Neural network models for situation similarity assessment in hybrid-CBR

Glukhikh, Igor; Чернышева, Т. В.; Glukhikh, Dmitry

doi:10.3233/jifs-221335

Cited by 4 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The difference between the abbreviated text from the training sample and the predicted one is computed. The training should be continued until the difference between the reference result and the predicted one reaches a minimum [12].…”

Section: Analysis and Implementation Of The Autoreference Systemmentioning

confidence: 99%

Application of speech recognition and autoreference models for logging tasks

Shentsov,

Chernysheva,

Barskaya

2024

Third International Conference on Optics, Computer Applications, and Materials Science (CMSD-III 2023)

View full text Add to dashboard Cite

Protocols play an important role in decision-making across many fields. The effectiveness of the work of various organizations and teams directly depends on their quality and speed of writing. Therefore, automating this process is of utmost importance today. This article proposes an approach to address the issue of logging by processing existing audio recordings of meetings or events and using an ensemble of artificial intelligence models, including a pre-trained acoustic speech recognition model based on the "Quartznet" architecture, a language N-gram model implemented using the "KenLM" tool, and a Russian-language model "RuBERT" retrained for extractive abstracting. The algorithms of these models' operation are examined, and the processes of data collecting and retraining, as well as the implementation of the selected models, are described. Quality metrics for the speech recognition system are compared, and an analysis of the implemented systems is conducted. To utilize the developed system an HTTP web server was deployed via an API. The final results of the developed automatic logging system, capable of extracting timestamps of spoken words, highlighting speakers in audio recordings, and reducing the resulting text to a specified percentage are demonstrated.

show abstract

Section: Analysis and Implementation Of The Autoreference Systemmentioning

confidence: 99%

Application of speech recognition and autoreference models for logging tasks

Shentsov,

Chernysheva,

Barskaya

2024

Third International Conference on Optics, Computer Applications, and Materials Science (CMSD-III 2023)

View full text Add to dashboard Cite

show abstract

“…We are increasingly witnessing the emergence of new possibilities in the field of artificial intelligence (AI). AI models offer complex, comprehensive solutions to a variety of tasks, from classifying toxic comments on social media to developing systems with extensive knowledge bases [1][2]. Such models not only improve efficiency, but also open up new opportunities for innovation and growth.…”

Section: Introductionmentioning

confidence: 99%

Creation of a painting dataset for use in artificial intelligence tasks

Barskaya,

Chernysheva,

Krupkin

et al. 2024

Third International Conference on Optics, Computer Applications, and Materials Science (CMSD-III 2023)

View full text Add to dashboard Cite

This article describes the creation of a custom thematic dataset for generating descriptions of artistic works (paintings). An algorithm for forming a dataset using deep learning models is proposed. Initially, an analysis of scientific publications was conducted to identify key features important for the perception of works of art. Then, relevant datasets with descriptions in various languages were extracted from various sources, including the collections of major museums. After preliminary processing and filtering of irrelevant features, the data were combined into a single dataset. All text data were translated into Russian. 7 key features and 21 fields were selected for each painting image with corresponding descriptive information. As a result, a new dataset consisting of 10,000 images of paintings and annotations to them was formed.

show abstract

“…В работе [32] представлены результаты исследования предложенных моделей M1, M2, M3 для вычисления Sim. В этой статье мы приводим результаты дальнейших исследований, где в целях улучшения метрик качества рассматриваются ансамбли нейросетевых моделей.…”

Section: Introductionunclassified

Сравнение И Отбор Ситуаций В Системах Вывода Решений На Прецедентах Для «умной» Фермы

Glukhikh,

Prokhoshin,

Glukhikh

2023

Self Cite

View full text Add to dashboard Cite

The trend of development of smart farms is aimed at their becoming fully autonomous, robotic enterprises. The prospects for the intellectualization of agricultural production and smart farms, in particular, today are associated with the development of technology systems used to detect, recognize complex production situations and search for effective solutions in these situations. The article presents the concept of such a decision support system on smart farms using the method of decision support based on case-based reasoning - CBR system. Its implementation requires a number of non-trivial tasks, which include, first of all, the tasks of formalizing the presentation of situations and creating methods for comparing and retrieving situations from the KB on this basis. In this study, a smart farm is presented as a complex technological object consisting of interrelated components, which are the technological subsystems of a smart farm, the products produced, the objects of the operational environment, as well as the relationships between them. To implement algorithms for situational decision-making based on precedents, a formalized representation of the situation in the form of a multivector is proposed. This allowed us to develop a number of models of the trained similarity function between situations. The conducted experiments have shown the operability of the proposed models, on the basis of which ensemble architecture of a neural network has been developed for comparing situations and selecting them from the knowledge base in decision-making processes. Of practical interest is monitoring the condition of plants by their video and photo images, which allows detecting undesirable plant conditions (diseases), which can serve as a signal to activate the process of searching for solutions in the knowledge base.

show abstract

Neural network models for situation similarity assessment in hybrid-CBR

Cited by 4 publications

References 23 publications

Application of speech recognition and autoreference models for logging tasks

Application of speech recognition and autoreference models for logging tasks

Creation of a painting dataset for use in artificial intelligence tasks

Сравнение И Отбор Ситуаций В Системах Вывода Решений На Прецедентах Для «умной» Фермы

Contact Info

Product

Resources

About