Pub Date : 2022-12-28DOI: 10.31649/1681-7893-2022-43-1-43-52
N. Zabolotna, V. Sholota
A method and decision support subsystem based on the principles of fuzzy logic for Mueller-matrix polarization diagnostics of biological tissues have been developed. On the basis of statistical, correlation and spectral analysis of invariant Muller-matrix images of biological tissues and their superpositions, informative signs of diagnosis are determined. Mathematical models of functions belonging to the "normal" and "pathology" states of the studied samples for the decisive rule in the system have been developed.
{"title":"Method and Decision Support Subsystem for Mueller-Matrix Laser Polarization Diagnosis of Biological Tissues","authors":"N. Zabolotna, V. Sholota","doi":"10.31649/1681-7893-2022-43-1-43-52","DOIUrl":"https://doi.org/10.31649/1681-7893-2022-43-1-43-52","url":null,"abstract":"A method and decision support subsystem based on the principles of fuzzy logic for Mueller-matrix polarization diagnostics of biological tissues have been developed. On the basis of statistical, correlation and spectral analysis of invariant Muller-matrix images of biological tissues and their superpositions, informative signs of diagnosis are determined. Mathematical models of functions belonging to the \"normal\" and \"pathology\" states of the studied samples for the decisive rule in the system have been developed.","PeriodicalId":142101,"journal":{"name":"Optoelectronic information-power technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130046975","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 : 2022-12-28DOI: 10.31649/1681-7893-2022-43-1-94-101
A.G. Gergelezhyu, M. Talakh, V. Dvorzhak, O. Ushenko
Based on the study of approaches and techniques for assessing the state of vegetation, an automated information system has been developed. It allows to perform vegetation indices’ monitoring of the territory on the basis of satellite images. The automation of their handling with the binding of temperature data is carried out. The program gives the ability to visualize the dynamics of vegetation indices and temperature and to evaluate existing connections and type of connections between the investigated factors.
{"title":"Automated System for Monitoring the State of Vegetation Cover Based on Satellite Images Recognition","authors":"A.G. Gergelezhyu, M. Talakh, V. Dvorzhak, O. Ushenko","doi":"10.31649/1681-7893-2022-43-1-94-101","DOIUrl":"https://doi.org/10.31649/1681-7893-2022-43-1-94-101","url":null,"abstract":"Based on the study of approaches and techniques for assessing the state of vegetation, an automated information system has been developed. It allows to perform vegetation indices’ monitoring of the territory on the basis of satellite images. The automation of their handling with the binding of temperature data is carried out. The program gives the ability to visualize the dynamics of vegetation indices and temperature and to evaluate existing connections and type of connections between the investigated factors.","PeriodicalId":142101,"journal":{"name":"Optoelectronic information-power technologies","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124674286","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 : 2022-12-28DOI: 10.31649/1681-7893-2022-43-1-24-35
Y. Tomka, M. Talakh, V. Dvorzhak, O. Ushenko
The most common approaches to assessing the quality of training neural networks in the context of the problem of "small training sets" are analyzed. A review of the code implementation of the most universal approaches and ways of extending training/testing samples is carried out. The logic of the work of STN-module is analyzed. It can be inserted into existing convolutional architectures, giving neural networks the ability to actively spatially transform feature maps, conditional on the feature map itself, without any extra training supervision or modification to the optimization process.
{"title":"Practical Aspects of Forming Training/Test Samples for Convolutional Neural Networks","authors":"Y. Tomka, M. Talakh, V. Dvorzhak, O. Ushenko","doi":"10.31649/1681-7893-2022-43-1-24-35","DOIUrl":"https://doi.org/10.31649/1681-7893-2022-43-1-24-35","url":null,"abstract":"The most common approaches to assessing the quality of training neural networks in the context of the problem of \"small training sets\" are analyzed. A review of the code implementation of the most universal approaches and ways of extending training/testing samples is carried out. The logic of the work of STN-module is analyzed. It can be inserted into existing convolutional architectures, giving neural networks the ability to actively spatially transform feature maps, conditional on the feature map itself, without any extra training supervision or modification to the optimization process.","PeriodicalId":142101,"journal":{"name":"Optoelectronic information-power technologies","volume":"161 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133937427","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 : 2022-12-28DOI: 10.31649/1681-7893-2022-43-1-82-93
S. Pavlov, W. Wójcik, R. Holyaka, O. D. Azarov, S. V. Bohomolov, Yang Longyin
The paper analyzed the characteristics of microelectronic flow sensors, which made it possible to draw a number of important conclusions, namely: modern microelectronic thermal flow sensors, and in particular biomedical sensors, are characterized by a significant variety of principles of signal formation - from elementary linear converters based on one sensitive element to non-linear ones ( generation, time-dependent) converters based on matrices of functionally integrated elements. The problem of energy consumption of thermal flow sensors remains relevant. This is especially characteristic when powering destination sensors from autonomous, i.e., small-sized, low-power, low-voltage electrochemical cells. A decrease in energy consumption (power and heating temperature) leads to the parasitic effect of signal line resistances and, as a result, to the deterioration of functional characteristics, in particular, to a decrease in the accuracy of flow rate measurement.
{"title":"Analysis of development state of the thermal flow sensors of general, biomedical and ecological designation","authors":"S. Pavlov, W. Wójcik, R. Holyaka, O. D. Azarov, S. V. Bohomolov, Yang Longyin","doi":"10.31649/1681-7893-2022-43-1-82-93","DOIUrl":"https://doi.org/10.31649/1681-7893-2022-43-1-82-93","url":null,"abstract":"The paper analyzed the characteristics of microelectronic flow sensors, which made it possible to draw a number of important conclusions, namely: modern microelectronic thermal flow sensors, and in particular biomedical sensors, are characterized by a significant variety of principles of signal formation - from elementary linear converters based on one sensitive element to non-linear ones ( generation, time-dependent) converters based on matrices of functionally integrated elements. The problem of energy consumption of thermal flow sensors remains relevant. This is especially characteristic when powering destination sensors from autonomous, i.e., small-sized, low-power, low-voltage electrochemical cells. A decrease in energy consumption (power and heating temperature) leads to the parasitic effect of signal line resistances and, as a result, to the deterioration of functional characteristics, in particular, to a decrease in the accuracy of flow rate measurement.","PeriodicalId":142101,"journal":{"name":"Optoelectronic information-power technologies","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134243701","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 : 2022-12-28DOI: 10.31649/1681-7893-2022-43-1-19-23
M.L. Kovalchuk, P.I. Ushtan, Y. Ushenko, I. Soltys
The advantages and disadvantages of learning a multilayer neural network using genetic algorithm are studied. Investigation was conducted on the basis of the developed software, which allows to detect indications of diseases by analyzing photographs of human organs` tissues. The Java programming language was used to implement the project. The software product consists of modules that implement: multilayer neural network, genetic algorithm and mechanism for reading and processing images from the file system. The genetic algorithm is used to calculate the initial values of synaptic weights, which are specified by the error propagation algorithm.
{"title":"Advantages and Disadvantages of Learning a Multilayer Neural Network Using a Genetic Algorithm","authors":"M.L. Kovalchuk, P.I. Ushtan, Y. Ushenko, I. Soltys","doi":"10.31649/1681-7893-2022-43-1-19-23","DOIUrl":"https://doi.org/10.31649/1681-7893-2022-43-1-19-23","url":null,"abstract":"The advantages and disadvantages of learning a multilayer neural network using genetic algorithm are studied. Investigation was conducted on the basis of the developed software, which allows to detect indications of diseases by analyzing photographs of human organs` tissues. The Java programming language was used to implement the project. The software product consists of modules that implement: multilayer neural network, genetic algorithm and mechanism for reading and processing images from the file system. The genetic algorithm is used to calculate the initial values of synaptic weights, which are specified by the error propagation algorithm.","PeriodicalId":142101,"journal":{"name":"Optoelectronic information-power technologies","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127630765","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 : 2022-12-28DOI: 10.31649/1681-7893-2022-43-1-65-75
V. I. Manzhula, M. Dyvak
The work proposes an approach to the construction of an interval model for solving the problems of localization of the recurrent laryngeal nerve in the process of surgery on the neck organs of the human. The interval model reflects the distribution of the amplitude of the information signal - the reaction to stimulation of the tissues of the surgery area with an alternating current of limited amplitude. The technical and software means of detection and visualization of the recurrent laryngeal nerve were analyzed. A method of identifying the specified mathematical model is proposed, which is based on the procedures for solving a nonlinear optimization problem. The proposed method simplifies the procedure for identifying the parameters of the interval model, in particular, due to the analytical representation of the objective function of the optimization problem, in contrast to the known method, where this function is discrete. The model was verified on experimental data obtained during the thyroid surgery. The developed interval nonlinear model makes it possible to detect and visualize the placement of the laryngeal nerve in the area of surgical intervention during the operation and, accordingly, ensures a reduction in the risk damage of its.
{"title":"Interval nonlinear model of information signal amplitude distribution in the task of detection and localization of the recurrent laryngeal nerve during surgical operations","authors":"V. I. Manzhula, M. Dyvak","doi":"10.31649/1681-7893-2022-43-1-65-75","DOIUrl":"https://doi.org/10.31649/1681-7893-2022-43-1-65-75","url":null,"abstract":"The work proposes an approach to the construction of an interval model for solving the problems of localization of the recurrent laryngeal nerve in the process of surgery on the neck organs of the human. The interval model reflects the distribution of the amplitude of the information signal - the reaction to stimulation of the tissues of the surgery area with an alternating current of limited amplitude. The technical and software means of detection and visualization of the recurrent laryngeal nerve were analyzed. A method of identifying the specified mathematical model is proposed, which is based on the procedures for solving a nonlinear optimization problem. The proposed method simplifies the procedure for identifying the parameters of the interval model, in particular, due to the analytical representation of the objective function of the optimization problem, in contrast to the known method, where this function is discrete. The model was verified on experimental data obtained during the thyroid surgery. The developed interval nonlinear model makes it possible to detect and visualize the placement of the laryngeal nerve in the area of surgical intervention during the operation and, accordingly, ensures a reduction in the risk damage of its.","PeriodicalId":142101,"journal":{"name":"Optoelectronic information-power technologies","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125361400","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 : 2022-12-28DOI: 10.31649/1681-7893-2022-43-1-5-10
A. Dovgun, Y. Ushenko, M. Gorsky
The conditions of asymptotic stability of the trivial solution of stochastic diffusion dynamic systems of automatic regulation with external disturbances are obtained. In work is to find criteria for the absolute stability of solutions of stochastic diffusion dynamic systems of automatic regulation (SAR) with external disturbances. The problem of determining sufficient algebraic conditions for the stability of stochastic diffusion dynamic SARs with aftereffect and taking into account external disturbances is relevant, since its solution makes it possible to study complex stochastic systems using matrix calculations.
{"title":"Criterion of Absolute Stability of Solutions of Stochastic Diffusion Dynamic Information Systems of Automatic Regulation With External Disturbances","authors":"A. Dovgun, Y. Ushenko, M. Gorsky","doi":"10.31649/1681-7893-2022-43-1-5-10","DOIUrl":"https://doi.org/10.31649/1681-7893-2022-43-1-5-10","url":null,"abstract":"The conditions of asymptotic stability of the trivial solution of stochastic diffusion dynamic systems of automatic regulation with external disturbances are obtained. In work is to find criteria for the absolute stability of solutions of stochastic diffusion dynamic systems of automatic regulation (SAR) with external disturbances. The problem of determining sufficient algebraic conditions for the stability of stochastic diffusion dynamic SARs with aftereffect and taking into account external disturbances is relevant, since its solution makes it possible to study complex stochastic systems using matrix calculations.","PeriodicalId":142101,"journal":{"name":"Optoelectronic information-power technologies","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125045936","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 : 2022-12-28DOI: 10.31649/1681-7893-2022-43-1-11-18
V. Borovytsky, I.I. Avdieionok, S.E. Tuzhanskyi, H. Lysenko
The article proposes a classification of photonic integrated circuits (PICs) for optical multiplication of vectors on matrices. According to this classification, such PIC can be divided into two groups. The first group combines multilayer photonic integrated circuits, in which active elements that perform multiplication are located in one layer, and optical waveguides for input and output signals are located in other layers. The second group covers planar PIC, in which active elements are placed in one layer together with optical waveguides. The article describes the construction, principles of operation of FIS of both groups and contains an analysis of their advantages and disadvantages.
{"title":"Photonic integrated circuits for optical matrix-vector multiplication","authors":"V. Borovytsky, I.I. Avdieionok, S.E. Tuzhanskyi, H. Lysenko","doi":"10.31649/1681-7893-2022-43-1-11-18","DOIUrl":"https://doi.org/10.31649/1681-7893-2022-43-1-11-18","url":null,"abstract":"The article proposes a classification of photonic integrated circuits (PICs) for optical multiplication of vectors on matrices. According to this classification, such PIC can be divided into two groups. The first group combines multilayer photonic integrated circuits, in which active elements that perform multiplication are located in one layer, and optical waveguides for input and output signals are located in other layers. The second group covers planar PIC, in which active elements are placed in one layer together with optical waveguides. The article describes the construction, principles of operation of FIS of both groups and contains an analysis of their advantages and disadvantages.","PeriodicalId":142101,"journal":{"name":"Optoelectronic information-power technologies","volume":"68 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134281008","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 : 2022-12-28DOI: 10.31649/1681-7893-2022-43-1-36-42
O. M. Yatsko, Y. Ushenko, O. Olar
The essence of intelligent data analysis (data mining), methods of intelligent data analysis are considered. The field of application of intelligent data analysis and existing systems are analyzed. Conclusions were made regarding the prospects of using methods of intelligent data analysis in web development.
{"title":"Review of Intelligent Data Analysis to Web-Development Applications","authors":"O. M. Yatsko, Y. Ushenko, O. Olar","doi":"10.31649/1681-7893-2022-43-1-36-42","DOIUrl":"https://doi.org/10.31649/1681-7893-2022-43-1-36-42","url":null,"abstract":"The essence of intelligent data analysis (data mining), methods of intelligent data analysis are considered. The field of application of intelligent data analysis and existing systems are analyzed. Conclusions were made regarding the prospects of using methods of intelligent data analysis in web development.","PeriodicalId":142101,"journal":{"name":"Optoelectronic information-power technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130311206","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 : 2022-12-28DOI: 10.31649/1681-7893-2022-43-1-53-64
Ibrahim Younouss Abdelhamid, Y. Nosova, Oleg Avrunin, Olena Y. Prisych, Alofy Bander Ali Saleh
The paper deals with a comparative analysis of aerodynamic nose drag coefficients based on the data of front and rear active rhinomanometry. Functional disorders of nasal breathing in the future lead to further complications of the upper and lower respiratory system, reduce the quality of life and lead to other pathological conditions. The diagnosis of such disorders is complicated by the low prevalence of nasal breathing testing tools (rhinomanometers) in medical practice and the peculiarities of functional research methods, which are particularly related to the low repeatability of results and the lack of a clear correlation between diagnostic data and the patient's objective feelings. The obtained data on the total coefficients of aerodynamic nasal resistance, which are determined using the methods of front and rear active rhinomanometry, correspond quite clearly to each other within 12%. The values of the total coefficients of nasal resistance, obtained by the method of posterior rhinomanometry, in all typical cases differ to a lesser extent. The perspective of the work is to gather statistical data to determine the features of nasal breathing testing to obtain accurate personalized values of nasal resistance coefficients in different breathing modes, taking into account individual variability.
{"title":"Comparative analysis of the coefficients of aerodynamic nasal resistance according to the data of front and back active rhinomanometry","authors":"Ibrahim Younouss Abdelhamid, Y. Nosova, Oleg Avrunin, Olena Y. Prisych, Alofy Bander Ali Saleh","doi":"10.31649/1681-7893-2022-43-1-53-64","DOIUrl":"https://doi.org/10.31649/1681-7893-2022-43-1-53-64","url":null,"abstract":"The paper deals with a comparative analysis of aerodynamic nose drag coefficients based on the data of front and rear active rhinomanometry. Functional disorders of nasal breathing in the future lead to further complications of the upper and lower respiratory system, reduce the quality of life and lead to other pathological conditions. The diagnosis of such disorders is complicated by the low prevalence of nasal breathing testing tools (rhinomanometers) in medical practice and the peculiarities of functional research methods, which are particularly related to the low repeatability of results and the lack of a clear correlation between diagnostic data and the patient's objective feelings. The obtained data on the total coefficients of aerodynamic nasal resistance, which are determined using the methods of front and rear active rhinomanometry, correspond quite clearly to each other within 12%. The values of the total coefficients of nasal resistance, obtained by the method of posterior rhinomanometry, in all typical cases differ to a lesser extent. The perspective of the work is to gather statistical data to determine the features of nasal breathing testing to obtain accurate personalized values of nasal resistance coefficients in different breathing modes, taking into account individual variability.","PeriodicalId":142101,"journal":{"name":"Optoelectronic information-power technologies","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126650184","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：