Modeling the dynamics of vibratory separator of the drum type with concentric arrangement of sieves

Our research focused on analyzing and advancing information technologies to identify ecological parameters in production. The primary goals were to enhance efficiency, reduce waste, and minimize the environmental impact of manufacturing processes. By incorporating the results of the study, we observed and systematized changes occurring in the transition from Industry 4.0 to Industry 5.0. Special attention was given to studying processes and technologies related to the generation of synthetic data and analyzing the implementation of cutting-edge technologies. The research object includes new parameters introduced within the framework of Industry 5.0, encompassing automation and cognitive technologies. Our scientific interests also extended to synthetic data used in modeling various production processes, including optimizing device performance in manufacturing and forecasting abnormal situations in industrial equipment operations. The subject of the research involves algorithms for generating synthetic data and methods for validating them to ensure their statistical similarity to real-world data. During the study, we also analyzed the impact of artificial intelligence implementation on improving the efficiency and adaptability of manufacturing systems.

Teaching of modern cybersecurity specialists should be up to date and use the newest methods and methodologies in universities as the IT industry is rapidly growing and constantly changing. A good idea is to use methods of management in IT companies as methods for current knowledge teaching of university students. It is also worth engaging students not only in educational international projects but the research projects as well. This work analyzes the method for teaching students, and the Scrum methodology was selected and implemented for educational and research projects. Students participated in both projects, however, Scrum models should be different for them and this is illustrated in the paper. The visualization of collected statistical data of the performed educational project illustrated distributions of students by specialization and by marks. The distributions by marks showed that using the Scrum model for the teaching course significantly increases the marks compared with the average level marks of the students in their specializations.

One of the key barriers to neural network adoption is the lack of computational resources and high-quality training data—particularly for unique objects without existing datasets. This research explores methods for generating realistic synthetic images that preserve the visual properties of target objects, ensuring their similarity to real-world appearance. We propose a flexible approach for synthetic data generation, focusing on improved accuracy and adaptability. Unlike many existing methods that rely heavily on specific generative models and require retraining with each new version, our method remains compatible with state-of-the-art models without high computational overhead. It is especially suited for user-defined objects, leveraging a 3D representation to preserve fine details and support integration into diverse environments. The approach also addresses resolution limitations by ensuring consistent object placement within high-quality scenes.

The article explores fundamental techniques for converting text into numerical data for machine learning algorithms. It meticulously examines various methods, including word vector representation via neural networks like Word2Vec, and explains the principles behind linear models such as logistic regression and support vector machines. Convolutional neural networks (CNN) and long short-term memory (LSTM) methods are also discussed, covering their components, mechanisms, and training processes. The research extends to developing and testing software for spam detection, hate speech identification, and recognizing offensive language. Using two datasets—one for labeled text messages and another for Twitter posts—the study analyzes data to address challenges like imbalanced data. A comparative analysis among linear models, deep neural networks, and single-layer models, using pre-trained bidirectional encoder representations from transformers (BERT) network, reveals promising results. The convolutional neural network stands out with a remarkable accuracy of 0.95. The study also adapts neural network architectures for hate speech and offensive language classification.