Development of an adaptive mass open online course in the framework of training in artificial neural network technologies

Problem and goal. The development of mass open online courses contributes to the increasing attention of students to them. At the moment, there are many large services that provide online training, but there are no clearly defined universal requirements for such courses. Also, along with this problem, there is a fairly high level of rejection of the course at various stages due to the loss of motivation to continue training. Methodology. A variant of solving these problems by using adaptive learning technologies on the example of a course on learning artificial neural network technologies was considered. Results. In the process of reviewing the issue, the topics of the online course sections were determined. As a result, a work plan was drafted and the most relevant ways to solve the identified problems were formulated. Conclusion. The developed strategy can help with further elaboration and testing of the designed course and can be applied to any mass open online course.

Environmental digital conflicts: Spanish-, german-, and russian-speaking actors

Introduction. Almost all significant social communications are moving to virtual spaces. Thus, environmental conflicts play an increasingly important role in public life, as civic activity in solving environmental problems grows. The development of eco-territorial conflicts and requests for their social reactions lead to the emergence of digital conflict zones, sectors of the media space in which the current environmental agenda is discussed by a wide range of users. The analysis of conflicts in the digital environment is truly relevant and can be performed using neural network technologies. Methodology. Big data obtained from social media has become an important source of analysis of social processes, behavioral characteristics, speech perception, society's assessment of events and phenomena. The purpose of the work was to determine the specifics of perception in the media space of environmental conflicts in urban planning and construction. To analyze digital content, a multimodal approach was used along with neural network technologies, text analysis, sentiment analysis, analysis of word associations. The research data was collected using Brand Analytics and the corpus Sketch Engine. Content analysis was carried out using the multilingual technology of neural networks TextAnalyst 2.3. and visual analysis using the Tableau platform. Results and Conclusions. As a result of the study, common and different signs of the development of digital conflict zones related to environmental problems in the Spanish, German and Russian-speaking media space were identified.

Modern Problems of Information Security in Control and Access Control Systems When Using Neural Networks

This work is devoted to a theoretical study of the investigation of incidents from the operation of access control systems using neural networks in our time. The work describes the processes of operation of control and access control systems, in which neural network technologies are most actively introduced among the components of access control and management systems, and which, from the introduction of neural networks into them, can show new vulnerabilities in the operation of the access control and management system as a whole.

Decision support in complex organizational systems using neural network technologies

In complex organizational systems in which there is asymmetry of information, an important element of effective work is equal access to objective statistics. Because of the benefits to one of the parties in such systems, key elements of effective management and making the right decisions, it is necessary to develop independent approaches. The developed approach makes it possible to assess risks in various situations and with various interactions within the system, and also allows you to recreate the missing information for decision-making from open statistical databases. The key element of the developed approach is the use of self-organizing Kohonen neural networks, which make it possible to classify objects based on the reconstructed information. The importance of the correct grouping of system objects makes it possible to recommend a management decision with greater accuracy. The developed approach allows you to reduce uncertainty (risk), and, as a result, reduce losses and maximize profits.

The Use of Neural Network Technologies in Prediction the Reservoir Properties of Unconsolidated Reservoir Rocks of Shallow Bitumen Deposits

In the conditions of the dynamically changing conjuncture of the oil and gas market, there is an urgent need to reduce the cost of oil production and increase the efficiency of development, this is especially important for the local ultra-viscous oil. In this regard, it is necessary to optimize costs at all stages, starting from the geological exploration and even at the stage of completion of the development process. For ultra-viscous oil deposits, this is especially relevant at the stage of assessing the resource potential of a separate uplift of any of the fields, when the only reliable way to perform a high-frequency section at shallow depths is to drill appraisal wells with full core sampling. An additional load is exerted by the period between core extraction and obtaining information about the flow properties of each of the samples. By themselves, standard core studies are complicated by the fact that sand rocks of weakly cemented bitumoids can often be destroyed during experiments. In this regard, the use of new approaches, including digital ones, which allow us to make quick decisions on a part of the geological section in the area of the appraisal well and on the uplift as a whole, are highly in demand. This article describes the methods that allow the determining of flow properties for uncemented (loose sands) rocks in Permian sediments. More than 25,000 core samples were studied from 805 wells at several fields of the Republic of Tatarstan. The technology used allows us to calculate a continuous curve of volumetric bitumen saturation in the conditions of complete or partial absence of core at the well. This paper presents the results of creating an algorithm for automatic prediction of weight bitumen saturation in a sand pack of the Sheshminsky horizon of the Permian system using neural network technologies, as well as using an alternative calculation method.

APPLICATION OF NEURAL NETWORK TECHNOLOGIES FOR QUALITY MANAGEMENT FOOD PRODUCTS IN THE PRODUCTION PROCESS

Рассматривается задача разработки интеллектуальной автоматизированной системы управления качеством кондитерских изделий с использованием нейросетевых технологий на примере производства подсолнечной халвы. The problem of developing an automatic system for managing the quality of food products using neural network technologies is considered on the example of the production of sunflower halva.

Paragraph Boundary Recognition in Novels for Story Understanding

The understanding of narrative stories by computer is an important task for their automatic generation. To date, high-performance neural-network technologies such as BERT have been applied to tasks such as the Story Cloze Test and Story Completion. In this study, we focus on the text segmentation of novels into paragraphs, which is an important writing technique for readers to deepen their understanding of the texts. This type of segmentation, which we call “paragraph boundary recognition”, can be considered to be a binary classification problem in terms of the presence or absence of a boundary, such as a paragraph between target sentences. However, in this case, the data imbalance becomes a bottleneck because the number of paragraphs is generally smaller than the number of sentences. To deal with this problem, we introduced several cost-sensitive loss functions, namely. focal loss, dice loss, and anchor loss, which were robust for imbalanced classification in BERT. In addition, introducing the threshold-moving technique into the model was effective in estimating paragraph boundaries. As a result of the experiment on three newly created datasets, BERT with dice loss and threshold moving obtained a higher F1 than the original BERT had using cross-entropy loss as its loss function (76% to 80%, 50% to 54%, 59% to 63%).