This article reviews the questions and directions of integration of artificial neural networks with knowledge bases. Two main directions of integration are considered: the inputs and outputs of artificial neural network to use integration of knowledge bases and artificial neural networks for solutions of application problems; by artificial neural network representation on the basis of ontological structures and its interpretation by means of knowledge processing in the knowledge base providing an intelligent environment for the development, training and integration of different artificial neural networks compatible with knowledge bases. The knowledge bases that are integrated with artificial neural networks are built on the basis of homogeneous semantic networks and multiagent approach to represent and process knowledge. An ontological model for representing artificial neural networks and their specifications within the framework of the model of unified semantic representation of knowledge is proposed. It is distinguished by the ability to represent artificial neural networks, its dynamics and other types of knowledge, including the specifications of artificial neural networks, as the common language for the representation of knowledge with a common theoreticalmodel semantics. A multiagent model for solving problems using artificial neural networks and other types of knowledge is proposed. It is distinguished by the interaction of agents in accordance with a given temporal model through a common memory that stores knowledge integrated into a single knowledge base.
The purpose of the work is to confirm experimentally theoretical estimates for time complexity of operations of the string processing model linked with the metric space for solving data processing problems in knowledge-driven systems including the research and comparison of the operation characteristics of these operations with the characteristics of similar operations for the most relevant data structures. Integral and unit testing were used to obtain the results of the performed computational experiments and verify their correctness. The C \ C++ implementation of operations of the string processing model was tested. The paper gives definitions of concepts necessary for the calculation of metric features calculated over strings. As a result of the experiments, theoretical estimates of the computational complexity of the implemented operations and the validity of the choice of parameters of the used data structures were confirmed, which ensures near-optimal throughput and operation time indicators of operations. According to the obtained results, the advantage is the ability to guarantee the time complexity of the string processing operations no higher than O at all stages of a life cycle of data structures used to represent strings, from their creation to destruction, which allows for high throughput in data processing and responsiveness of systems built on the basis of the implemented operations. In case of solving particular string processing problems and using more suitable for these cases data structures such as vector or map the implemented operations have disadvantages meaning they are inferior in terms of the amount of data processed per time unit. The string processing model is focused on the application in knowledge-driven systems at the data management level.
АннотацияВ данной работе предлагается подход к проектированию предприятий рецептурного производства на основе формальных онтологий на примере белорусского предприятия ОАО «Савушкин продукт». Рассмотрены вопросы формализации стандартов, на основе которых осуществляется деятельность производства на примере стандарта ISA-88. Предлагается рассматривать стандарт ISA-88 как онтологию предметной области рецептурного производства, записанную на естественном языке. Формализация стандарта, таким образом, состоит в отображении структуры и содержания исходного текста документа стандарта на иерархию предметных областей и соответствующих им онтологий. Формальное представление стандарта является основой корпоративной интеллектуальной системы и позволяет автоматизировать решение целого ряда задач, включая информационное обслуживание сотрудников, приведение производства в соответствие стандартам и формальную оценку такого соответствия. Принципиально новым в данной работе является применение в качестве основы для построения интеллектуальной системы предприятия формального представления промышленного стандарта, выполненного на базе графодинамических моделей представления и обработки знаний.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.