The paper presents the conception of an intelligent system for troubleshooting an aircraft. The intelligent system requirements, its structure (architecture), and the domain conceptual model are described. In particular, the case-based and rule-based expert systems are defined as the main subsystems. The first one is designed to store information about malfunctions that are not accounted for in the current version of the documentation and find a solution by demonstrating similar problem situations. The second one provides the formation of plans to eliminate failures and malfunctions based on information from troubleshooting manuals. The features of their implementation are considered.
In this paper, we consider the application of the PESoT technology and a tool (namely, Personal Knowledge Base Designer) for prototyping rule-based knowledge bases by using the automated analysis and transformation of decision tables presented in the CSV format. Created prototypes of knowledge bases designed for intelligent decision-making support when analyzing and forecasting the risk (probability) of forest fires based on information about the forest fire hazard class, weather conditions, and other factors. A description of the main stages of the approach and an illustrative example are presented.
The paper describes the cloud service of ISDCT SB RAS for machine learning research. The introduction discusses the relevance of creating a service. Further, the theoretical part is considered, which describes the component of the services and the principle of their interaction. Then the results of practical application and discussion are presented. In the conclusion, the results of the work are summarized.
The article describes original algorithms developed to improve the spatial resolution of digital images using a circular scan procedure. Examples of image reconstruction in the presence and absence of noise are given, and the error in reconstructing the original signal is calculated.
This paper presents a complete solution for extraction of textual information and tables from PDF with a text layer. The presented solution consist of two parts: PyTabby is a tool for extracting text and tables from PDF with a complex background and layout, and Python wrapper module for Docreader tool. The PyTabby tool extracts text and tables from the low level representation of the PDF format. It enables employment of the additional information excluded in scanned documents and provides improvement of quality and performance compared with Optical Character Recognition (OCR) methods. The presented solution is incorporated into Docreader tool to parse PDF files with a text layer and is used as a part of the TALISMAN technology for social analytics.
The paper represents a prototype of service-oriented tools for developing digital twins. These tools automate most of the stages in preparing and carrying out a computational experiment reducing the possibility of human error. Computational experiments based on simulation modeling are performed using the proposed tools. As an example in applying the represented tools, a digital twin of a heat pump used as environmentally-friendly equipment of an infrastructure object on the Baikal natural territory is considered. Owing to the growing anthropogenic load, special attention is paid to the objects located at the coast of Lake Baikal. During the simulation modeling, both the heat pump performance characteristics and retrospective meteorological data are used to predict climatic conditions and select optimal control parameters. In addition, the computational experiment has obviously shown that heat pump use significantly reduces the harmful effect on the environment.
The paper continues the series of publications devoted to the knowledge-based systems development platform (KBSDP). The focal point is a discussion about extensibility features of the platform: both presently available and potentially possible. The deployment issues related to contemporary technologies are also discussed. It is proposed to implement KBSDP components in accordance with the Platform as a Service paradigm. With the help of serverless (cloud) functions, it is also suggested to integrate external functionality into the KBSDP. An implementation model is proposed and related software is modified. In the context of illustrative examples (component-based modeling and integrated environmental modeling), the problems of technical, conceptual, and methodological integrations are analyzed. A set of ontologies for component-based modeling is adopted for utilization in KBSDP. The ideas for implementing conceptual and methodological integrations in the KBSDP workflow component are considered. Examples of sematic ports and controllers are presented, the principal algorithm of smart coupling is defined.
A problem of flexible geographical data representation and Web-based visualization is considered. The data stored in a knowledge graph as ontologies (vocabularies) in accordance to W3C standards. For viewing data, a web geographical information system (GIS) application is realized, which renders map interpreting SPARQL queries to Sematic Web server storing the knowledge graph. The technologies used for designing are based on contemporary Web 3.0, allowing one to implement Linked Open Data (LOD) compliance for GIS information publishing and integration.
To improve the quality of software systems, tools are currently being created to eliminate a large number of errors at the development stage. One of the problems that affects the quality of the programs being created is the occurrence of type mismatch errors. Such errors can occur in all programming languages. But for programming languages with static type-checking problems of type inconsistencies are detected even at the stage of compiling the program, whereas for languages with dynamic type-checking, errors of this kind can be detected only during the execution of the program code. For some programming languages with dynamic type-checking, for example, JavaScript and Python, there are already tools for tracking errors. But to date, there is no such tool for the programming language of 1C:Enterprise. The article describes the process of creating a software package for finding type mismatch errors in programs written in the programming language of 1C:Enterprise. The composition of the type system of 1C:Enterprise is described. The types of errors that were found using the developed static verification tool are listed.
Quality of complex technical systems is highly dependent on the quality of integrated software systems. Software system quality is determined with their functionalities and quality attributes that describe how the functionalities are performed. Although there exists a large list of software architecture quality attributes that technical systems can satisfy, they do that to a greater or lesser extent. Internet of Things (IoT) systems are complex socio-technical systems that include a variety of software elements distributed on specific hardware components and servers. Selecting and fulfilling of the most suitable quality attributes during system design is a challenging task. In this paper, we present our subjective experience with scalability, maintainability, security, availability and portability quality attributes during design of a layered sensor-based IoT system for monitoring industrial environmental conditions. Further research directions are also presented.
The freely available tabular data represented in various digital formats, such as print-oriented documents, spreadsheets, and web pages, are a valuable source to populate knowledge graphs. However, difficulties that inevitably arise with the extraction and integration of the tabular data often hinder their intensive use in practice. TabbyDOC project aims at elaborating a theoretical basis and developing open software for data extraction from arbitrary tables. Previously, it was devoted to the following issues: (i) table extraction tables from print-oriented documents, (ii) data transformation from spreadsheet tables to relational and linked data. This paper summarizes the project’s results that are intended for the following tasks: (i) automation of fine-tuning artificial neural networks for table detection in document images, (ii) a synthesis of programs for spreadsheet data transformation driven by user-defined rules of table analysis and interpretation, and (iii) generating RDF-triples from entities extracted from relational tables.
This paper presents a web portal created for Preschool institution in Zrenjanin, Serbia. This portal is created to present most relevant information and it is based on underlying CMS (Content Management System). The web portal was created in 2014 and refactored in 2020, in aim to adjust to new PHP hosting platform. In solving problem of uncertain exact time of hosting upgrade (shift from PHP 5 to PHP 7 support), it was necessary to include automation in detecting and adjustments to hosting platform change. Therefore, self-adaptation mechanism was developed and included in the solution, to provide constant availability of web portal, regardless the hosting platform change. Self-adaptation mechanism is based on sensor-effector approach.
The territories of the Baikal Region and Mongolia belong to the areas with evaluated seismic activity. In turn, these territories are at heightened risk of potentially damaging events for human socio-economic activity. Consequently, seismic activity recording and forecasting would allow us to minimise possible damages. These issues require collecting and processing large volumes of heterogeneous data. In order to effectively process such datasets, it would be necessary to use state-of-the-art information technologies and expandable analytical systems. Such systems should have a set of tools to enable collection, generation, transformation, visualisation and analysis of data. However, while implementing products of these types, developers, normally tend to use low-level tools for programming (various general-purpose programming languages and standard DBMS capabilities). On the other hand, developers tend to create highly specialised systems that are closely related to a specific automation object and focus on certain data structures. The paper considers an approach to the development of an informationanalytical system as an infrastructure element for assessing the seismic hazard of large lithospheric blocks of the Baikal region and Mongolia.
Characteristic features of the Baikal natural territory (BNT) are analyzed and the problems of forest monitoring are highlighted. An approach is proposed for the digital transformation of forest resource monitoring using a service-oriented paradigm, an infrastructure approach, and declarative specifications, as well as end-to-end and Web technologies for collecting and processing large amounts of spatiotemporal data. A scheme of a digital forest monitoring platform based on an information–analytical geoportal environment is described, including a system for processing and storing spatiotemporal data and a catalog of basic and thematic services for assessing the consequences of natural and anthropogenic impacts on forests of the BNT. The experience of using deep learning methods to monitor changes in the state of forests is presented. An automated determination of land cover types is carried out on the basis of Sentinel-2 images. The composition of classes of the training data set created for the BNT is described. The result of satellite image classification with the identified land cover classes is given. The digital platform (DP) thus created can be used to assess and predict the state of forest resources of the BNT and make managerial decisions on effective forest management.
We develop the document analysis system, which is able to extract text and text metadata (such as font size and style), and restore the document structure. Some parts of the pipeline are based on machine learning thus requiring training and the labeled dataset, creating a training dataset is based on manual labeling. In this article, we describe an approach to the creation of a labeling system in the task of multiclass classification of document lines (paragraphs). The pipeline consists of several stages ranged from getting the source documents to getting a ready-to-learn dataset. An approach to the analysis of scanned documents and documents in docx and txt format is considered. In our work, we focus on intra-team labeling, thus we do not consider some problems, common for the crowdsourcing approach (such as unscrupulous annotators).
The Web stores a large volume of web-tables with semi-structured data. The Semantic Web community considers them as a valuable source for the knowledge graph population. Interrelated named entities can be extracted from web-tables and mapped to a knowledge graph. It generally requires reconstructing the semantics missing in web-tables to interpret them according to their meaning. This paper discusses prospects of an end-to-end solution for the knowledge graph population by entities extracted from web-tables of predefined types. The discussion covers theoretical foundations both for transforming data from web-tables to entity sets (table analysis) and for mapping entities, attributes, and relations to a knowledge graph (semantic table annotation). Unlike general-purpose text mining and web-scraping tools, we aim at developing a solution that takes into account the relational nature of the information represented in web-tables. In contrast to the table-specific proposals, our approach implies both the table analysis and the semantic table annotation.
New results related to rule-based reasoning component of knowledge-based systems development platform are considered in the paper. Namely, the technique for the alternative way of rule creation based on the decision table approach is proposed. The data model of the decision table in the context of the platform, the transformation scheme from the decision table into rules are suggested. The implementation issues based on previously developed components are also discussed. The graphical user interface and database diagram are shown. As an illustrative example, the problem of identification of degradation processes of mechanical systems is chosen. The proposed technique is well suited for situations when there are numerous combinations of the facts of quite large set of templates in condition and action parts of rules. The end-user benefits are to represent knowledge in a tabular form that is convenient for analysis and evaluation, as well as to reduce the number of actions when creating a rule by the description of repeated actions in the transformation scheme.
New details of the implementation of the data representation and editing component of the knowledge-based systems development platform is proposed in the paper. The two modes of considered component is described. The typical component structure along with the core to client component parts communication issues are presented. The main UI control elements are listed and grouped according to the criteria of the number of efforts that applied developers spend in the course of making UI. On the top of controls from the first group considered component provides user interface for data control component and implements unified user interface for any valid component of the platform. The second group is responsible for user interface of the platform as a whole and also for problem-oriented functions of the core components (for example, rule or workflow editors). The third group relies on a predefined set of parameterized typical database manipulations and supports the applied developer in the process of UI customization. The implementation of two techniques is considered on the case of the conceptual model design component extension.
