This article considered the problem of determining the creditworthiness of an enterprise operating in the field of trade and services. The assessment of the creditworthiness of borrowers, particularly small businesses, needs to be more careful: the level of development of small enterprises and their specific activities must be considered, as well as the uncertainty in obtaining any financial result. A method for assessing the creditworthiness of enterprises (trade and services) is proposed, based on the use of the mathematical apparatus of the theory of fuzzy sets. This article analyzes the indicators of industry and regional specifics, indicators of the activity of a small enterprise, and financial and economic indicators typical for the service sector and trade. The rules on the basis of which decisions are made are formed in the form of logical formulas containing parameters. In its most general form, one parameter is predicted, called the creditworthiness index, which varies from 0 to 1 and has a natural interpretation. On the basis of the proposed method, examples of calculating the assessment of the creditworthiness of enterprises operating in the field of trade and services are given. The proposed scientific approach can be used as a basis for creating expert decision support systems for lending to small businesses.

Fire detection is an important task in the field of safety and emergency prevention. In recent years, deep learning methods have shown high efficiency in solving various computer vision problems, including detecting objects in images. In this paper, monitoring wildfires was considered, which allows you to quickly respond to them and prevent their spread using deep learning methods. For the experiment, images from the satellite and images from the FireWatch sensor were taken as initial data. In this work, the deep learning algorithms you only look once (YOLO), convolutional neural network (CNN), and fast recurrent neural network (FastRNN) were considered, which makes it possible to determine the accuracy of a natural fire. As a result of the experiments, an automated fire recognition algorithm using YOLOv4 deep learning methods was created. It is expected that the results of the study will show that deep learning methods can be successfully applied to detect fire in images. This may lead to the development of automated monitoring systems capable of quickly and reliably detecting fire situations, which will help improve safety and reduce the risk of fires.

Modern developments in the fields of natural language processing (NLP) and computer vision (CV) emphasize the increasing importance of generating images from text descriptions. The presented article analyzes and compares two key methods in this area: generative adversarial network with conditional latent semantic analysis (GAN-CLS) and ultra-long transformer network (XLNet). The main components of GAN-CLS, including the generator, discriminator, and text encoder, are discussed in the context of their functional tasks—generating images from text inputs, assessing the realism of generated images, and converting text descriptions into latent spaces, respectively. A detailed comparative analysis of the performance of GAN-CLS and XLNet, the latter of which is widely used in the organic light-emitting diode (OEL) field, is carried out. The purpose of the study is to determine the effectiveness of each method in different scenarios and then provide valuable recommendations for selecting the best method for generating images from text descriptions, taking into account specific tasks and resources. Ultimately, our paper aims to be a valuable research resource by providing scientific guidance for NLP and CV experts.

The research is aimed at developing a prototype of a decision support information system for managers of a company operating in the real estate rental industry. The system provides tools for data analysis, the use of mathematical models and expert knowledge to solve complex problems. The work analyzes the practical aspects of the design and use of decision support systems and formulates the requirements for the functionality of the system being developed. The Python programming language was used for implementation. The prototype includes machine learning models, expert systems, user interface and reports. Linear regression, data clustering density-based spatial clustering of applications with noise (DBSCAN) and backpropagation methods were implemented to train the classifying perceptron. The developed tool represents a significant contribution to the field of decision support, providing unique analysis and forecasting capabilities in the dynamic real estate rental environment. This prototype is an innovative solution that promotes effective management and strategic decision making in complex real estate business scenarios.

This article presents a comprehensive comparative analysis of two advanced hybrid machine learning approaches for keyword extraction: bidirectional encoder representations from transformers (BERT) combined with autoencoder (AE) and term frequency-inverse document frequency (TF-IDF) combined with autoencoder. The research targets the task of semantic analysis in text data to evaluate the effectiveness of these methods in ensuring adequate keyword coverage across diverse text corpora. The study delves into the architecture and operational principles of each method, with a particular focus on the integration with autoencoders to enhance the semantic integrity and relevance of the extracted keywords. The experimental section provides a detailed performance analysis of both methods on various text datasets, highlighting how the structure and semantic richness of the source data influence the outcomes. The evaluation methodology includes precision, recall, and F1-score metrics. The paper discusses the advantages and disadvantages of each approach and their suitability for specific keyword extraction tasks. The findings offer valuable insights for the scientific community, aiding in the selection of the most appropriate text processing method for applications requiring deep semantic understanding and high accuracy in information extraction.

This article is dedicated to the development and investigation of methods for automatic object recognition using artificial intelligence and convolutional neural networks. A standard dataset for object recognition, including images of various types, was used as the experimental base, allowing the creation of a model capable of effectively classifying objects under various conditions, such as changes in lighting, viewing angles, and image quality. The methodology includes data normalization and augmentation, stratified dataset splitting, and model architecture optimization to ensure a balance between computational efficiency and classification accuracy. The developed convolutional neural network features a layered architecture with activation functions and regularization methods, enabling the model to remain robust and adaptive. The results of the study demonstrated the high accuracy and reliability of the proposed model. The analysis of classification errors identified challenges related to the recognition of visually similar objects and proposed solutions to minimize them. This work emphasized the significance of using artificial intelligence and convolutional neural networks for automating object recognition, opening new perspectives for their application in intelligent systems and high-precision technologies.