univariate transformations.","PeriodicalId":36122,"journal":{"name":"Radioelectronic and Computer Systems","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45863218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. Chumachenko, T. Chumachenko, Nataliia Kirinovych, I. Meniailov, O. Muradyan, O. Salun
The COVID-19 pandemic has become a challenge to public health systems worldwide. As of June 2022, more than 545 million cases have been registered worldwide, more than 6.34 million of which have died. The gratuitous and bloody war launched by Russia in Ukraine has affected the public health system, including disruptions to COVID-19 vaccination plans. The use of simulation models to estimate the necessary coverage of COVID-19 vaccination in Ukraine will make it possible to rapidly change the policy to combat the pandemic in the wartime. This study aims to develop a COVID-19 vaccination model in Ukraine and to study the impact of war on this process. The study is multidisciplinary and includes a sociological study of the attitude of the population of Ukraine toward COVID-19 vaccination before the escalation of the war, the modeling of the vaccine campaign, forecasting the required number of doses administered after the start of the war, epidemiological analysis of the simulation results. This research targeted the COVID-19 epidemic process during the war. The research subjects are the methods and models of epidemic process simulation based on statistical machine learning. Sociological analysis methods were applied to achieve this goal, and an ARIMA model was developed to assess COVID-19 vaccination coverage As a result of the study, the population of Ukraine was clustered in attitude to COVID-19 vaccination. As a result of a sociological study of 437 donors and 797 medical workers, four classes were distinguished: supporters, loyalists, conformists, and skeptics. An ARIMA model was built to simulate the daily coverage of COVID-19 vaccinations. A retrospective forecast verified the model's accuracy for the period 01/25/22 - 02/23/22 in Ukraine. The forecast accuracy for 30 days was 98.79%. The model was applied to estimate the required vaccination coverage in Ukraine for the period 02/24/22 – 03/25/22. Conclusions. A multidisciplinary study made it possible to assess the adherence of the population of Ukraine to COVID-19 vaccination and develop an ARIMA model to assess the necessary COVID-19 vaccination coverage in Ukraine. The model developed is highly accurate and can be used by public health agencies to adjust vaccine policies in wartime. Given the barriers to vaccination acceptance, despite the hostilities, it is necessary to continue to perform awareness-raising work in the media, covering not only the events of the war but also setting the population on the need to receive the first and second doses of the COVID-19 vaccine for previously unvaccinated people, and a booster dose for those who have previously received two doses of the vaccine, involving opinion leaders in such works.
{"title":"Barriers of COVID-19 vaccination in Ukraine during the war: the simulation study using ARIMA model","authors":"D. Chumachenko, T. Chumachenko, Nataliia Kirinovych, I. Meniailov, O. Muradyan, O. Salun","doi":"10.32620/reks.2022.3.02","DOIUrl":"https://doi.org/10.32620/reks.2022.3.02","url":null,"abstract":"The COVID-19 pandemic has become a challenge to public health systems worldwide. As of June 2022, more than 545 million cases have been registered worldwide, more than 6.34 million of which have died. The gratuitous and bloody war launched by Russia in Ukraine has affected the public health system, including disruptions to COVID-19 vaccination plans. The use of simulation models to estimate the necessary coverage of COVID-19 vaccination in Ukraine will make it possible to rapidly change the policy to combat the pandemic in the wartime. This study aims to develop a COVID-19 vaccination model in Ukraine and to study the impact of war on this process. The study is multidisciplinary and includes a sociological study of the attitude of the population of Ukraine toward COVID-19 vaccination before the escalation of the war, the modeling of the vaccine campaign, forecasting the required number of doses administered after the start of the war, epidemiological analysis of the simulation results. This research targeted the COVID-19 epidemic process during the war. The research subjects are the methods and models of epidemic process simulation based on statistical machine learning. Sociological analysis methods were applied to achieve this goal, and an ARIMA model was developed to assess COVID-19 vaccination coverage As a result of the study, the population of Ukraine was clustered in attitude to COVID-19 vaccination. As a result of a sociological study of 437 donors and 797 medical workers, four classes were distinguished: supporters, loyalists, conformists, and skeptics. An ARIMA model was built to simulate the daily coverage of COVID-19 vaccinations. A retrospective forecast verified the model's accuracy for the period 01/25/22 - 02/23/22 in Ukraine. The forecast accuracy for 30 days was 98.79%. The model was applied to estimate the required vaccination coverage in Ukraine for the period 02/24/22 – 03/25/22. Conclusions. A multidisciplinary study made it possible to assess the adherence of the population of Ukraine to COVID-19 vaccination and develop an ARIMA model to assess the necessary COVID-19 vaccination coverage in Ukraine. The model developed is highly accurate and can be used by public health agencies to adjust vaccine policies in wartime. Given the barriers to vaccination acceptance, despite the hostilities, it is necessary to continue to perform awareness-raising work in the media, covering not only the events of the war but also setting the population on the need to receive the first and second doses of the COVID-19 vaccine for previously unvaccinated people, and a booster dose for those who have previously received two doses of the vaccine, involving opinion leaders in such works.","PeriodicalId":36122,"journal":{"name":"Radioelectronic and Computer Systems","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49202979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Accurate and up-to-date road maps are crucial for numerous applications such as urban planning, automatic vehicle navigation systems, and traffic monitoring systems. However, even in the high resolutions remote sensing images, the background and roads look similar due to the occlusion of trees and buildings, and it is difficult to accurately segment the road network from complex background images. In this research paper, an algorithm based on deep learning was proposed to segment road networks from remote sensing images. This semantic segmentation algorithm was developed with a modified UNet. Because of the lower availability of remote sensing images for semantic segmentation, the data augmentation method was used. Initially, the semantic segmentation network was trained by a large number of training samples using traditional UNet architecture. After then, the number of training samples is reduced gradually, and measures the performance of a traditional UNet model. This basic UNet model gives better results in the form of accuracy, IOU, DICE score, and visualization of the image for the 362 training samples. The idea here is to simply extract road data from remote sensing images. As a result, unlike traditional UNet, there is no need for a deeper neural network encoder-decoder structure. Hence, the number of convolutional layers in the modified UNet is lower than that in the standard UNet. Therefore, the complexity of the deep learning architecture and the training time required by the road network model was reduced. The model performance measured by the intersection over union (IOU) was 93.71% and the average segmentation time of a single image was 0.28 sec. The results showed that the modified UNet could efficiently segment road networks from remote sensing images with identical backgrounds. It can be used under various situations.
{"title":"A novel approach for semantic segmentation of automatic road network extractions from remote sensing images by modified UNet","authors":"Miral J. Patel, A. Kothari, Hasmukh P. Koringa","doi":"10.32620/reks.2022.3.12","DOIUrl":"https://doi.org/10.32620/reks.2022.3.12","url":null,"abstract":"Accurate and up-to-date road maps are crucial for numerous applications such as urban planning, automatic vehicle navigation systems, and traffic monitoring systems. However, even in the high resolutions remote sensing images, the background and roads look similar due to the occlusion of trees and buildings, and it is difficult to accurately segment the road network from complex background images. In this research paper, an algorithm based on deep learning was proposed to segment road networks from remote sensing images. This semantic segmentation algorithm was developed with a modified UNet. Because of the lower availability of remote sensing images for semantic segmentation, the data augmentation method was used. Initially, the semantic segmentation network was trained by a large number of training samples using traditional UNet architecture. After then, the number of training samples is reduced gradually, and measures the performance of a traditional UNet model. This basic UNet model gives better results in the form of accuracy, IOU, DICE score, and visualization of the image for the 362 training samples. The idea here is to simply extract road data from remote sensing images. As a result, unlike traditional UNet, there is no need for a deeper neural network encoder-decoder structure. Hence, the number of convolutional layers in the modified UNet is lower than that in the standard UNet. Therefore, the complexity of the deep learning architecture and the training time required by the road network model was reduced. The model performance measured by the intersection over union (IOU) was 93.71% and the average segmentation time of a single image was 0.28 sec. The results showed that the modified UNet could efficiently segment road networks from remote sensing images with identical backgrounds. It can be used under various situations.","PeriodicalId":36122,"journal":{"name":"Radioelectronic and Computer Systems","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49661444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Volodymyr Prymirenko, Andrii Demianiuk, R. Shevtsov, Serhii Bazilo, Petro Steshenko
The subject of the paper is the process of joint use of false aircraft targets as part of a group of combat unmanned aerial vehicles to perform tasks to destroy enemy targets. The current paper determines the optimal number of false aircraft targets in a group of combat unmanned aerial vehicles to defeat targets with the desired degree of their defeat and acceptable losses of own combat unmanned aerial vehicles. The scientific task is to improve the methodology for determining the optimal number of false aircraft targets in a group of combat unmanned aerial vehicles to defeat targets with the desired degree of defeat and acceptable losses of own combat unmanned aerial vehicles. To achieve the purpose of the research paper, the following tasks were performed: the process of joint use of false aircraft targets as part of a group of combat unmanned aerial vehicles to defeat targets with the desired degree of their defeat has been formalized; a mathematical model for determining the optimal composition of false aircraft targets as part of a group of combat unmanned aerial vehicles to minimize the losses of real aircraft during their tasks has been developed; based on the conditions of a practical example, the functioning of the improved methodology has been tested and the relevant recommendations have been substantiated. Methods. The mathematical model uses combinatorics and binomial probability distribution. The following results were obtained. An improved methodology is presented, which is multifunctional since, on the one hand, its use makes it possible to determine the required number of false aircraft targets in a group of combat unmanned aerial vehicles to defeat targets with the desired degree of their defeat and acceptable losses of own combat unmanned aerial vehicles, and on the other hand, to determine the predicted level of losses of real aircraft targets from the group when using a certain number of false aircraft targets. Conclusions. The availability of an improved methodology with ready-made calculation formulas will allow the prediction of possible results of combat use of groups of unmanned aerial vehicles based on the initial parameters and substantiate recommendations on their possible composition.
{"title":"The impact of the joint use of false aircraft targets in a group of combat unmanned aerial vehicles on the results of destruction","authors":"Volodymyr Prymirenko, Andrii Demianiuk, R. Shevtsov, Serhii Bazilo, Petro Steshenko","doi":"10.32620/reks.2022.3.10","DOIUrl":"https://doi.org/10.32620/reks.2022.3.10","url":null,"abstract":"The subject of the paper is the process of joint use of false aircraft targets as part of a group of combat unmanned aerial vehicles to perform tasks to destroy enemy targets. The current paper determines the optimal number of false aircraft targets in a group of combat unmanned aerial vehicles to defeat targets with the desired degree of their defeat and acceptable losses of own combat unmanned aerial vehicles. The scientific task is to improve the methodology for determining the optimal number of false aircraft targets in a group of combat unmanned aerial vehicles to defeat targets with the desired degree of defeat and acceptable losses of own combat unmanned aerial vehicles. To achieve the purpose of the research paper, the following tasks were performed: the process of joint use of false aircraft targets as part of a group of combat unmanned aerial vehicles to defeat targets with the desired degree of their defeat has been formalized; a mathematical model for determining the optimal composition of false aircraft targets as part of a group of combat unmanned aerial vehicles to minimize the losses of real aircraft during their tasks has been developed; based on the conditions of a practical example, the functioning of the improved methodology has been tested and the relevant recommendations have been substantiated. Methods. The mathematical model uses combinatorics and binomial probability distribution. The following results were obtained. An improved methodology is presented, which is multifunctional since, on the one hand, its use makes it possible to determine the required number of false aircraft targets in a group of combat unmanned aerial vehicles to defeat targets with the desired degree of their defeat and acceptable losses of own combat unmanned aerial vehicles, and on the other hand, to determine the predicted level of losses of real aircraft targets from the group when using a certain number of false aircraft targets. Conclusions. The availability of an improved methodology with ready-made calculation formulas will allow the prediction of possible results of combat use of groups of unmanned aerial vehicles based on the initial parameters and substantiate recommendations on their possible composition.","PeriodicalId":36122,"journal":{"name":"Radioelectronic and Computer Systems","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42604092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Modern additive technologies make it possible to create structures of variable thickness and of any shape. Thus, designers face problems of optimal design of a new type, and these are problems of topological optimization. Such problems are to determine the optimal form of the structure or the optimal distribution of material over the structure. As a rule, the criterion of optimality is the mass of the structure. However, the structure must retain its bearing capacity under a certain load. The symmetric two-shear adhesive joint of the main plate with two overlays of the same shape on both sides is the object of study in this article. The main goal of this study was to determine the optimal form of overlays with variable thicknesses under certain restrictions. The main restriction is the strength of the structure. Furthermore, additional restrictions are imposed on the minimum and maximum thickness of the overlay. Therefore, the solution to the problem is presented in the form of a set of the following tasks: building a mathematical model of the adhesive joint, building a numerical solution to the primal problem using the finite difference method, and building a genetic optimization algorithm. In the presented article, to improve the convergence of the genetic algorithm is proposed to use an island model that consists of several populations. The main feature of the proposed model of the genetic algorithm lies in the fact that on one of the "islands" mutations occur more frequently and with higher dispersion than on the other two "islands". On the one hand, this decision ensures a high rate of evolutionary selection, and on the other hand, the stability of the results is achieved. Several modeling problems are solved in this article. The main results of this research include the following: nonlinear dependence of the overlay length on the applied load was determined; restrictions on the minimum thickness of the overlay, which cause the appearance of a certain “plateau” at the edge of the overlay, the thickness of which is equal to the minimum allowable were defined.
{"title":"Topological optimization of a symmetrical adhesive joint. Island model of genetic algorithm","authors":"Sergiy Kurennov, K. Barakhov, O. Vambol","doi":"10.32620/reks.2022.3.05","DOIUrl":"https://doi.org/10.32620/reks.2022.3.05","url":null,"abstract":"Modern additive technologies make it possible to create structures of variable thickness and of any shape. Thus, designers face problems of optimal design of a new type, and these are problems of topological optimization. Such problems are to determine the optimal form of the structure or the optimal distribution of material over the structure. As a rule, the criterion of optimality is the mass of the structure. However, the structure must retain its bearing capacity under a certain load. The symmetric two-shear adhesive joint of the main plate with two overlays of the same shape on both sides is the object of study in this article. The main goal of this study was to determine the optimal form of overlays with variable thicknesses under certain restrictions. The main restriction is the strength of the structure. Furthermore, additional restrictions are imposed on the minimum and maximum thickness of the overlay. Therefore, the solution to the problem is presented in the form of a set of the following tasks: building a mathematical model of the adhesive joint, building a numerical solution to the primal problem using the finite difference method, and building a genetic optimization algorithm. In the presented article, to improve the convergence of the genetic algorithm is proposed to use an island model that consists of several populations. The main feature of the proposed model of the genetic algorithm lies in the fact that on one of the \"islands\" mutations occur more frequently and with higher dispersion than on the other two \"islands\". On the one hand, this decision ensures a high rate of evolutionary selection, and on the other hand, the stability of the results is achieved. Several modeling problems are solved in this article. The main results of this research include the following: nonlinear dependence of the overlay length on the applied load was determined; restrictions on the minimum thickness of the overlay, which cause the appearance of a certain “plateau” at the edge of the overlay, the thickness of which is equal to the minimum allowable were defined.","PeriodicalId":36122,"journal":{"name":"Radioelectronic and Computer Systems","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48239133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Kulik, K. Dergachov, Sergiy Pasichnik, D. Sokol
The object of study in this article is the formation process of a rational control of the temperature of a vortex energy separator under destabilizing influences. The subject matter of the article is the process of forming a dichotomous tree by two-digit predicates from diagnostic models a vortex energy-separator device as a rational control object when destabilizing influences appear, and its further recovery. The goal is to develop an analytical approach to the formation of digital algorithms for the rational control of cold and hot air flow temperatures of a vortex energy separator. The tasks are to study the features of the process in the vortex energy-separator device; to describe a rational control system of the vortex energy-separator device; to analyze the experimental characteristics of the vortex energy-separator device; to form linear mathematical models of the nominal mode of the vortex energy-separator device; to develop linear diagnostic models that describe the inoperable states of the vortex energy separator as a rational control object; to form logical signs of diagnosing using diagnostic models, to develop recovering algorithms for the vortex energy separator. The methods used are transfer functions, discrete state space, forming production rules, two-digit predicate equations, dichotomous trees, diagnosing and recovering the operability of dynamic objects. The following results were obtained: the vortex energy-separation process features analysis, the rational control system structure and function description, the experimental characteristics analysis, the development of mathematical models, diagnostic and recovering tool development for the emergency operation process of a vortex energy separator as a rational control object for a given destabilizing influence set. Conclusions. Scientific novelty is the development of an analytical approach to the development of rational control of the vortex separation process of the air flow under the significant influence of various kinds of destabilizing influences.
{"title":"Rational control of the temperature of vortex energy separator under destabilizing influence","authors":"A. Kulik, K. Dergachov, Sergiy Pasichnik, D. Sokol","doi":"10.32620/reks.2022.3.04","DOIUrl":"https://doi.org/10.32620/reks.2022.3.04","url":null,"abstract":"The object of study in this article is the formation process of a rational control of the temperature of a vortex energy separator under destabilizing influences. The subject matter of the article is the process of forming a dichotomous tree by two-digit predicates from diagnostic models a vortex energy-separator device as a rational control object when destabilizing influences appear, and its further recovery. The goal is to develop an analytical approach to the formation of digital algorithms for the rational control of cold and hot air flow temperatures of a vortex energy separator. The tasks are to study the features of the process in the vortex energy-separator device; to describe a rational control system of the vortex energy-separator device; to analyze the experimental characteristics of the vortex energy-separator device; to form linear mathematical models of the nominal mode of the vortex energy-separator device; to develop linear diagnostic models that describe the inoperable states of the vortex energy separator as a rational control object; to form logical signs of diagnosing using diagnostic models, to develop recovering algorithms for the vortex energy separator. The methods used are transfer functions, discrete state space, forming production rules, two-digit predicate equations, dichotomous trees, diagnosing and recovering the operability of dynamic objects. The following results were obtained: the vortex energy-separation process features analysis, the rational control system structure and function description, the experimental characteristics analysis, the development of mathematical models, diagnostic and recovering tool development for the emergency operation process of a vortex energy separator as a rational control object for a given destabilizing influence set. Conclusions. Scientific novelty is the development of an analytical approach to the development of rational control of the vortex separation process of the air flow under the significant influence of various kinds of destabilizing influences.","PeriodicalId":36122,"journal":{"name":"Radioelectronic and Computer Systems","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46799061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. Moskalenko, Natalia Fonta, O. Nikulina, M. Grinchenko, Svetlana Yershova
The subject matter of this article is the process of forming a company's development finance program. The goal is to develop the information technology to determine the company's financial condition for the financial planning subsystem of an enterprise performance management (EPM) System. The tasks are to develop a method for forming a company's development finance program as the basis for the financial planning subsystem of the EPM system; develop a methodology of determining the financial condition of the company as a component of the method; develop an information technology (IT) for determining the company’s financial condition; develop a method for forecasting financial states on the strategic period using a neural network. The following results were obtained. The method for forming a company's development finance program is implemented as the financial planning subsystem for the EPM system. A methodology for determining the financial condition of a company as a component of this method is presented in this article. Information technology for the implementation of this methodology has been developed. The components of the IT are the calculation of financial indicators based on data from financial statements for a certain period; the analysis of return on equity; the determination of the company financial stability; the determination of the financial condition in dynamics; the forecasting of the company's financial condition for the strategic period; the formation of development strategies for forecasting financial condition. The method for forecasting financial states in the strategic period was implemented using a neural network with the Temporal Fusion Transformer architecture. Conclusions. The scientific novelty of the results obtained is as follows: 1) the stages of the process of forming a company's development finance program were improved by methodology for determining the financial condition of the company, by model for determining the rational ratio of own and borrowed funds, by technology for selecting possible sources of financing development projects, by method for determining investment project financing schemes;2) methodology for determining the financial condition of the company was further developed by including a component for predicting financial indicators using a neural network; 3) the company's financial condition module for EPM System was further developed by IT implementation, which implements the assessment and forecast of the company's financial condition is carried out and the financial strategy of the company's development is formed.
{"title":"Information technology of determination the company's financial condition for the financial planning subsystem of the EPM system","authors":"V. Moskalenko, Natalia Fonta, O. Nikulina, M. Grinchenko, Svetlana Yershova","doi":"10.32620/reks.2022.2.07","DOIUrl":"https://doi.org/10.32620/reks.2022.2.07","url":null,"abstract":"The subject matter of this article is the process of forming a company's development finance program. The goal is to develop the information technology to determine the company's financial condition for the financial planning subsystem of an enterprise performance management (EPM) System. The tasks are to develop a method for forming a company's development finance program as the basis for the financial planning subsystem of the EPM system; develop a methodology of determining the financial condition of the company as a component of the method; develop an information technology (IT) for determining the company’s financial condition; develop a method for forecasting financial states on the strategic period using a neural network. The following results were obtained. The method for forming a company's development finance program is implemented as the financial planning subsystem for the EPM system. A methodology for determining the financial condition of a company as a component of this method is presented in this article. Information technology for the implementation of this methodology has been developed. The components of the IT are the calculation of financial indicators based on data from financial statements for a certain period; the analysis of return on equity; the determination of the company financial stability; the determination of the financial condition in dynamics; the forecasting of the company's financial condition for the strategic period; the formation of development strategies for forecasting financial condition. The method for forecasting financial states in the strategic period was implemented using a neural network with the Temporal Fusion Transformer architecture. Conclusions. The scientific novelty of the results obtained is as follows: 1) the stages of the process of forming a company's development finance program were improved by methodology for determining the financial condition of the company, by model for determining the rational ratio of own and borrowed funds, by technology for selecting possible sources of financing development projects, by method for determining investment project financing schemes;2) methodology for determining the financial condition of the company was further developed by including a component for predicting financial indicators using a neural network; 3) the company's financial condition module for EPM System was further developed by IT implementation, which implements the assessment and forecast of the company's financial condition is carried out and the financial strategy of the company's development is formed.","PeriodicalId":36122,"journal":{"name":"Radioelectronic and Computer Systems","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43302855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The research subject of this article is the methods of locally adaptive filtering of non-stationary signals. The goal is to develop a locally-adaptive algorithm for non-stationary noise (from the viewpoint of its time-varying variance) suppression in signals characterized by a different behavior of the informative component, with restricted apriori information about the signal model and noise variance. The tasks are to investigate the effectiveness of the proposed local-adaptive myriad filter using numerical statistical estimates of processing quality for a complex model of one-dimensional process that contains different elementary signals in various additive Gaussian noise variance variations; to investigate the effectiveness of non-stationary noise suppression for model and real signals. The methods are integral and local indicators of filter quality according to the criteria of the mean square error have been obtained using numerical simulation (via Monte Carlo analysis). The following results have been obtained: a noise- and signal-adapting myriad filter for the suppressing of non-stationary noise with significantly varying variance in signals with different behaviors of the informative component is proposed. Statistical estimates of the filter quality, evaluated by numerical simulation, show a higher efficiency of the proposed local-adaptive myriad filter in conditions of different noise levels compared to the other highly efficient locally-adaptive filters. Practically, total preservation of a signal at very low noise levels, minimal dynamical errors caused by filtering at low and middle noise levels, and more effective noise suppression at high values of noise variance are demonstrated. The analysis of output signals and plots of parameters for local adaptation and adaptable parameters confirm the high efficiency and correct operation of the investigated locally-adaptive algorithms. The high robust properties of these nonlinear filters are shown, as well as the expedience of using to spike the elimination of the previous robust Hampel filter in which the median operation is replaced by a myriad one. Examples displaying the high quality of non-stationary noise suppression in a biomedical signal of electronystagmogram are presented. Conclusions. The scientific novelty of the obtained results is the development of locally-adaptive myriad filters with time-varying noise- and signal-dependent parameters for de-noising processes with non-stationary signal behavior and noise variance. This filter does not require time for parameter adaptation and their exact adjustment, a priori knowledge of the signal model and noise variance, and can be applied in a quasi-real-time mode. The proposed algorithm of noise- and signal-adapting myriad filtering algorithm improves the quality of signal processing in difficult conditions of significant noise non-stationarity (variance variation).
{"title":"Адаптивний міріадний фільтр із шумо- та сигнально-залежним зміненням параметрів у часі","authors":"Nataliya Tulyakova, O. Trofymchuk","doi":"10.32620/reks.2022.2.17","DOIUrl":"https://doi.org/10.32620/reks.2022.2.17","url":null,"abstract":"The research subject of this article is the methods of locally adaptive filtering of non-stationary signals. The goal is to develop a locally-adaptive algorithm for non-stationary noise (from the viewpoint of its time-varying variance) suppression in signals characterized by a different behavior of the informative component, with restricted apriori information about the signal model and noise variance. The tasks are to investigate the effectiveness of the proposed local-adaptive myriad filter using numerical statistical estimates of processing quality for a complex model of one-dimensional process that contains different elementary signals in various additive Gaussian noise variance variations; to investigate the effectiveness of non-stationary noise suppression for model and real signals. The methods are integral and local indicators of filter quality according to the criteria of the mean square error have been obtained using numerical simulation (via Monte Carlo analysis). The following results have been obtained: a noise- and signal-adapting myriad filter for the suppressing of non-stationary noise with significantly varying variance in signals with different behaviors of the informative component is proposed. Statistical estimates of the filter quality, evaluated by numerical simulation, show a higher efficiency of the proposed local-adaptive myriad filter in conditions of different noise levels compared to the other highly efficient locally-adaptive filters. Practically, total preservation of a signal at very low noise levels, minimal dynamical errors caused by filtering at low and middle noise levels, and more effective noise suppression at high values of noise variance are demonstrated. The analysis of output signals and plots of parameters for local adaptation and adaptable parameters confirm the high efficiency and correct operation of the investigated locally-adaptive algorithms. The high robust properties of these nonlinear filters are shown, as well as the expedience of using to spike the elimination of the previous robust Hampel filter in which the median operation is replaced by a myriad one. Examples displaying the high quality of non-stationary noise suppression in a biomedical signal of electronystagmogram are presented. Conclusions. The scientific novelty of the obtained results is the development of locally-adaptive myriad filters with time-varying noise- and signal-dependent parameters for de-noising processes with non-stationary signal behavior and noise variance. This filter does not require time for parameter adaptation and their exact adjustment, a priori knowledge of the signal model and noise variance, and can be applied in a quasi-real-time mode. The proposed algorithm of noise- and signal-adapting myriad filtering algorithm improves the quality of signal processing in difficult conditions of significant noise non-stationarity (variance variation).","PeriodicalId":36122,"journal":{"name":"Radioelectronic and Computer Systems","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44623550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：