Pub Date : 2024-03-05DOI: 10.3103/s0147688223050027
V. V. Arlazarov
Abstract
In this paper, the task of combining recognition results from multiple images is considered. Systems in which such problems occur are analyzed, and some known approaches are described. It should be noted that currently there is no unified approach that could be used to solve the combination problem for increasing text recognition accuracy using multiple images or in a video stream. As an example, a comparative study of three different approaches to the combination of per-frame recognition results of identity document fields is presented, and it is demonstrated that different approaches may be advantageous for different parts of a data set, while a selection of the potential best single result still significantly outperforms all of the analyzed methods. The task of the per-frame combination of recognition results is an important component in video stream recognition systems and requires careful consideration and the formulation of general approaches that would be applicable to various domains.
{"title":"Problems of Combining Multiple Text Recognition Results","authors":"V. V. Arlazarov","doi":"10.3103/s0147688223050027","DOIUrl":"https://doi.org/10.3103/s0147688223050027","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>In this paper, the task of combining recognition results from multiple images is considered. Systems in which such problems occur are analyzed, and some known approaches are described. It should be noted that currently there is no unified approach that could be used to solve the combination problem for increasing text recognition accuracy using multiple images or in a video stream. As an example, a comparative study of three different approaches to the combination of per-frame recognition results of identity document fields is presented, and it is demonstrated that different approaches may be advantageous for different parts of a data set, while a selection of the potential best single result still significantly outperforms all of the analyzed methods. The task of the per-frame combination of recognition results is an important component in video stream recognition systems and requires careful consideration and the formulation of general approaches that would be applicable to various domains.</p>","PeriodicalId":43962,"journal":{"name":"Scientific and Technical Information Processing","volume":"28 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140046071","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 : 2024-03-05DOI: 10.3103/s0147688223050064
V. V. Gribova, Ph. M. Moskalenko, V. A. Timchenko, E. A. Shalfeeva
Abstract—
The paper presents the IACPaaS cloud platform, which is used for creating intelligent services based on ontologies, as well as the conceptual ideas and architecture underlying its development. The main features of the supported technologies for creating intelligent services of various types are described, as the experience of their use. The platform offers an evolved instrumental support for the development of all components of intelligent services. First of all, it was positioned as an environment for creating cloud systems with knowledge bases, and now it is considered to be a tool for software development based on ontologies with semantic representation.
{"title":"The IACPaaS Platform for Developing Systems Based on Ontologies: A Decade of Use","authors":"V. V. Gribova, Ph. M. Moskalenko, V. A. Timchenko, E. A. Shalfeeva","doi":"10.3103/s0147688223050064","DOIUrl":"https://doi.org/10.3103/s0147688223050064","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract—</h3><p>The paper presents the IACPaaS cloud platform, which is used for creating intelligent services based on ontologies, as well as the conceptual ideas and architecture underlying its development. The main features of the supported technologies for creating intelligent services of various types are described, as the experience of their use. The platform offers an evolved instrumental support for the development of all components of intelligent services. First of all, it was positioned as an environment for creating cloud systems with knowledge bases, and now it is considered to be a tool for software development based on ontologies with semantic representation.</p>","PeriodicalId":43962,"journal":{"name":"Scientific and Technical Information Processing","volume":"23 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140046181","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 : 2024-03-05DOI: 10.3103/s0147688223050040
D. A. Devyatkin, O. G. Grigoriev
Abstract
Axis-parallel decision trees perform poorly on that multidimensional sparse data that are frequently input in many tasks. A straightforward solution is to create decision trees that have oblique splits; however, most training approaches have low performance. These models can easily overfit, so they should be combined with a random ensemble. This paper proposes an algorithm to train kernel decision trees. At each stump, the algorithm optimizes a loss function with a margin rescaling approach that simultaneously optimizes the margin and impurity criteria. We performed an experimental evaluation of several tasks, such as studying the reaction of social media users and image recognition. The experimental results show that the proposed algorithm trains ensembles that outperform other oblique or kernel forests in many datasets.
{"title":"Method of Training a Kernel Tree","authors":"D. A. Devyatkin, O. G. Grigoriev","doi":"10.3103/s0147688223050040","DOIUrl":"https://doi.org/10.3103/s0147688223050040","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>Axis-parallel decision trees perform poorly on that multidimensional sparse data that are frequently input in many tasks. A straightforward solution is to create decision trees that have oblique splits; however, most training approaches have low performance. These models can easily overfit, so they should be combined with a random ensemble. This paper proposes an algorithm to train kernel decision trees. At each stump, the algorithm optimizes a loss function with a margin rescaling approach that simultaneously optimizes the margin and impurity criteria. We performed an experimental evaluation of several tasks, such as studying the reaction of social media users and image recognition. The experimental results show that the proposed algorithm trains ensembles that outperform other oblique or kernel forests in many datasets.</p>","PeriodicalId":43962,"journal":{"name":"Scientific and Technical Information Processing","volume":"41 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140882943","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 : 2024-03-05DOI: 10.3103/s0147688223050155
A. V. Zaboleeva-Zotova, A. B. Petrovsky
Abstract
This paper considers the means for conceptual design of complex technical systems. A quasi-axiomatic theory was constructed that formalizes the procedures of generating meaning for a natural language description of the process of creating a new technical solution. Semantic categories, structures of universal sets, and operations for comparing elements of the universe are introduced. The types of connection of elementary subsystems are described. A formalization of the procedure for multilevel synthesis of a technical system using a generative grammar over fuzzy structures is proposed. An example of the design of a technical device is given.
{"title":"Formalization of the Structural Synthesis of Technical Systems at the Initial Stage of Design","authors":"A. V. Zaboleeva-Zotova, A. B. Petrovsky","doi":"10.3103/s0147688223050155","DOIUrl":"https://doi.org/10.3103/s0147688223050155","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>This paper considers the means for conceptual design of complex technical systems. A quasi-axiomatic theory was constructed that formalizes the procedures of generating meaning for a natural language description of the process of creating a new technical solution. Semantic categories, structures of universal sets, and operations for comparing elements of the universe are introduced. The types of connection of elementary subsystems are described. A formalization of the procedure for multilevel synthesis of a technical system using a generative grammar over fuzzy structures is proposed. An example of the design of a technical device is given.</p>","PeriodicalId":43962,"journal":{"name":"Scientific and Technical Information Processing","volume":"27 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140882996","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 : 2024-03-05DOI: 10.3103/s0147688223040020
N. G. Inshakova, I. A. Pankeev
Abstract
The functions of the title in theoretical and practical interpretation are considered. Problems and mistakes of naming are pointed out from the point of view of actual requirements to the information presentation. Recommendations for creating title complex optimal in the situation of information glut are offered. The main conclusions are supported by the results of a group survey of journalism students.
{"title":"Media Text Headlines in the Context of Information Redundancy","authors":"N. G. Inshakova, I. A. Pankeev","doi":"10.3103/s0147688223040020","DOIUrl":"https://doi.org/10.3103/s0147688223040020","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>The functions of the title in theoretical and practical interpretation are considered. Problems and mistakes of naming are pointed out from the point of view of actual requirements to the information presentation. Recommendations for creating title complex optimal in the situation of information glut are offered. The main conclusions are supported by the results of a group survey of journalism students.</p>","PeriodicalId":43962,"journal":{"name":"Scientific and Technical Information Processing","volume":"237 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140036175","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 : 2024-03-05DOI: 10.3103/s0147688223050052
S. L. Frenkel, V. N. Zakharov
Abstract
Many modern machine learning tools are inefficient due to the pronounced nonlinearity of traffic changes and nonstationarity. For this, the task of predicting the signs of increments (directions of change) of the process of time series is singled out. This article proposes the use of some results of the theory of random processes for a quick assessment of the predictability of signs of increments with acceptable accuracy. The proposed procedure is a simple heuristic rule for predicting the increment of two neighboring values for a random sequence. The connection of this approach to time series with known approaches to the prediction of binary sequences is shown. The possibility of using the experience of predicting the absolute values of traffic in predicting the signs of changes is considered.
{"title":"Internet Traffic Prediction Model","authors":"S. L. Frenkel, V. N. Zakharov","doi":"10.3103/s0147688223050052","DOIUrl":"https://doi.org/10.3103/s0147688223050052","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>Many modern machine learning tools are inefficient due to the pronounced nonlinearity of traffic changes and nonstationarity. For this, the task of predicting the signs of increments (directions of change) of the process of time series is singled out. This article proposes the use of some results of the theory of random processes for a quick assessment of the predictability of signs of increments with acceptable accuracy. The proposed procedure is a simple heuristic rule for predicting the increment of two neighboring values for a random sequence. The connection of this approach to time series with known approaches to the prediction of binary sequences is shown. The possibility of using the experience of predicting the absolute values of traffic in predicting the signs of changes is considered.</p>","PeriodicalId":43962,"journal":{"name":"Scientific and Technical Information Processing","volume":"33 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140046082","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 : 2024-03-05DOI: 10.3103/s0147688223040135
T. I. Frolova, D. S. Ilchenko, E. A. Striga
Abstract
The article presents the results of a study of the genre policy of the leading Russian business journals Forbes Russia, Expert, and Profile when creating analytical publications on technological innovations. The results of this made it possible to formulate the dominant strategies for the journalistic analysis of scientific and technological topics which are characteristic to each publication. Forbes Russia is focused on the analysis of the subjects of the scientific and technological development of the economy, which is reflected in the active use of the case and column genres. The editorial staff of Profile prefers to analyze trends in the scientific and technological development of the economy and society and publishes texts in the genres of review, forecast, and general research article. Expert is dominated by the analysis of current problems in the scientific and technological development of the economy and society, embodied in the publications of works in genres such as practical and analytical articles, case studies, and expert interviews.
{"title":"Business Media Strategies in Analysis of Scientific and Technical Topic","authors":"T. I. Frolova, D. S. Ilchenko, E. A. Striga","doi":"10.3103/s0147688223040135","DOIUrl":"https://doi.org/10.3103/s0147688223040135","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>The article presents the results of a study of the genre policy of the leading Russian business journals <i>Forbes Russia</i>, <i>Expert</i>, and <i>Profile</i> when creating analytical publications on technological innovations. The results of this made it possible to formulate the dominant strategies for the journalistic analysis of scientific and technological topics which are characteristic to each publication. <i>Forbes Russia</i> is focused on the analysis of the subjects of the scientific and technological development of the economy, which is reflected in the active use of the case and column genres. The editorial staff of <i>Profile</i> prefers to analyze trends in the scientific and technological development of the economy and society and publishes texts in the genres of review, forecast, and general research article. <i>Expert</i> is dominated by the analysis of current problems in the scientific and technological development of the economy and society, embodied in the publications of works in genres such as practical and analytical articles, case studies, and expert interviews.</p>","PeriodicalId":43962,"journal":{"name":"Scientific and Technical Information Processing","volume":"9 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140036052","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}