https://repository.hneu.edu.ua/handle/123456789/140 Sun, 26 Apr 2026 15:51:20 GMT 2026-04-26T15:51:20Z https://repository.hneu.edu.ua/handle/123456789/39691 Назва: Methods of automation of software development processes for the internet of things based on artificial intelligence Автори: Fedorchenko V. Короткий огляд (реферат): This section of the monograph addresses the challenges artificial intelligence (AI) has significantly transformed the development process in the Internet of Things (IoT). AI technologies offer powerful solutions for automating all aspects of IoT software development, ensuring efficiency and scalability. This study delves into evolving automation approaches, focusing on leveraging AI to streamline IoT software development. The study highlights the need for automation and identifies key areas where AI can be integrated to optimize development workflows and reduce human intervention. Thu, 01 Jan 2026 00:00:00 GMT https://repository.hneu.edu.ua/handle/123456789/39691 2026-01-01T00:00:00Z https://repository.hneu.edu.ua/handle/123456789/39684 Назва: Intelligent optimization of high-concurrency distributed systems Автори: Holubnychyi D. Короткий огляд (реферат): This section of the monograph addresses the challenges of high-load e-commerce platforms under conditions of peak traffic and increasing business complexity. The limitations of monolithic architectures are analyzed, including latency, lock contention, and database overload. A solution based on microservice architecture, multi-tier caching, elastic scaling, and intelligent resource management is proposed. The study justifies dynamic performance optimization considering the constraints of the CAP theorem. The results demonstrate improved system responsiveness, stability, and traffic monetization efficiency. The proposed approach is applicable to other distributed systems with a high level of parallelism, providing a basis for designing scalable and resilient architectures. Thu, 01 Jan 2026 00:00:00 GMT https://repository.hneu.edu.ua/handle/123456789/39684 2026-01-01T00:00:00Z https://repository.hneu.edu.ua/handle/123456789/39275 Назва: Сучасні інформаційні системи та технології в цифровому суспільстві : матеріали Міжнародної науково-практичної конференції, 16 – 17 квітня 2026 р.: тези доповідей. Короткий огляд (реферат): Наведені тези пленарних та секційних доповідей за теоретичними та практичними результатами наукових досліджень і розробок. Представлені результати теоретичних та практичних досліджень стосовно галузі комп’ютерних наук, інженерії програмного забезпечення, кібербезпеки, а також cистем та технологій інтелектуальної обробки даних. Thu, 01 Jan 2026 00:00:00 GMT https://repository.hneu.edu.ua/handle/123456789/39275 2026-01-01T00:00:00Z https://repository.hneu.edu.ua/handle/123456789/39145 Назва: Development and research of multimodal neural architectures for heterogeneous unbalanced data in classification tasks Автори: Minukhin S.; Rudoi V. Короткий огляд (реферат): The article presents a comprehensive study of modern multimodal neural architectures for integrating heterogeneous and partially unbalanced data in classification tasks. It considers early and late fusion approaches, hybrid architectures with cross-modal attention, and transformers that allow the formation of consistent latent spaces of visual, auditory, and textual features. Particular attention is paid to contrastive learning (CLIP-like approaches, multimodal InfoNCE), which ensures semantic consistency of representations and improves classification accuracy in the presence of uneven data distribution and rare classes. A model is proposed that combines early and late fusion with cross-modal attention and contrastive learning to form a coherent joint latent space. Features of each modality are processed by specialized encoders, and fusion is performed with adaptive weighting, which minimizes the impact of heterogeneous data imbalance and enables the efficient processing of signals of different natures and intensities. The use of pruning, quantization, and knowledge distillation has reduced computational costs without losing accuracy, ensuring stable model performance in real-world streaming scenarios with limited resources. The results of applying the proposed model to the BDD100K and CMU-MOSEI datasets confirmed the model's high efficiency in processing heterogeneous and unbalanced data. For BDD100K, Accuracy 0.953, F1-score 0.956, ROC-AUC 0.947 were achieved, and the integral indicators Micro F1, Macro F1, and Weighted F1 were 0.953, 0.949, and 0.955, respectively; For CMU-MOSEI, Accuracy 0.956, F1-score 0.969, ROC-AUC 0.968, and the integral indicators Micro F1, Macro F1, and Weighted F1 were 0.956, 0.962, and 0.968, respectively. A comparative analysis with classical feature concatenation approaches, recent State-of-the-Art multimodal fusion models, and AutoML-based solutions demonstrated that the proposed architecture consistently outperforms existing methods. In particular, the model improves classification accuracy by approximately 2–4% compared to recent SOTA architectures and provides more stable F1-scores for minority classes. A comparison with the AutoML-based framework B-T4SA also confirms the robustness of the proposed approach. These results demonstrate that the developed model ensures higher classification consistency for both frequent and rare classes under heterogeneous and imbalanced data conditions. Thu, 01 Jan 2026 00:00:00 GMT https://repository.hneu.edu.ua/handle/123456789/39145 2026-01-01T00:00:00Z