DSpace Фонд:https://repository.hneu.edu.ua/handle/123456789/1402026-06-02T16:38:42Z2026-06-02T16:38:42ZNeuro-symbolic Formal Verification of Culinary instructions via ontology-grounded constraint satisfactionShaposhnyk M. V.Minukhin S. V.https://repository.hneu.edu.ua/handle/123456789/402702026-06-02T10:40:58Z2026-01-01T00:00:00ZНазва: Neuro-symbolic Formal Verification of Culinary instructions via ontology-grounded constraint satisfaction
Автори: Shaposhnyk M. V.; Minukhin S. V.
Короткий огляд (реферат): This study proposes the «Formal-of-Thought» (FoT) approach—an architecture that shifts artificial intelligence from passive generation to active formal verification using the FoodOn ontology. FoT uses large language models (LLMs) as a specification compiler, «mapping» DenseNet-121 features to FoodOn proofs using the «Retrieval-Augmented Generation» method. Safety constraints are formulated as logical predicates, and compliance with them is verified using an SMT solver.2026-01-01T00:00:00ZIntegration of large language models and sensor data in recommendation systems for personalized physiological and dietary monitoringMinukhin S. V.Khaustov D. A.https://repository.hneu.edu.ua/handle/123456789/402692026-06-02T10:42:22Z2026-01-01T00:00:00ZНазва: Integration of large language models and sensor data in recommendation systems for personalized physiological and dietary monitoring
Автори: Minukhin S. V.; Khaustov D. A.
Короткий огляд (реферат): This study proposes the «Formal -of-Thought» (FoT)—an architecture that shifts artificial intelligence from passive generation to active formal reasoning. This approach uses the Health-LLM principle to convert numerical sensor data in the form of time series into textual descriptions based on an individual user profile. It combines this with the PHIA agent, which utilizes multi-step ReAct reasoning, Python code generation (Pandas), few-shot learning via embedded sentence-T5 and K-means clustering, as well as the GPT-4 Text -to-SQL method with few-shot learning and RAG for heterogeneous data.2026-01-01T00:00:00ZMinimization of total task tardiness using a ranking-based method with sorting rulesMinukhin S. V.https://repository.hneu.edu.ua/handle/123456789/402672026-06-02T10:42:12Z2026-01-01T00:00:00ZНазва: Minimization of total task tardiness using a ranking-based method with sorting rules
Автори: Minukhin S. V.
Короткий огляд (реферат): This paper proposes a model of general tardiness in task execution based on a graph G, in which each vertex corresponds to a task, and each edge (i, j) is characterized by a weight Tj = max(0, Cj − dj), where Cj denotes the completion time and dj denotes the execution time of task j. A distinctive feature of this problem is that the weights of the graph’s edges emanating from an arbitrary vertex Ji are not constant values but depend on the order in which the vertices leading to vertex Ji are traversed, since this determines the value of Cj, which is defined as the sum of the durations of the operations preceding the execution of operation Ji. This problem can be reduced to finding the shortest Hamiltonian path in the graph. A method is proposed to solve this problem based on randomly determining the initial order of the vertices in the graph.2026-01-01T00:00:00ZТехнологія Django у системах електронної комерціїБілоус А. В.Карпенко М. Ю.https://repository.hneu.edu.ua/handle/123456789/402592026-06-02T08:58:19Z2026-01-01T00:00:00ZНазва: Технологія Django у системах електронної комерції
Автори: Білоус А. В.; Карпенко М. Ю.
Короткий огляд (реферат): У роботі проведено порівняльний аналіз фреймворку Django з альтернативними платформами веб-розробки за критеріями функціональності, безпеки, швидкості створення застосунків та підтримки баз даних. На основі результатів порівняння обґрунтовано доцільність використання Django для розробки систем електронної комерції. Показано, що Django є ефективною платформою для створення сучасних систем електронної комерції в умовах цифровізації бізнесу та нестабільного середовища.2026-01-01T00:00:00Z