Intellekt. Sist. Proizv.最新文献

{"title":"Exploiting Deep Learning Techniques for the Verification of Handwritten Signatures","authors":"F. B. Albasu, M. A. Al Akkad","doi":"10.22213/2410-9304-2023-3-27-39","DOIUrl":"https://doi.org/10.22213/2410-9304-2023-3-27-39","url":null,"abstract":"Biometric featuresare common measures of identity verification where signaturesarethe most used type. The digital technology has given birth to new ways of biometric identification, such as fingerprints, iris and face recognition,while dealing with handwritten signatures is still a challenging task, because handwritten signatures are more prone to forgery than other means of verification due to issues like computer error, insufficient datasets, and loss of information. This work aims to develop a system that takes a signature image as its input and determines whether the signature is genuine written by its author or forged by another individual. The system is based on a neural network algorithm called Convolutional Siamese Neural Networks, which is used for deep learning and computer vision as well as other machine learning tasks such as natural language processing and digital signal processing.A Contrastive Loss function which compares the Euclidean distance of the output feature vectors is used, and a writer-independent model is used for training and image classification. This work’s objective is toenhance the precision of signature verification and take it as a base for future work on signature verification and use it in user identification, fraud detection and prevention, and forensic investigation applications. The system can be applied in banking, government and private organizations, and forensic investigation for identity and document verification, impersonation and fraud detection and prevention, crime and judicial investigation, and passport verification","PeriodicalId":238017,"journal":{"name":"Intellekt. Sist. Proizv.","volume":"263 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139321741","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}

{"title":"Applicability Evaluation of Natural Gas State Equations at Low Temperatures","authors":"R. I. Ganiev, D. Y. Kutovoy, V. A. Fafurin, M. Shustrova, V. B. Yavkin","doi":"10.22213/2410-9304-2023-3-4-10","DOIUrl":"https://doi.org/10.22213/2410-9304-2023-3-4-10","url":null,"abstract":"The paper analyzes the possibility of operating range expanding of natural gas state equations for low temperatures. The state equations of natural gas and methods of estimating the compressibility factor, entrenched in modern national and international standards, were analyzed. It has been shown that the range of their applicability is limited to a temperature value of 250 K, however, these temperature limitations is not restricted bystate equations directly butstipulated by the lack of reliable data about natural gas compressibility factor values at temperatures below 250 K and methods for complementary errorcalculation that may arise. The results of comparison of values of natural gas compressibility factor as a function of temperature at pressure of 1.3 and 6 MPa calculated by means of the most widely used state equations are presented. It was found that the results of the calculation according to the considered methods have satisfactory convergence within the range of 220 K, that generally confirms the applicability of modern state equations for low temperatures. In its turn, the effect of assumptions applied nowadays to definegas volume flow rateon flow metering error showed that application of substitutive compressibility values may result in significant complementary systematic error. This indicates the practicability of expanding the database of compressibility factor values for natural gas for low temperatures, as well as developmentof a standard to assess the value of the corresponding complementary error.","PeriodicalId":238017,"journal":{"name":"Intellekt. Sist. Proizv.","volume":"28 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139321311","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}

{"title":"Improving the Efficiency of the Organization Based on the Automation Criterion","authors":"M. I. Grachev","doi":"10.22213/2410-9304-2023-3-144-150","DOIUrl":"https://doi.org/10.22213/2410-9304-2023-3-144-150","url":null,"abstract":"The modern development of information technologies involves their introduction into the technological processes of enterprises and organizations. At the same time, the head of an enterprise or organization is faced with a stream of problems arising in the work of the system he manages, must make timely decisions to identify the flow of problems arising in the system, identify them and neutralize them as soon as possible, for this he needs to have an analytical dynamic solution model. The published literature currently considers models based on the analysis. Consideration of the model on the basis of a natural-scientific approach will allow you to build a model adequate to the situation under consideration, which will bring results. In this study, an analytical dynamic decision model for a decision maker (LPR) has been developed. Formed on the basis of the synthesis process, the transformation of a management decision into a solution model. The solution model will depend on the basic components of the system under consideration for the occurrence of a flow of problems, identification of a flow of problems and neutralization of a flow of problems. The resulting synthesis indicator of the implementation of the management solution allows you to identify the flow of problems in the managed system and neutralize it, as well as to obtain characteristics about the operation of the managed system. By setting the required indicator of the effectiveness of the implementation of a management decision and solving the inverse problem, the manager can obtain the necessary characteristics of the system to guarantee the achievement of the goal of the activity. As a result, the manager receives the automation criterion and, with the help of the resources available to him, adjusts the work of the organization to the required level of the indicator. The automation criterion obtained in the work will be the rule by which the automation of the enterprise takes place, which will allow solving important tasks for the LPR and timely counteract emerging problems in the management system.","PeriodicalId":238017,"journal":{"name":"Intellekt. Sist. Proizv.","volume":"38 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139321651","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}

{"title":"Temperature Field Modelas a Factor to Improve a Horizontal Ground Heat Exchanger of a Heat Pump System: Review of Scientific Approaches and the Content of the Analytical Model","authors":"A. V. Shchenyatsky, K. S. Shatalov, O. M. Shatalova","doi":"10.22213/2410-9304-2023-3-132-143","DOIUrl":"https://doi.org/10.22213/2410-9304-2023-3-132-143","url":null,"abstract":"The article is devoted to the research of issues related to the organization of control systems for heat pump installations (HPS). HPS is used to use low-potential energy of the environment in the heat supply of buildings. HPS with horizontal ground heat exchangers (HGHE) are of great importance for improving energy efficiency. The efficiency and reliability of HPS with HGHE strongly depends on the state of the soil temperature field. A large number of scientific publications are devoted to modeling soil temperature fields forHGHEparameterdetermination; a significant part of them is devoted to the study of vertical ground heat exchangers. Scientific developments presented in foreign publications on modeling the temperature field of the HGHE location environment are focused on the use of HPS in the cold supply mode and/or in the heat supply mode under conditions of a slight decrease in temperature, which excludes soil freezing. The aim of the study was to apply the existing methods of the analytical theory of thermal conductivity to develop a soil-environment TP model for the placement of a HGHE HPS; the developed model is intended for engineering calculations of the main design HGHEparameters; the model is also applicable to determine the annual specific heat flow as an important parameter in the optimal control system of the HPI. The development of the model is based on the condition of a two-element structure of the soil massif: under the HGHE and above the HGHE; the target parameter is the temperature of the soil mass, depending on the coordinate and time, disclosed through the indicator 'relative temperature rise'; in accordance with the provisions of the thermal conductivitytheory, the relative excess temperature is given for the cases of a semi-infinite body (soil mass under the HGHE) and a slab (soil mass above the HGHE). The proposed model is implemented on the example of two constituent entities of the Russian Federation. The results obtained made it possible to determine the minimum guaranteed possibility of using HPS for heat supply in these climatic conditions. The model presented in the article can be used as a context for further studies of the main parameters of HGHE HPS operation and optimization of HPS operation modes.","PeriodicalId":238017,"journal":{"name":"Intellekt. Sist. Proizv.","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139321586","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}

{"title":"Comparison of the Effectiveness of Yolov5 and yolov8 Algorithms for Detecting Human Personal Protective Equipment","authors":"S. A. Filichkin, S. V. Vologdin","doi":"10.22213/2410-9304-2023-3-124-131","DOIUrl":"https://doi.org/10.22213/2410-9304-2023-3-124-131","url":null,"abstract":"The article deals with the comparative analysis of different architectures of convolutional neural networks of YOLO class: YOLOv5 and YOLOv8. Neural network was trained on a dataset consisting of more than 2,200 marked digital images. Detection and recognition of 8 classes of personal protective equipment such as medical masks, gloves, helmets, goggles, uniforms and others was performed. To evaluate the efficiency of the object detection algorithms such characteristics as accuracy metrics, learning time and memory size of the neural networks were used. The research confirms the high efficiency and accuracy of the YOLO algorithms in the detection and recognition of objects in digital still and video images. The research shows that the average accuracy of mAP object detection in YOLOv8 is 3% higher than in YOLOv5, while the performance in the new algorithm has increased by more than 50% compared with the earlier version of the neural network. The results obtained can be used to improve the object detection system in various fields, such as the automotive industry, medical and scientific research, the security field, and etc. Based on the results of the experiment, conclusions were made regarding the selection of an algorithm for the detection of human personal protective equipment. Further research in this area may be based on expanding the volume of training datasets to improve the accuracy of object recognition and evaluate the performance of algorithms on large amounts of data. Further research is planned in the area of optimizing the architecture of convolutional neural networks to improve the efficiency, speed and accuracy of object detection in digital images.","PeriodicalId":238017,"journal":{"name":"Intellekt. Sist. Proizv.","volume":"215 3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139321463","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}

{"title":"Modeling and Management of Hybrid System Photovoltaic-FC-Ultracapacitors Power Systems","authors":"H. A. Issa, Layth Mohammed Abd Ali, M. N. Al-Maliki, B. Yakimovich, V. Kuvshinov","doi":"10.22213/2410-9304-2023-3-82-94","DOIUrl":"https://doi.org/10.22213/2410-9304-2023-3-82-94","url":null,"abstract":"This study shows an improved DC microgrid power management technique. The value of utilizing renewable energy has long been debatable, and this article suggests a typical DC microgrid because of the advantages it has over AC technology. A solar cell (PV), fuel cell (FC) and storage component - an ultracapacitor (UC)-make up the standard microgrid. The most important goal of the paper is to optimize the management strategy for the bus voltage with arranged power-sharing between these types of renewable energy that are used here. For variable solar irradiance and various loading conditions, the proposed management seeks to deliver high-quality energy to the load while taking into consideration the FC state. The ultracapacitor was prepared to furnish the transient period due to the FC's slow dynamics. To maintain the DC bus voltage steady in the face of load variations, a management algorithm is put into practice. To generate the references, the management controller relies on a differential flatness method. The electricity from the ultracapacitor controls the DC bus. Earlier studies showed that the circuit of the fuel cell was integrated with a standalone photovoltaic system and discovered that the fuel cell doesn't have the same properties. In the current research, observations were made on power quality elements like voltage, current, and power for energy storage systems. With several self-definition elements of the photovoltaic, fuel cell, and ultracapacitor, along with their parameters, simulation is used as the study method medium. The outcome demonstrates that since the ultracapacitor serves as the primary storage, the fuel cell integration has little impact on it, and only small changes in voltage and current were observed. Due to the fuel cell integration characteristic of providing the system a major perturbation, most perturbation from the system had been absorbed while in an ultracapacitor","PeriodicalId":238017,"journal":{"name":"Intellekt. Sist. Proizv.","volume":"11 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139321682","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}

{"title":"Digital Twin is an Effective Tool for Digital Transformation of Industrial Enterprises","authors":"N. L. Taranukha, S.V. Semenova, S. N. Pankov","doi":"10.22213/2410-9304-2023-3-11-26","DOIUrl":"https://doi.org/10.22213/2410-9304-2023-3-11-26","url":null,"abstract":"The article presents the results of a study of digital transformation processes taking place on scientific and industrial enterprises using digital twin technology. The degree of introduction of digital technologies and the level of labor productivity in the developed countries and in Russia were considered. The concept, definition, properties and characteristics of digital twin technology were studied. The applied methods of digital design and modeling in the digital twintechnology were investigated. The author analyzes the features of creation, functionality, and the advantages of digital twin technology at various stages of the object's life cycle - during design, production and operation. Practical examples of digital twins application in the domestic industry are given: the design of a premium-class car of the 'Tuple' project, the optimization of technological grinding operations of product manufacturing, the introduction of a predictive prognostic system and monitoring of modern high-tech equipment of the combined-cycle unit of the Izhevsk CHP-1 PSU for monitoring the operational condition, reliable forecasting of technological processes, protection from incidents and accidents. The application of digital twin technology as a training complex to train the operational personnel of industrial facilities based on modeling of rarely encountered and critically dangerous operating modes of industrial facilities is investigated. The Russian market of digital design and modeling is studied and key leaders were identified. The top digital technologies to achieve technological leadership of domestic companies are summarized. As a result of the research, the key capabilities of digital twin technology and barriers constraining the processes of full-scale digital transformation of scientific and industrial enterprises are identified. Recommendations for the successful implementation and development of digital twin technology are proposed. The motivating factors of state support for the digital transformation of domestic business are summarized.","PeriodicalId":238017,"journal":{"name":"Intellekt. Sist. Proizv.","volume":"27 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139321582","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}

{"title":"The Principles of Modelling Causal Relationships in Financial Time Series on the Example of Stock Indices","authors":"N.R. Sandu, R.V. Faizullin","doi":"10.22213/2410-9304-2023-3-105-114","DOIUrl":"https://doi.org/10.22213/2410-9304-2023-3-105-114","url":null,"abstract":"In the article, the authors consider the issues of modeling causal relationships using the example of financial time series. Many endogenous indicators with tens and hundreds of feedbacks characterise any complex dynamic system. The links between the elements of the system determine the impact on the result of the system through a variety of parameters that can lead to a distortion of the effect of managerial influence and, as a result, to a distortion of the system's efficiency as a whole. Modelling is an effective tool for determining the considered system parameters under the influence of external forces and restrictions on it.In the activity of the control system, the analytical tools of mathematical modelling based on the developed modelallow to see how the system will change over time and what factors have the most significant impact on it. The system is changeable in time, which causes the difference between the initial state and the state at a certain point. That is explained by causal relationships between the elements of the systems and the level of influence of external factors, which can be referred to as economic or market ones. The latter, in turn, can be analyzed and, as a result, predicted using mathematical methods. Speaking of external factors, many of them are not amenable to precise analysis, and examples of these are natural and ecological ones.In this article, the authors define the principles of modelling causal relationships in financial time series using the example of stock indices. In the course of the study, the unsteadiness of time series was verified by Dickey-Fuller tests, as well as using the KPSS test solution, which confirmed the unsteadiness of stock indices in the selected time period. The calculations were carried out using the modern statistical package Eviews.As a consequence, the relevance of this article is based on the search for an answer to the question of stationary financial time series.","PeriodicalId":238017,"journal":{"name":"Intellekt. Sist. Proizv.","volume":"56 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139321683","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}

{"title":"Methodological Aspects of Local Natural and Technical System Assessment Based on the Results of Environmental Monitoring","authors":"M. Gorokhov, M. A. Korepanov, P. M. Kurguzkin","doi":"10.22213/2410-9304-2023-3-54-61","DOIUrl":"https://doi.org/10.22213/2410-9304-2023-3-54-61","url":null,"abstract":"The concept of a natural-technical system is considered as a set of man-made and natural objects located on a single territory is considered. The environmental safety of the natural and technical system is ensured by limiting the negative impact on the environment from a technogenic object. It is noted that the regulation of the negative impact is necessary but not sufficient condition for environmental safety, since it is primarily focused on the implementation of sanitary and hygienic standards in relation to the people’s living or working conditions on the territory of a natural and technical system. The use of sanitary and hygienic maximum allowable concentrations in assessing the transformation of environmental objects is not very informative. It is noted that in the regular functioning conditions of a man-made object, the information basis for assessing negative changes in the environment is the results of environmental monitoring. Environmental monitoring systems are developed mostly for highly hazardous production facilities in terms of organizing the obtaining quantitative data on environmental pollution. The issues of quantitative assessment of the ecological state of the territory have not been adequately considered. The indicators used in the form of aggregated convolutional indices are still focused on sanitary and hygienic standards. In addition, their information content is reduced due to the cross-correlation of indicators used in the calculation in the form of pollutant concentrations. It is noted that objects of flora and fauna are more sensitive to negative impacts, and therefore, along with the quantitative chemical analysis of the pollution of the territory, monitoring of the biotic component of the environment is carried out. At the same time, biomonitoring data are considered as independent results. The relationship between general desirability function in assessing the state of biocenoses and other characteristics of the territory, including its pollution, is usually not studied, which also reduces their informational value. Based on the analysis of the considered materials, it was concluded that for an informative assessment and forecast of the ecological state of the natural and technical system, the development of integral indices of the biotic and abiotic components of the environment in their relationship is required.","PeriodicalId":238017,"journal":{"name":"Intellekt. Sist. Proizv.","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139321749","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}

{"title":"Interpretation Algorithm of Linear and Non-elementary Linear Regression Models Under Multicollinearity Conditions","authors":"M.P. Bazilevski","doi":"10.22213/2410-9304-2023-3-40-47","DOIUrl":"https://doi.org/10.22213/2410-9304-2023-3-40-47","url":null,"abstract":"When constructing machine learning models, more and more researchers come to understanding that in addition to the accuracy of the model, its interpretability is also important, that means the degree of understandability to a person. Currently, a new field is being formed in science - interpretable machine learning. This article is devoted to the study of linear regression models interpretation questions. Traditionally, linear regressions are interpreted in terms of weak correlation of explanatory variables. In this case, according to a well-known pattern, it is possible to explain the influence of each input variable on the output variable. Often the explanatory variables are highly correlated with each other. In such a situation, it is recommended to exclude strongly correlated variables, that leads, firstly, to a decrease in the model quality, and secondly, to integrity loss of the study and the interpretation of a process or phenomenon under study. In this paper, we propose an algorithm for interpreting a linear regression constructed for any degree of explanatory variablecorrelation. The algorithm gives the traditional interpretation of linear regression with weak correlation of all explanatory variables, while in case of strong correlation, as it follows from the theorem proved in the article, regression interpretation with several variables is reduced to interpreting an equation with one variable, without losing information about the relationships between pairs of explanatory variables. The algorithm can be used not only for simple linear regressions, but also for non-elementary ones, containing, in addition to explanatory variables, their pairs transformed by means of binary operations min and max. The operation of the algorithm is demonstrated on specific examples.","PeriodicalId":238017,"journal":{"name":"Intellekt. Sist. Proizv.","volume":"72 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139321508","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}