Tetiana A. Luhova, Candidate of Art Sciences, Associate Professor, Associate Professor of the Information Activity and Media Communications Department, E-mail: lug2308@gmail.com, ORCID: 0000-0002-3573-9978 Oleksandr A. Blazhko, Candidate of Technical Sciences, Associate Professor, Associate Professor of the System Software Department, E-mail: blazhko@ieee.org , ORCID: 0000-0001-7413-275X Yuliia L. Troianovska, Senior Lecturer of the Information System Department, E-mail: troyanovskaja@gmail.com, ORCID: 0000-0002-6716-9391 Odessa National Polytechnic University, Shevchenko av, 1, Odessa, Ukraine, 65044
Tetiana A. Luhova，艺术科学候选人，副教授，信息活动与媒体传播系副教授，E-mail: lug2308@gmail.com, ORCID: 0000-0002-3573-9978 Oleksandr A. Blazhko，技术科学候选人，副教授，系统软件系副教授，E-mail: blazhko@ieee.org, ORCID: 0000-0001-7413-275X Yuliia L. Troianovska，信息系统系高级讲师，E-mail:troyanovskaja@gmail.com, ORCID: 0000-0002-6716-9391敖德萨国立理工大学，舍甫琴科1，乌克兰敖德萨65044
{"title":"FEATURES OF USING DIVERSIFIERS OF HACKATHON-CONTESTS IN CANVAS-ORIENTED APPROACH TO GAME DESIGN","authors":"O. Blazhko, Tetiana Luhova, Yuliia Troianovska","doi":"10.15276/HAIT.02.2019.6","DOIUrl":"https://doi.org/10.15276/HAIT.02.2019.6","url":null,"abstract":"Tetiana A. Luhova, Candidate of Art Sciences, Associate Professor, Associate Professor of the Information Activity and Media Communications Department, E-mail: lug2308@gmail.com, ORCID: 0000-0002-3573-9978 Oleksandr A. Blazhko, Candidate of Technical Sciences, Associate Professor, Associate Professor of the System Software Department, E-mail: blazhko@ieee.org , ORCID: 0000-0001-7413-275X Yuliia L. Troianovska, Senior Lecturer of the Information System Department, E-mail: troyanovskaja@gmail.com, ORCID: 0000-0002-6716-9391 Odessa National Polytechnic University, Shevchenko av, 1, Odessa, Ukraine, 65044","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133349018","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}
O. Ruban, Олександр Дмитрович Рубан, Александр Дмитриевич Рубан
The features of using the theory of Volterra series and neural networks in problems of nonlinear dynamic systems modeling are considered. A comparative analysis of methods for constructing models of nonlinear dynamic systems based on the theory of Volterra series and neural networks is carried out; areas of effective application of each method are indicated. The problem statement is formulated, consisting in the creation of a mathematical apparatus for transforming models of nonlinear dynamic systems derived from the Volterra series apparatus into an artificial neural network of a certain structure. The three-layer structure of a direct signal propagation neural network has been substantiated and investigated for represent nonlinear dynamic systems. It is outlined a class of systems that can be efficiently approximated by this network. The dependence of the Volterra kernels coefficients and the weighting coefficients of the hidden layer of the three-layer forward-propagation neural network is established. An algorithm for constructing an artificial neural network based on the Volterra series is given. The results of computer simulation of nonlinear dynamic systems using the Volterra neural network and direct signal propagation neural network are presented. The analysis of experimental data confirms the effectiveness of using Volterra neural networks in problems of modeling nonlinear dynamic systems. Conclusions and recommendations on the effective use of Volterra neural networks for modeling nonlinear dynamic systems are made.
{"title":"VOLTERRA NEURAL NETWORK CONSTRUCTION IN THE NONLINEAR DYNAMIC SYSTEMS MODELING PROBLEM","authors":"O. Ruban, Олександр Дмитрович Рубан, Александр Дмитриевич Рубан","doi":"10.15276/hait.01.2019.2","DOIUrl":"https://doi.org/10.15276/hait.01.2019.2","url":null,"abstract":"The features of using the theory of Volterra series and neural networks in problems of nonlinear dynamic systems modeling are considered. A comparative analysis of methods for constructing models of nonlinear dynamic systems based on the theory of Volterra series and neural networks is carried out; areas of effective application of each method are indicated. The problem statement is formulated, consisting in the creation of a mathematical apparatus for transforming models of nonlinear dynamic systems derived from the Volterra series apparatus into an artificial neural network of a certain structure. The three-layer structure of a direct signal propagation neural network has been substantiated and investigated for represent nonlinear dynamic systems. It is outlined a class of systems that can be efficiently approximated by this network. The dependence of the Volterra kernels coefficients and the weighting coefficients of the hidden layer of the three-layer forward-propagation neural network is established. An algorithm for constructing an artificial neural network based on the Volterra series is given. The results of computer simulation of nonlinear dynamic systems using the Volterra neural network and direct signal propagation neural network are presented. The analysis of experimental data confirms the effectiveness of using Volterra neural networks in problems of modeling nonlinear dynamic systems. Conclusions and recommendations on the effective use of Volterra neural networks for modeling nonlinear dynamic systems are made.","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121846524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. Vychuzhanin, Владимир Викторович Вычужанин, Володимир Викторович Вичужанін
{"title":"ON THE CONSTRUCTION OF A SOFTWARE ARCHITECTURE FOR NUCLEAR SYSTEMS ON A CRYSTAL","authors":"V. Vychuzhanin, Владимир Викторович Вычужанин, Володимир Викторович Вичужанін","doi":"10.15276/HAIT.01.2019.1","DOIUrl":"https://doi.org/10.15276/HAIT.01.2019.1","url":null,"abstract":"","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125675390","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 THE MOTION OF A SOLID BODY UNDER THE ACTION OF THE MOMENT OF LIGHT PRESSURE IN THE MEDIUM WITH RESISTANCE","authors":"A. Rachinskaya","doi":"10.15276/hait.01.2019.5","DOIUrl":"https://doi.org/10.15276/hait.01.2019.5","url":null,"abstract":"","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115353880","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}
B. Tymchenko, Anhelina Hramatik, Heorhii Tulchiy, S. Antoshchuk, Борис Ігорович Тимченко, Ангеліна Антоліївна Граматік, Георгій Петрович Tульчий, Світлана Григорівна Антощук, Борис Игоревич Тимченко, Ангелина Анатольевна Граматик, Георгий Петрович Тульчий, Светлана Григорьевна Антощук
Nowadays, accurate diagnosis of diseases, their treatment and prognosis is a very acute problem of modern medicine. By studying information about human proteins, you can identify differentially expressed proteins. These proteins are potentially interesting biomarkers that can be used for an accurate diagnosis, prognosis, or selection of individual treatments, especially for cancer. A surprising finding from this research is that we have relatively few proteins that are tissue specific. Almost half of all proteins are categorized as housekeeping proteins, expressed in all cells. Only 2,300 proteins in the human body have been identified as tissue enriched, meaning they have elevated expression levels in certain tissues. Thanks to advances in high-throughput microscopy, images are generated too quickly for manual evaluation. Consequently, the need for automating the analysis of biomedical images is as great as ever to speed up the understanding of human cells and diseases. Historically, the classification of proteins was limited to individual patterns in one or more cell types, but in order to fully understand the complexity of a human cell, models must classify mixed patterns according to a number of different human cells. The article formulates the problem of image classification in medical research. In this area, classification methods using deep convolutional neural networks are actively used. Presented article gives a brief overview of the various approaches and methods of similar research. As a dataset was taken “The Human Protein Atlas”, that presents a tissue-based map of the human proteome, completed in 2014 after 11 years of research. All protein expression profiling data is publicly accessible in an interactive database, enabling tissue-based exploration of the human proteome. It was done an analysis of the work and the methods that were used during the research. To solve this problem, the deep neural network model is proposed taking into account the characteristics of the domain and the sample under study. The neural network model is based on Inception-v3 architecture. Optimization procedure contains combination of several tweaks for fast convergence: stochastic gradient descent with warm restarts (learning rate schedule for exploring different local minima), progressive image resizing (training starts from small resolution and sequentially increases each cycle of SGDR). We propose new method for threshold selection for F1 measure. Developed model can be used to create an instrument integrated into the medical system of intellectual microscopy to determine the location of the protein from a high-performance image.
{"title":"CLASSIFYING MIXED PATTERNS OF PROTEINS IN MICROSCOPIC IMAGES WITH DEEP NEURAL NETWORKS","authors":"B. Tymchenko, Anhelina Hramatik, Heorhii Tulchiy, S. Antoshchuk, Борис Ігорович Тимченко, Ангеліна Антоліївна Граматік, Георгій Петрович Tульчий, Світлана Григорівна Антощук, Борис Игоревич Тимченко, Ангелина Анатольевна Граматик, Георгий Петрович Тульчий, Светлана Григорьевна Антощук","doi":"10.15276/hait.01.2019.3","DOIUrl":"https://doi.org/10.15276/hait.01.2019.3","url":null,"abstract":"Nowadays, accurate diagnosis of diseases, their treatment and prognosis is a very acute problem of modern medicine. By studying information about human proteins, you can identify differentially expressed proteins. These proteins are potentially interesting biomarkers that can be used for an accurate diagnosis, prognosis, or selection of individual treatments, especially for cancer. A surprising finding from this research is that we have relatively few proteins that are tissue specific. Almost half of all proteins are categorized as housekeeping proteins, expressed in all cells. Only 2,300 proteins in the human body have been identified as tissue enriched, meaning they have elevated expression levels in certain tissues. Thanks to advances in high-throughput microscopy, images are generated too quickly for manual evaluation. Consequently, the need for automating the analysis of biomedical images is as great as ever to speed up the understanding of human cells and diseases. Historically, the classification of proteins was limited to individual patterns in one or more cell types, but in order to fully understand the complexity of a human cell, models must classify mixed patterns according to a number of different human cells. The article formulates the problem of image classification in medical research. In this area, classification methods using deep convolutional neural networks are actively used. Presented article gives a brief overview of the various approaches and methods of similar research. As a dataset was taken “The Human Protein Atlas”, that presents a tissue-based map of the human proteome, completed in 2014 after 11 years of research. All protein expression profiling data is publicly accessible in an interactive database, enabling tissue-based exploration of the human proteome. It was done an analysis of the work and the methods that were used during the research. To solve this problem, the deep neural network model is proposed taking into account the characteristics of the domain and the sample under study. The neural network model is based on Inception-v3 architecture. Optimization procedure contains combination of several tweaks for fast convergence: stochastic gradient descent with warm restarts (learning rate schedule for exploring different local minima), progressive image resizing (training starts from small resolution and sequentially increases each cycle of SGDR). We propose new method for threshold selection for F1 measure. Developed model can be used to create an instrument integrated into the medical system of intellectual microscopy to determine the location of the protein from a high-performance image.","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134282938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. Pavlenko, S. Pavlenko, Віталій Данилович Павленко, Сергій Віталійович Павлєнко, Віталій Данилович Павленко, Сергей Витальевич Павленко
{"title":"ORGANIZATION OF COMPUTATIONS IN CLUSTERS USING TRANSPARENT PARALLELIZING PRINCIPLES","authors":"V. Pavlenko, S. Pavlenko, Віталій Данилович Павленко, Сергій Віталійович Павлєнко, Віталій Данилович Павленко, Сергей Витальевич Павленко","doi":"10.15276/hait.01.2019.6","DOIUrl":"https://doi.org/10.15276/hait.01.2019.6","url":null,"abstract":"","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114649688","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}
I. Petrov, N. Rudnichenko, Denis Shibaev, Natalia Shibaeva, V. Vychuzhanin
{"title":"DESIGN OF AUTOMATED INFORMATION SUPPORT SYSTEM FOR MARINE AGENT IN SERVICE ERGATIC SYSTEMS","authors":"I. Petrov, N. Rudnichenko, Denis Shibaev, Natalia Shibaeva, V. Vychuzhanin","doi":"10.15276/hait.01.2018.4","DOIUrl":"https://doi.org/10.15276/hait.01.2018.4","url":null,"abstract":"","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":" 32","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132094832","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}
T. Gumennykova, Tetiana Luhova, Oksana Riashchenko, Yuliia Troianovska
{"title":"INTEGRATION OF THE PROCESS OF COMPUTER GAME DEVELOPMENT WITH AUGMENTED REALITY IN STREAM-EDUCATION COMPONENTS","authors":"T. Gumennykova, Tetiana Luhova, Oksana Riashchenko, Yuliia Troianovska","doi":"10.15276/hait.01.2018.5","DOIUrl":"https://doi.org/10.15276/hait.01.2018.5","url":null,"abstract":"","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128995280","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":"METHOD OF THE SENSOR NETWORK RESOURCES ALLOCATION IN THE CONDITIONS OF EDGE COMPUTING","authors":"S. Antoshchuk, Ivan Lobachev, Roman Maleryk","doi":"10.15276/hait.01.2018.3","DOIUrl":"https://doi.org/10.15276/hait.01.2018.3","url":null,"abstract":"","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125947743","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}
Olena Arsirii, Oksana Babilunha, Olga Manikaeva, Oleksii Rudenko
{"title":"AUTOMATION OF THE PREPARATION PROCESS WEAKLY-STRUCTURED MULTI-DIMENSIONAL DATA OF SOCIOLOGICAL SURVEYS IN THE DATA MINING SYSTEM","authors":"Olena Arsirii, Oksana Babilunha, Olga Manikaeva, Oleksii Rudenko","doi":"10.15276/hait.01.2018.1","DOIUrl":"https://doi.org/10.15276/hait.01.2018.1","url":null,"abstract":"","PeriodicalId":375628,"journal":{"name":"Herald of Advanced Information Technology","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134524436","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：