Objectives. The aim of the work is to experimentally investigate the effectiveness of ensemble methods for multidimensional text analysis in document categorization tasks using the example of authorship identification. Particular attention is paid to comparing classical machine learning algorithms, their ensembles, and the developed hybrid quantum-classical model.

Methods. The study uses support vector machines, logistic regression, and random forests, as well as an ensemble of these models and a hybrid model of the author's architecture. The proposed hybrid approach combines syntactic analysis based on the support vector method, semantic analysis using the BERT transformer model, and a quantum variational module. Experiments were conducted on different corpora of English texts with varying number of authors. Quality was assessed using accuracy, completeness, and F1-score metrics.

Results. In a series of experiments with a small number of authors, all models showed high accuracy, with the hybrid model achieving the best results (F1 score up to 82.5%). In experiments with a large number of authors, a regular decrease in quality was observed, but the hybrid model demonstrated better stability, outperforming classical ensembles on all corpora. The most significant increase in accuracy was recorded on a complex corpus of short texts (blogs) with a large number of authors.

Conclusion. The hybrid quantum-classical model developed by the authors has proven its effectiveness for author attribution tasks and can be scaled for a wider range of document categorization tasks, especially in conditions of high feature dimensionality and a large number of classes. The use of the quantum module made it possible to identify complex nonlinear dependencies in the data that are inaccessible to traditional approaches. The results obtained open up prospects for the practical use of the proposed approach in text analysis systems, including the processing of short messages and extensive author databases. Further development of the research is related to expanding the set of features, optimizing the architecture of quantum circuits, and adapting the model for use in various application areas.

Objectives. The aim of the study is to develop a method for predicting cancer cell nuclear centers in immunohistochemical fluorescence images using point annotation of nuclear centers.

Methods. Deep learning convolutional neural networks are used in this study.

Results. A method for predicting cancer cell nuclear centers in immunohistochemical fluorescence images of diseased tissues is proposed. The method differs from existing approaches by using point annotation of nuclear centers during the learning process. An algorithm for image pre- and postprocessing has been developed, enabling an end-to-end analysis for images of any dimension.

Conclusion. A method for predicting cancer cell nuclear centers in immunohistochemical fluorescence images has been developed. It has a simple architecture, a small number of trainable parameters, and does not require complex post-processing of analysis results, traditionally involved in semantic segmentation for separating clustered nuclei. The method allows for counting the number of cancer cells per unit area, which in turn makes it possible to assess the extent of the disease. The total analysis time for a 2048×2048 pixel image using the T4 (Google Colab) compute engine averages 750 ms, enabling the analysis of high-dimensional, whole-slide images in a reasonable time.

Objectives. The study aims to analyze the problem of preventive risk management for problematic situations and incidents in the functioning of "smart communities" as nuclear structures of large organizational systems under conditions of global turbulence based on mathematical models using the Wiener integral and Wiener entropy.

Methods. A review of the literature, a method of mathematical modeling using the Wiener integral and Wiener entropy phenomenon are applied for preventive risk management in "smart communities" as nuclear structures of large organizational systems for various purposes under the influence of global turbulence factors.

Results. A general description of the problem of preventive incident risk management in "smart communities" as nuclear structures of organizational systems has been presented. The expediency of using the Wiener integral and Wiener entropy for analysis and preventive risk management in "smart communities" in conditions of systemic turbulence is substantiated. Mathematical models are proposed that provide various stages of preventive risk management for problematic situations and dangerous incidents in "smart communities" within large organizational systems based on the Wiener integral. In particular, it is a risk identification and assessment model based on the Wiener integral, an early detection and forecasting model, and a model for optimizing preventive risk management strategies. In addition, numerical algorithms and model validation are proposed, as well as algorithms for preventive risk management in "smart communities".

Conclusion. The fundamentals of the approach to preventive incident risk management in "smart communities" as nuclear structures of large organizational systems based on the Wiener integral and Wiener entropy have been developed.

Objectives. The aim of the research is to develop an intelligent scheduling system operating locally on the user's equipment without data transmission via Internet.

Methods. This paper examines the problem of ensuring the privacy and autonomy of digital assistants dependent on cloud infrastructure. A client-server architecture is proposed, in which the server component is implemented using the FastAPI framework and an SQLite database, and the client interface is written in JavaScript. Schedule visualization and entry editing are performed through the web interface.

Results. The system's voice pipeline is described: the Porcupine engine is used for activation, and the Faster-Whisper model with int8 quantization is used for transcription. A comparative analysis of the technology stack, ensuring high speech recognition accuracy, is conducted. A hybrid natural language understanding module is developed. RAG technology is implemented, integrating schedule data into the response generation context. Speech synthesis is performed using the Piper neural network, whose execution through ONNX Runtime ensures high processing speed. A heuristic greedy search algorithm for managing time resources has been developed.

Conclusion. The developed system is considered applicable in the corporate sector, where information security and operation in closed network environments are critical.

Objectives. This paper investigates the feasibility of applying a Contest Success Function (CSF) to optimize priority fee expenditures in blockchain networks utilizing priority fee auctions. We analyze the model's ability to describe the relationship between "effort" (bid amount) and the probability of successful transaction inclusion.

Methods. We conducted an experiment to compare the efficiency of the canonical CSF model (Tullock contest strategy) against a baseline strategy – a simple average of the target percentile derived from historical data. Both strategies utilized context gathered from historical datasets to generate bid proposals for the subsequent block. Performance was evaluated based on two primary metrics: the average effort (mean bid size) and the success rate (the percentage of bids successfully landing within the target percentile). The experiment comprised a total of 632 rounds of bid generation.

Results. The experimental trials yielded performance metrics indicating that the canonical CSF model is well-suited for cost optimization in priority fee auctions. Specifically, strategies with decisiveness parameters  and  demonstrated the most favorable results. Furthermore, a positive correlation was observed between the decisiveness parameter  and the strategy's performance; a decrease in the value of  led to a corresponding decline in the strategy's efficiency for cost optimization.

Conclusion. The experimental results demonstrate the overall effectiveness of the canonical CSF for optimizing priority fee expenditures. This approach is particularly relevant for sectors with rapidly advancing blockchain integration, most notably financial services, investment management, and trading. However, it is worth noting that the proposed methodologies are agnostic to specific implementations or projects; they are applicable to any network that implements a transaction prioritization mechanism via additional fees. There remains significant scope for further research, including the introduction of novel performance metrics, the use of more specialized datasets, and the investigation of different historical context window sizes for the model.

Objectives. The aim of this work is to develop and implement a conceptual model of a quantum-secured blockchain by integrating a quantum key distribution mechanism based on the E91 protocol into a classical architecture.

Methods. The vulnerabilities of classical blockchain cryptographic mechanisms to threats posed by quantum computing are considered. To create a resilient architecture, it is proposed to combine the properties of quantum entanglement with classical cryptographic methods. The E91 quantum key distribution protocol, based on quantum entanglement and the Bell inequality test (CHSH test), is used as the foundation. A new field, E91 MAC, is introduced to link blocks in the chain, calculated using the HMAC algorithm from the hash of the previous block with a key generated by the E91 protocol. The Delegated Proof of Stake (DPoS) algorithm is chosen as the consensus mechanism. The software implementation includes simulating the E91 protocol using the IBM Quantum cloud platform and the Qiskit library, as well as deploying a peer-to-peer blockchain network with a CLI interface in Python using TCP sockets.

Results. A conceptual model was developed and a prototype of a quantum-secured blockchain was implemented. A functional peer-to-peer network with the DPoS consensus algorithm and a distributed voting mechanism was created. The successful simulation of the E91 protocol confirmed the possibility of generating and verifying a quantum key. The fundamental feasibility of integrating a quantum authentication mechanism (E91 MAC) into the block creation and validation process was demonstrated.

Conclusion. The proposed hybrid architecture demonstrates a novel approach to blockchain security, based not only on computational complexity but also on the fundamental laws of quantum mechanics. The integration of the E91 protocol and the DPoS mechanism provides potential resilience to quantum attacks and high network energy efficiency. The software prototype confirms the practical feasibility of the concept for creating secure next-generation distributed ledgers.