Pub Date : 2021-12-27DOI: 10.17212/2782-2001-2021-4-7-18
Andrey Kitenko
The paper explores the possibility of using neural networks to single out target artifacts on different types of documents. Numerous types of neural networks are often used for document processing, from text analysis to the allocation of certain areas where the desired information may be contained. However, to date, there are no perfect document processing systems that can work autonomously, compensating for human errors that may appear in the process of work due to stress, fatigue and many other reasons. In this work, the emphasis is on the search and selection of target artifacts in drawings, in conditions of a small amount of initial data. The proposed method of searching and highlighting artifacts in the image consists of two main parts, detection and semantic segmentation of the detected area. The method is based on training with a teacher on marked-up data for two convolutional neural networks. The first convolutional network is used to detect an area with an artifact, in this example YoloV4 was taken as the basis. For semantic segmentation, the U-Net architecture is used, where the basis is the pre-trained Efficientnetb0. By combining these neural networks, good results were achieved, even for the selection of certain handwritten texts, without using the specifics of building neural network models for text recognition. This method can be used to search for and highlight artifacts in large datasets, while the artifacts themselves may be different in shape, color and type, and they may be located in different places of the image, have or not have intersection with other objects.
{"title":"A method of searching and marking artifacts in images applying detection and segmentation algorithms","authors":"Andrey Kitenko","doi":"10.17212/2782-2001-2021-4-7-18","DOIUrl":"https://doi.org/10.17212/2782-2001-2021-4-7-18","url":null,"abstract":"The paper explores the possibility of using neural networks to single out target artifacts on different types of documents. Numerous types of neural networks are often used for document processing, from text analysis to the allocation of certain areas where the desired information may be contained. However, to date, there are no perfect document processing systems that can work autonomously, compensating for human errors that may appear in the process of work due to stress, fatigue and many other reasons. In this work, the emphasis is on the search and selection of target artifacts in drawings, in conditions of a small amount of initial data. The proposed method of searching and highlighting artifacts in the image consists of two main parts, detection and semantic segmentation of the detected area. The method is based on training with a teacher on marked-up data for two convolutional neural networks. The first convolutional network is used to detect an area with an artifact, in this example YoloV4 was taken as the basis. For semantic segmentation, the U-Net architecture is used, where the basis is the pre-trained Efficientnetb0. By combining these neural networks, good results were achieved, even for the selection of certain handwritten texts, without using the specifics of building neural network models for text recognition. This method can be used to search for and highlight artifacts in large datasets, while the artifacts themselves may be different in shape, color and type, and they may be located in different places of the image, have or not have intersection with other objects.","PeriodicalId":292298,"journal":{"name":"Analysis and data processing systems","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123800431","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}
Pub Date : 2021-12-27DOI: 10.17212/2782-2001-2021-4-37-48
Anastasia S. Ovchinnikova
The paper presents an approach to coupled modeling of hydrodynamic and thermal processes occurring in the oil reservoir during field development using thermal methods of enhanced oil recovery. To simulate the processes of non-isothermal multiphase flow, an approach based on implicit calculation of pressure using the finite element method and an explicit calculation of phase saturations is used. A computational scheme for calculating the temperature field is considered. This scheme makes it possible to take into account both heat transfer between phases and heat transfer of a fluid mixture and matrix-rock. In order to take into account the effect of thermal conductivity, a coefficient characterizing the rate of heat transfer between the fluid mixture and the rock is used. The proposed scheme also takes into account the effect of the temperature field on the phases flow in the field reservoir and provides for the possibility of heat sources and sinks occured due to chemical reactions or thermodynamic processes in gaseous phases. Numerical experiments were carried out on a model of a real oil field obtained as a result of history matching of well data. The model contains a large number of wells and is characterized by a high heterogeneity of the porous medium. The applicability of the considered computational scheme is demonstrated on the example of modeling hot water injection into wells crossing a formation with super-viscous oil. The efficiency of thermal methods for the development of super-viscous oil fields is shown. When hot water was injected into the reservoir, the increase in oil production was about 25 % due to a significant decrease in oil viscosity. The time spent for calculating the temperature field while simulating a multiphase flow did not exceed 6 % of the total computational time.
{"title":"A computational scheme for calculating the temperature field when oil production problems","authors":"Anastasia S. Ovchinnikova","doi":"10.17212/2782-2001-2021-4-37-48","DOIUrl":"https://doi.org/10.17212/2782-2001-2021-4-37-48","url":null,"abstract":"The paper presents an approach to coupled modeling of hydrodynamic and thermal processes occurring in the oil reservoir during field development using thermal methods of enhanced oil recovery. To simulate the processes of non-isothermal multiphase flow, an approach based on implicit calculation of pressure using the finite element method and an explicit calculation of phase saturations is used. A computational scheme for calculating the temperature field is considered. This scheme makes it possible to take into account both heat transfer between phases and heat transfer of a fluid mixture and matrix-rock. In order to take into account the effect of thermal conductivity, a coefficient characterizing the rate of heat transfer between the fluid mixture and the rock is used. The proposed scheme also takes into account the effect of the temperature field on the phases flow in the field reservoir and provides for the possibility of heat sources and sinks occured due to chemical reactions or thermodynamic processes in gaseous phases. Numerical experiments were carried out on a model of a real oil field obtained as a result of history matching of well data. The model contains a large number of wells and is characterized by a high heterogeneity of the porous medium. The applicability of the considered computational scheme is demonstrated on the example of modeling hot water injection into wells crossing a formation with super-viscous oil. The efficiency of thermal methods for the development of super-viscous oil fields is shown. When hot water was injected into the reservoir, the increase in oil production was about 25 % due to a significant decrease in oil viscosity. The time spent for calculating the temperature field while simulating a multiphase flow did not exceed 6 % of the total computational time.","PeriodicalId":292298,"journal":{"name":"Analysis and data processing systems","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134589288","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}
Pub Date : 2021-12-27DOI: 10.17212/2782-2001-2021-4-49-62
V. Telezhkin, Bekhruz B. Saidov
In this paper, we investigate the problem of improving data quality using the Kalman filter in Matlab Simulink. Recently, this filter has become one of the most common algorithms for filtering and processing data in the implementation of control systems (including automated control systems) and the creation of software systems for digital filtering from noise and interference, for example, speech signals. It is also widely used in many fields of science and technology. Due to its simplicity and efficiency, it can be found in GPS receivers, in devices for processing sensor readings for various purposes, etc. It is known that one of the important tasks that should be solved in systems for processing sensor readings is the ability to detect and filter noise. Sensor noise leads to unstable measurement data. This, of course, ultimately leads to a decrease in the accuracy and performance of the control device. One of the methods that can be used to solve the problem of optimal filtering is the development of cybernetic algorithms based on the Kalman and Wiener filters. The filtering process can be carried out in two forms, namely: hardware and software algorithms. Hardware filtering can be built electronically. However, it is less efficient as it requires additional circuitry in the system. To overcome this obstacle, you can use filtering in the form of programming algorithms in a single method. In addition to the fact that it does not require electronic hardware circuitry, the filtering performed is even more accurate because it uses a computational process. The paper analyzes the results of applying the Kalman filter to eliminate errors when measuring the coordinates of the tracked target, to obtain a "smoothed" trajectory and shows the results of the filter development process when processing an electrocardiogram. The development of the Kalman filter algorithm is based on the procedure of recursive assessment of the measured state of the research object.
{"title":"Information processing using the Kalman filter in Matlab Simulink","authors":"V. Telezhkin, Bekhruz B. Saidov","doi":"10.17212/2782-2001-2021-4-49-62","DOIUrl":"https://doi.org/10.17212/2782-2001-2021-4-49-62","url":null,"abstract":"In this paper, we investigate the problem of improving data quality using the Kalman filter in Matlab Simulink. Recently, this filter has become one of the most common algorithms for filtering and processing data in the implementation of control systems (including automated control systems) and the creation of software systems for digital filtering from noise and interference, for example, speech signals. It is also widely used in many fields of science and technology. Due to its simplicity and efficiency, it can be found in GPS receivers, in devices for processing sensor readings for various purposes, etc. It is known that one of the important tasks that should be solved in systems for processing sensor readings is the ability to detect and filter noise. Sensor noise leads to unstable measurement data. This, of course, ultimately leads to a decrease in the accuracy and performance of the control device. One of the methods that can be used to solve the problem of optimal filtering is the development of cybernetic algorithms based on the Kalman and Wiener filters. The filtering process can be carried out in two forms, namely: hardware and software algorithms. Hardware filtering can be built electronically. However, it is less efficient as it requires additional circuitry in the system. To overcome this obstacle, you can use filtering in the form of programming algorithms in a single method. In addition to the fact that it does not require electronic hardware circuitry, the filtering performed is even more accurate because it uses a computational process. The paper analyzes the results of applying the Kalman filter to eliminate errors when measuring the coordinates of the tracked target, to obtain a \"smoothed\" trajectory and shows the results of the filter development process when processing an electrocardiogram. The development of the Kalman filter algorithm is based on the procedure of recursive assessment of the measured state of the research object.","PeriodicalId":292298,"journal":{"name":"Analysis and data processing systems","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121552415","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}
Pub Date : 2021-12-27DOI: 10.17212/2782-2001-2021-4-63-72
G. Aldonin, V. V. Cherepanov
In domestic and foreign practice, a great deal of experience has been accumulated in the creation of means for monitoring the functional state of the human body. The existing complexes mainly analyze the electrocardiogram, blood pressure and a number of other physiological parameters. Diagnostics is often based on formal statistical data which are not always correct due to the nonstationarity of bioprocesses and without taking into account their physical nature. An urgent task of monitoring the state of the cardiovascular system is the creation of effective algorithms for computer technologies to process biosignals based on nonlinear dynamic models of body systems since biosystems and bioprocesses have a nonlinear nature and fractal structure. The nervous and muscular systems of the heart, the vascular and bronchial systems of the human body are examples of such structures. The connection of body systems with their organization in the form of self-similar fractal structures with scaling close to the “golden ratio” makes it possible to diagnose them topically. It is possible to obtain detailed information about the state of the human body’s bio-networks for topical diagnostics on the basis of the wavelet analysis of biosignals (the so-called wavelet-introscopy). With the help of wavelet transform, it is possible to reveal the structure of biosystems and bioprocesses, as a picture of the lines of local extrema of wavelet diagrams of biosignals. Mathematical models and software for wavelet introscopy make it possible to extract additional information from biosignals about the state of biosystems. Early detection of latent forms of diseases using wavelet introscopy can shorten the cure time and reduce the consequences of disorders of the functional state of the body (FSO), and reduce the risk of disability. Taking into account the factors of organizing the body’s biosystems in the form of self-similar fractal structures with a scaling close to the “golden ratio” makes it possible to create a technique for topical diagnostics of the most important biosystems of the human body.
{"title":"Wavelet introscopy of human organism bionets","authors":"G. Aldonin, V. V. Cherepanov","doi":"10.17212/2782-2001-2021-4-63-72","DOIUrl":"https://doi.org/10.17212/2782-2001-2021-4-63-72","url":null,"abstract":"In domestic and foreign practice, a great deal of experience has been accumulated in the creation of means for monitoring the functional state of the human body. The existing complexes mainly analyze the electrocardiogram, blood pressure and a number of other physiological parameters. Diagnostics is often based on formal statistical data which are not always correct due to the nonstationarity of bioprocesses and without taking into account their physical nature. An urgent task of monitoring the state of the cardiovascular system is the creation of effective algorithms for computer technologies to process biosignals based on nonlinear dynamic models of body systems since biosystems and bioprocesses have a nonlinear nature and fractal structure. The nervous and muscular systems of the heart, the vascular and bronchial systems of the human body are examples of such structures. The connection of body systems with their organization in the form of self-similar fractal structures with scaling close to the “golden ratio” makes it possible to diagnose them topically. It is possible to obtain detailed information about the state of the human body’s bio-networks for topical diagnostics on the basis of the wavelet analysis of biosignals (the so-called wavelet-introscopy). With the help of wavelet transform, it is possible to reveal the structure of biosystems and bioprocesses, as a picture of the lines of local extrema of wavelet diagrams of biosignals. Mathematical models and software for wavelet introscopy make it possible to extract additional information from biosignals about the state of biosystems. Early detection of latent forms of diseases using wavelet introscopy can shorten the cure time and reduce the consequences of disorders of the functional state of the body (FSO), and reduce the risk of disability. Taking into account the factors of organizing the body’s biosystems in the form of self-similar fractal structures with a scaling close to the “golden ratio” makes it possible to create a technique for topical diagnostics of the most important biosystems of the human body.","PeriodicalId":292298,"journal":{"name":"Analysis and data processing systems","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121867222","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}
Pub Date : 2021-12-27DOI: 10.17212/2782-2001-2021-4-19-36
Yulia L. Korotkova, Y. A. Mesentsev
The paper discusses the problem of optimal regulation of aircraft assignments for airline flights. Due to the fact that the activities of the airline are subject to changes caused by both external and internal environment, the planned schedule needs continuous management and control. In the event when the actual flight schedule deviates from the planned one, it is necessary to promptly make a decision on adjusting (restoring) the schedule and reassigning aircraft. Operational schedule management involves making adjustments to the current schedule from a depth of several hours to several days. The solution to the problem is to determine the unambiguous correspondence of flights and specific aircraft subject to maximizing the likelihood of meeting production targets and observing a number of restrictions. The task of managing airline schedules belongs to the class of scheduling optimization problems for parallel-sequential systems studied within the scheduling theory. It is NP-hard and requires the development of computationally efficient solution algorithms. However, the issue of choosing criteria for the optimization problem deserves special attention, since the correct choice plays an essential role in terms of assessing the effectiveness of decision-making. In the theory of decision-making, no general method for choosing the optimality criteria has been found. The definition of the target criterion depends on the expectations of the production. Within the framework of this paper, an original criterion is proposed for constructing an optimal solution to the discrete problem of managing aircraft assignments, the main idea of which is to find a balance between the duration of the schedule and the number of flights with a negative deviation from the planned schedule by assessing the level of punctuality violation risk. The paper gives a detailed concept of punctuality, describes an approach to assessing the level of risk, and also proposes an original formal formulation of the task of operational management of aircraft assignments based on the criterion of minimizing the risk of violation of flight punctuality.
{"title":"A risk-based approach to solving the problem of airline schedule operational management","authors":"Yulia L. Korotkova, Y. A. Mesentsev","doi":"10.17212/2782-2001-2021-4-19-36","DOIUrl":"https://doi.org/10.17212/2782-2001-2021-4-19-36","url":null,"abstract":"The paper discusses the problem of optimal regulation of aircraft assignments for airline flights. Due to the fact that the activities of the airline are subject to changes caused by both external and internal environment, the planned schedule needs continuous management and control. In the event when the actual flight schedule deviates from the planned one, it is necessary to promptly make a decision on adjusting (restoring) the schedule and reassigning aircraft. Operational schedule management involves making adjustments to the current schedule from a depth of several hours to several days. The solution to the problem is to determine the unambiguous correspondence of flights and specific aircraft subject to maximizing the likelihood of meeting production targets and observing a number of restrictions. The task of managing airline schedules belongs to the class of scheduling optimization problems for parallel-sequential systems studied within the scheduling theory. It is NP-hard and requires the development of computationally efficient solution algorithms. However, the issue of choosing criteria for the optimization problem deserves special attention, since the correct choice plays an essential role in terms of assessing the effectiveness of decision-making. In the theory of decision-making, no general method for choosing the optimality criteria has been found. The definition of the target criterion depends on the expectations of the production. Within the framework of this paper, an original criterion is proposed for constructing an optimal solution to the discrete problem of managing aircraft assignments, the main idea of which is to find a balance between the duration of the schedule and the number of flights with a negative deviation from the planned schedule by assessing the level of punctuality violation risk. The paper gives a detailed concept of punctuality, describes an approach to assessing the level of risk, and also proposes an original formal formulation of the task of operational management of aircraft assignments based on the criterion of minimizing the risk of violation of flight punctuality.","PeriodicalId":292298,"journal":{"name":"Analysis and data processing systems","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127783019","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}
Pub Date : 2021-09-30DOI: 10.17212/2782-2001-2021-3-53-74
M. Grif, R. Elakkiya, Alexey L. Prikhodko, M. Bakaev, Rajalakshmi E
In the paper, we consider recognition of sign languages (SL) with a particular focus on Russian and Indian SLs. The proposed recognition system includes five components: configuration, orientation, localization, movement and non-manual markers. The analysis uses methods of recognition of individual gestures and continuous sign speech for Indian and Russian sign languages (RSL). To recognize individual gestures, the RSL Dataset was developed, which includes more than 35,000 files for over 1000 signs. Each sign was performed with 5 repetitions and at least by 5 deaf native speakers of the Russian Sign Language from Siberia. To isolate epenthesis for continuous RSL, 312 sentences with 5 repetitions were selected and recorded on video. Five types of movements were distinguished, namely, "No gesture", "There is a gesture", "Initial movement", "Transitional movement", "Final movement". The markup of sentences for highlighting epenthesis was carried out on the Supervisely.ly platform. A recurrent network architecture (LSTM) was built, implemented using the TensorFlow Keras machine learning library. The accuracy of correct recognition of epenthesis was 95 %. The work on a similar dataset for the recognition of both individual gestures and continuous Indian sign language (ISL) is continuing. To recognize hand gestures, the mediapipe holistic library module was used. It contains a group of trained neural network algorithms that allow obtaining the coordinates of the key points of the body, palms and face of a person in the image. The accuracy of 85 % was achieved for the verification data. In the future, it is necessary to significantly increase the amount of labeled data. To recognize non-manual components, a number of rules have been developed for certain movements in the face. These rules include positions for the eyes, eyelids, mouth, tongue, and head tilt.
{"title":"Recognition of Russian and Indian Sign Languages Based on Machine Learning","authors":"M. Grif, R. Elakkiya, Alexey L. Prikhodko, M. Bakaev, Rajalakshmi E","doi":"10.17212/2782-2001-2021-3-53-74","DOIUrl":"https://doi.org/10.17212/2782-2001-2021-3-53-74","url":null,"abstract":"In the paper, we consider recognition of sign languages (SL) with a particular focus on Russian and Indian SLs. The proposed recognition system includes five components: configuration, orientation, localization, movement and non-manual markers. The analysis uses methods of recognition of individual gestures and continuous sign speech for Indian and Russian sign languages (RSL). To recognize individual gestures, the RSL Dataset was developed, which includes more than 35,000 files for over 1000 signs. Each sign was performed with 5 repetitions and at least by 5 deaf native speakers of the Russian Sign Language from Siberia. To isolate epenthesis for continuous RSL, 312 sentences with 5 repetitions were selected and recorded on video. Five types of movements were distinguished, namely, \"No gesture\", \"There is a gesture\", \"Initial movement\", \"Transitional movement\", \"Final movement\". The markup of sentences for highlighting epenthesis was carried out on the Supervisely.ly platform. A recurrent network architecture (LSTM) was built, implemented using the TensorFlow Keras machine learning library. The accuracy of correct recognition of epenthesis was 95 %. The work on a similar dataset for the recognition of both individual gestures and continuous Indian sign language (ISL) is continuing. To recognize hand gestures, the mediapipe holistic library module was used. It contains a group of trained neural network algorithms that allow obtaining the coordinates of the key points of the body, palms and face of a person in the image. The accuracy of 85 % was achieved for the verification data. In the future, it is necessary to significantly increase the amount of labeled data. To recognize non-manual components, a number of rules have been developed for certain movements in the face. These rules include positions for the eyes, eyelids, mouth, tongue, and head tilt.","PeriodicalId":292298,"journal":{"name":"Analysis and data processing systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115584336","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}
Pub Date : 2021-09-30DOI: 10.17212/2782-2001-2021-3-37-52
V. Voronin, A. Morozov
Today, almost everyone is faced with computer security problems in one or another way. Antivirus programs are used to control threats to the security of malicious software. Conventional methods for detecting malware are no longer effective enough; nowadays, neural networks and behavioral analysis technology have begun to be used for these purposes. Analyzing the behavior of programs is a difficult task, since there is no clear sequence of actions to accurately identify a program as malicious. In addition, such programs use measures to resist such detection, for example, noise masking the sequence of their work with meaningless actions. There is also the problem of uniquely identifying the class of malware due to the fact that malware can use similar methods, while being assigned to different classes. In this paper, it is proposed to use NLP methods, such as word embedding, and LDA in relation to the problems of analyzing malware API calls sequences in order to reveal the presence of semantic dependencies and assess the effectiveness of the application of these methods. The results obtained indicate the possibility of identifying the key features of malware behavior, which in the future will significantly improve the technology for detecting and identifying such programs.
{"title":"Technology of key feature identification in malware API calls sequences","authors":"V. Voronin, A. Morozov","doi":"10.17212/2782-2001-2021-3-37-52","DOIUrl":"https://doi.org/10.17212/2782-2001-2021-3-37-52","url":null,"abstract":"Today, almost everyone is faced with computer security problems in one or another way. Antivirus programs are used to control threats to the security of malicious software. Conventional methods for detecting malware are no longer effective enough; nowadays, neural networks and behavioral analysis technology have begun to be used for these purposes. Analyzing the behavior of programs is a difficult task, since there is no clear sequence of actions to accurately identify a program as malicious. In addition, such programs use measures to resist such detection, for example, noise masking the sequence of their work with meaningless actions. There is also the problem of uniquely identifying the class of malware due to the fact that malware can use similar methods, while being assigned to different classes. In this paper, it is proposed to use NLP methods, such as word embedding, and LDA in relation to the problems of analyzing malware API calls sequences in order to reveal the presence of semantic dependencies and assess the effectiveness of the application of these methods. The results obtained indicate the possibility of identifying the key features of malware behavior, which in the future will significantly improve the technology for detecting and identifying such programs.","PeriodicalId":292298,"journal":{"name":"Analysis and data processing systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128485258","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}
Pub Date : 2021-09-30DOI: 10.17212/2782-2001-2021-3-75-86
V. Guzhov, I. O. Marchenko, E. Trubilina, Dmitry S. Khaidukov
The method of modular arithmetic consists in operating not with a number, but with its remainders after division by some integers. In the modular number system or the number system in the residual classes, a multi-bit integer in the positional number system is represented as a sequence of several positional numbers. These numbers are the remainders (residues) of dividing the original number into some modules that are mutually prime integers. The advantage of the modular representation is that it is very simple to perform addition, subtraction and multiplication operations. In parallel execution of operations, the use of modular arithmetic can significantly reduce the computation time. However, there are drawbacks to modular representation that limit its use. These include a slow conversion of numbers from modular to positional representation; the complexity of comparing numbers in modular representation; the difficulty in performing the division operation; and the difficulty of determining the presence of an overflow. The use of modular arithmetic is justified if there are fast algorithms for calculating a number from a set of remainders. This article describes a fast algorithm for converting numbers from modular representation to positional representation based on a geometric approach. The review is carried out for the case of a comparison system with two modules. It is also shown that as a result of increasing numbers in positional calculus, they successively change in a spiral on the surface of a two-dimensional torus. Based on this approach, a fast algorithm for comparing numbers and an algorithm for detecting an overflow during addition and multiplication of numbers in modular representation were developed. Consideration for the multidimensional case is possible when analyzing a multidimensional torus and studying the behavior of the turns on its surface.
{"title":"Comparison of numbers and analysis of overflow in modular arithmetic","authors":"V. Guzhov, I. O. Marchenko, E. Trubilina, Dmitry S. Khaidukov","doi":"10.17212/2782-2001-2021-3-75-86","DOIUrl":"https://doi.org/10.17212/2782-2001-2021-3-75-86","url":null,"abstract":"The method of modular arithmetic consists in operating not with a number, but with its remainders after division by some integers. In the modular number system or the number system in the residual classes, a multi-bit integer in the positional number system is represented as a sequence of several positional numbers. These numbers are the remainders (residues) of dividing the original number into some modules that are mutually prime integers. The advantage of the modular representation is that it is very simple to perform addition, subtraction and multiplication operations. In parallel execution of operations, the use of modular arithmetic can significantly reduce the computation time. However, there are drawbacks to modular representation that limit its use. These include a slow conversion of numbers from modular to positional representation; the complexity of comparing numbers in modular representation; the difficulty in performing the division operation; and the difficulty of determining the presence of an overflow. The use of modular arithmetic is justified if there are fast algorithms for calculating a number from a set of remainders. This article describes a fast algorithm for converting numbers from modular representation to positional representation based on a geometric approach. The review is carried out for the case of a comparison system with two modules. It is also shown that as a result of increasing numbers in positional calculus, they successively change in a spiral on the surface of a two-dimensional torus. Based on this approach, a fast algorithm for comparing numbers and an algorithm for detecting an overflow during addition and multiplication of numbers in modular representation were developed. Consideration for the multidimensional case is possible when analyzing a multidimensional torus and studying the behavior of the turns on its surface.","PeriodicalId":292298,"journal":{"name":"Analysis and data processing systems","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134029865","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}
Pub Date : 2021-09-30DOI: 10.17212/2782-2001-2021-3-87-98
I.L. Zhbanov, V. Zhbanova
The paper presents a method for encrypting geo-images based on the reorganization of the internal structure of the filter. Methods for digital image filtering in the MATLAB environment are taken as a basis. The essence of encryption is to control the aliasing of noise and the kernel of smearing. Knowing these values will allow the addressee to recover the transmitted cards with minimal interference, which will be unattainable for the data interceptor. Under conditions of unfavorable factors, conditions sometimes arise that lead to the loss of information content of images and, as a consequence, damage to information. Therefore, the development of methods to minimize their influence is an urgent task of the study. Thus, one of the approaches to the construction of spatial filters with a controlled structure is proposed for the selection of contrasting images in noises of different intensities. The procedure for converting any spatial filter from an initial display to a form that allows you to control its internal state is described. The obtained results of the original and transformed images make it possible to draw conclusions about the possibility of practical application of the proposed invariant spatial filter in the blocks for analyzing the original image. The method can be used to transfer photo, video messages and text information between consumers using data transmission systems for any purpose. Due to the factorial dependence, it is very problematic for information interceptors to find the required resulting position of all image encryption parameters (sizes, type of the distortion function, regularization parameters α and σ) for information interceptors, since the computational costs are not commensurate with the capabilities of modern computers. This can be used to transfer photo, video messages and text information between consumers using data transmission systems for any purpose, especially when transferring cartographic information.
{"title":"Method for encryption of cartographic images on the basis of internal reorganization of the digital filter structure","authors":"I.L. Zhbanov, V. Zhbanova","doi":"10.17212/2782-2001-2021-3-87-98","DOIUrl":"https://doi.org/10.17212/2782-2001-2021-3-87-98","url":null,"abstract":"The paper presents a method for encrypting geo-images based on the reorganization of the internal structure of the filter. Methods for digital image filtering in the MATLAB environment are taken as a basis. The essence of encryption is to control the aliasing of noise and the kernel of smearing. Knowing these values will allow the addressee to recover the transmitted cards with minimal interference, which will be unattainable for the data interceptor. Under conditions of unfavorable factors, conditions sometimes arise that lead to the loss of information content of images and, as a consequence, damage to information. Therefore, the development of methods to minimize their influence is an urgent task of the study. Thus, one of the approaches to the construction of spatial filters with a controlled structure is proposed for the selection of contrasting images in noises of different intensities. The procedure for converting any spatial filter from an initial display to a form that allows you to control its internal state is described. The obtained results of the original and transformed images make it possible to draw conclusions about the possibility of practical application of the proposed invariant spatial filter in the blocks for analyzing the original image. The method can be used to transfer photo, video messages and text information between consumers using data transmission systems for any purpose. Due to the factorial dependence, it is very problematic for information interceptors to find the required resulting position of all image encryption parameters (sizes, type of the distortion function, regularization parameters α and σ) for information interceptors, since the computational costs are not commensurate with the capabilities of modern computers. This can be used to transfer photo, video messages and text information between consumers using data transmission systems for any purpose, especially when transferring cartographic information.","PeriodicalId":292298,"journal":{"name":"Analysis and data processing systems","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132712217","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}
Pub Date : 2021-09-30DOI: 10.17212/2782-2001-2021-3-99-114
A. A. Zuenko, R. Makedonov, Yurii A. Oleynik
A method of intelligent search for accurate solutions to the planning of open-pit mining has been developed. The method is implemented within the framework of the Constraint Programming Paradigm that allows us to process heterogeneous qualitative and quantitative constraints (in particular, economic, technological, etc.) simultaneously, as well as to maintain the model of subject domain being developed which is open to adding new constraints or deleting existing constraints. Various constraints can be added to the model, including those for which it is difficult to find a suitable analytical expression. In contrast to existing methods of local search the proposed method systematically explores the search space. The method allows us to find a global optimum in large dimensional spaces that describe practically significant problems arising in production. Currently, to solve this problem, the methods of integer linear programming are widely used. But its fundamental disadvantage is the need to represent all the constraints in the form of linear equalities and inequalities. However, in practice, some combinatorial optimization problems cannot be linearized and solved using traditional methods of mathematical programming. The developed method is illustrated by the example of a three-dimensional problem of finding the position of an intermediate pit wall by the processing periods taking into account the specified performance for mineral and overburden rocks and the objective profit function taking into account discounting. The types of constraints necessary for modeling the problem under consideration are identified. The possibility of applying the existing inference procedures on constraints is considered for these types. The method proposed makes it possible to obtain accurate solutions due to the intellectualization of the solution process by using highly efficient algorithms of reducing the search space for each type of constraints and specialized heuristics for pruning unpromising alternatives in the search tree.
{"title":"Intelligent search for accurate solutions to the planning open-pit mining","authors":"A. A. Zuenko, R. Makedonov, Yurii A. Oleynik","doi":"10.17212/2782-2001-2021-3-99-114","DOIUrl":"https://doi.org/10.17212/2782-2001-2021-3-99-114","url":null,"abstract":"A method of intelligent search for accurate solutions to the planning of open-pit mining has been developed. The method is implemented within the framework of the Constraint Programming Paradigm that allows us to process heterogeneous qualitative and quantitative constraints (in particular, economic, technological, etc.) simultaneously, as well as to maintain the model of subject domain being developed which is open to adding new constraints or deleting existing constraints. Various constraints can be added to the model, including those for which it is difficult to find a suitable analytical expression. In contrast to existing methods of local search the proposed method systematically explores the search space. The method allows us to find a global optimum in large dimensional spaces that describe practically significant problems arising in production. Currently, to solve this problem, the methods of integer linear programming are widely used. But its fundamental disadvantage is the need to represent all the constraints in the form of linear equalities and inequalities. However, in practice, some combinatorial optimization problems cannot be linearized and solved using traditional methods of mathematical programming. The developed method is illustrated by the example of a three-dimensional problem of finding the position of an intermediate pit wall by the processing periods taking into account the specified performance for mineral and overburden rocks and the objective profit function taking into account discounting. The types of constraints necessary for modeling the problem under consideration are identified. The possibility of applying the existing inference procedures on constraints is considered for these types. The method proposed makes it possible to obtain accurate solutions due to the intellectualization of the solution process by using highly efficient algorithms of reducing the search space for each type of constraints and specialized heuristics for pruning unpromising alternatives in the search tree.","PeriodicalId":292298,"journal":{"name":"Analysis and data processing systems","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128909984","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：