Radio Electronics, Computer Science, Control最新文献

{"title":"STEWART PLATFORM DYNAMICS MODEL IDENTIFICATION","authors":"V. Zozulya, S. Osadchy, S. N. Nedilko","doi":"10.15588/1607-3274-2024-1-22","DOIUrl":"https://doi.org/10.15588/1607-3274-2024-1-22","url":null,"abstract":"Context. At the present stage, with the current demands for the accuracy of motion control processes for a moving object on a specified or programmable trajectory, it is necessary to synthesize the optimal structure and parameters of the stabilization system (controller) of the object, taking into account both real controlled and uncontrolled stochastic disturbing factors. Also, in the process of synthesizing the optimal controller structure, it is necessary to assess and consider multidimensional dynamic models, including those of the object itself, its basic components, controlled and uncontrolled disturbing factors that affect the object in its actual motion. \u0000Objective. The aim of the research, the results of which are presented in this article, is to obtain and assess the accuracy of the Stewart platform dynamic model using a justified algorithm for the multidimensional moving object dynamics identification. \u0000Method. The article employs a frequency-domain identification method for multidimensional stochastic stabilization systems of moving objects with arbitrary dynamics. The proposed algorithm for multidimensional moving object dynamics model identification is constructed using operations of polynomial and fractional-rational matrices addition, multiplication, Wiener factorization, Wiener separation, and determination of dispersion integrals. \u0000Results. As a result of the conducted research, the problem of identifying the dynamic model of a multidimensional moving object is formalized, illustrated by the example of a test stand based on the Stewart platform. The outcomes encompass the identification of the dynamic model of the Stewart platform, its transfer function, and the transfer function of the shaping filter. The verification of the identification results confirms the sufficient accuracy of the obtained models. \u0000Conclusions. The justified identification algorithm allows determining the order and parameters of the linearized system of ordinary differential equations for a multidimensional object and the matrix of spectral densities of disturbances acting on it under operating conditions approximating the real functioning mode of the object prototype. The analysis of the identification results of the dynamic models of the Stewart platform indicates that the primary influence on the displacement of the center of mass of the moving platform is the variation in control inputs. However, neglecting the impact of disturbances reduces the accuracy of platform positioning. Therefore, for the synthesis of the control system, methods should be applied that enable determining the structure and parameters of a multidimensional controller, considering such influences.","PeriodicalId":518330,"journal":{"name":"Radio Electronics, Computer Science, Control","volume":"84 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140754764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"REALIZATION OF THE DECISION-MAKING SUPPORT SYSTEM FOR TWITTER USERS’ PUBLICATIONS ANALYSIS","authors":"T. Batiuk, D. Dosyn","doi":"10.15588/1607-3274-2024-1-16","DOIUrl":"https://doi.org/10.15588/1607-3274-2024-1-16","url":null,"abstract":"Context. The paper emphasizes the need for a decision-making system that can analyze users’ messages and determine the sentiment to understand how news and events impact people’s emotions. Such a system would employ advanced techniques to analyze users’ messages, delving into the sentiment expressed within the text. The primary goal is to gain insights into how news and various events reverberate through people’s emotions. \u0000Objective. The objective is to create a decision-making system that can analyze and determine the sentiment of user messages, understand the emotional response to news and events, and distribute the data into clusters to gain a broader understanding of users’ opinions. This multifaceted objective involves the integration of advanced techniques in natural language processing and machine learning to build a robust decision-making system. The primary goals are sentiment analysis, comprehension of emotional responses to news and events, and data clustering for a holistic view of user opinions. \u0000Method. The use of long-short-term memory neural networks for sentiment analysis and the k-means algorithm for data clustering is proposed for processing large volumes of user data. This strategic combination aims to tackle the challenges posed by processing large volumes of user-generated data in a more nuanced and insightful manner. \u0000Results. The study and conceptual design of the decision-making system have been completed and the decision-making system was created. The system incorporates sentiment analysis and data clustering to understand users’ opinions and the sentiment value of such opinions dividing them into clusters and visualizing the findings. \u0000Conclusions. The conclusion is that the development of a decision-making system capable of analyzing user sentiment and clustering data can provide valuable insights into users’ reactions to news and events in social networks. The proposed use of longshort-term memory neural networks and the k-means algorithm is considered suitable for sentiment analysis and data clustering tasks. The importance of studying existing works and systems to understand available algorithms and their applications is emphasized. The article also describes created and implemented a decision-making system and demonstrated the functionality of the system using a sample dataset.","PeriodicalId":518330,"journal":{"name":"Radio Electronics, Computer Science, Control","volume":"500 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140750895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DEVELOPMENT OF APPLIED ONTOLOGY FOR THE ANALYSIS OF DIGITAL CRIMINAL CRIME","authors":"L. Vlasenko, N. Lutska, N. Zaiets, T. Savchenko, A. A. Rudenskiy","doi":"10.15588/1607-3274-2023-4-17","DOIUrl":"https://doi.org/10.15588/1607-3274-2023-4-17","url":null,"abstract":"Context. A feature of the modern digital world is that crime is often committed thanks to the latest computer technologies, and the work of law enforcement agencies faces a number of complex challenges in the digital environment. The development of information technology and Internet communications creates new opportunities for criminals who use digital traces and evidence to commit crimes, which complicates the process of identifying and tracking them. \u0000Objective. Development of an applied ontology for a system for analyzing a digital criminal offense, which will effectively analyze, process and interpret a large amount of digital data. It will help to cope with the complex task of processing digital data, and will also help automate the process of discovering new knowledge. \u0000Methods. To build an ontological model as a means of reflecting knowledge about digital crime, information was collected on existing international and domestic classifications. The needs and requirements that must be satisfied by the developed ontology were also analyzed. The creation of an ontological model that reflects the basic concepts, relationships in the field of digital criminal offense was carried out in accordance with a recognized ontological analysis of a specialized subject area. \u0000Results. An applied ontology contains the definition of entities, properties, classes, subclasses, etc., as well as the creation of semantic relationships between them. At the center of the semantics is the Digital Crime class, the problem area of which is complemented by the interrelated classes Intruder, Digital evidence, Types of Crime, and Criminal liability. Such characteristics as motive, type of crime, method of commission, classification signs of digital traces and types of crime, as well as other individual information were assigned to the attributes of the corresponding classes. An ontological model was implemented in OWL using the Protégé software tool. A feature of the implementation of the applied ontology was the creation of SWRL rules for automatically filling in additional links between a class instance. Manual and automatic verification of the ontology showed the integrity, consistency, a high degree of correctness and adequacy of the model. The bugs found were usually related to technical aspects and semantic inconsistencies, which were corrected during further development iterations. \u0000Conclusions. The research confirmed the effectiveness of the developed applied ontology for the analysis of digital criminality, providing more accurate and faster results compared to traditional approaches.","PeriodicalId":518330,"journal":{"name":"Radio Electronics, Computer Science, Control","volume":"2 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140532382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SONGS CONTINUATION GENERATION TECHNOLOGY BASED ON TEST GENERATION STRATEGIES, TEXTMINING AND LANGUAGE MODEL T5","authors":"O. Mediakov, V. Vysotska","doi":"10.15588/1607-3274-2023-4-15","DOIUrl":"https://doi.org/10.15588/1607-3274-2023-4-15","url":null,"abstract":"Context. Pre-trained large language models are currently the driving force behind the development of not only NLP, but also deep learning systems in general. Model transformers are able to solve virtually all problems that currently exist, provided that certain requirements and training practices are met. In turn, words, sentences and texts are the basic and most important way of communication between intellectually developed beings. Of course, speech and texts are used to convey certain emotions, events, etc. One of the main ways of using language to describe experienced emotions is songs with lyrics. However, often due to the need to preserve rhyme and rhyming, the dimensions of verse lines, song structure, etc., artists have to use repetition of lines in the lyrics. In addition, the process of writing texts can be long. \u0000Objective of the study is to develop information technology for generating the continuation of song texts based on the T5 machine learning model with (SA, specific author) and without (NSA, non-specific author) consideration of the author's style. \u0000Method. Choosing a decoding strategy is important for the generation process. However, instead of favoring a particular strategy, the system will support multiple strategies. In particular, the following 8 strategies: Contrastive search, Top-p sampling, Top-k sampling, Multinomial sampling, Beam search, Diverse beam search, Greedy search, and Beam-search multinomial sampling. \u0000Results. A machine learning model was developed to generate the continuation of song lyrics using large language models, in particular the T5 model, to accelerate, complement and increase the flexibility of the songwriting process. \u0000Conclusions. The created model shows excellent results of generating the continuation of song texts on test data. Analysis of the raw data showed that the NSA model has less degrading results, while the SA model needs to balance the amount of text for each author. Several text metrics such as BLEU, RougeL and RougeN are calculated to quantitatively compare the results of the models and generation strategies. The value of the BLEU metric is the most variable, and its value varies significantly depending on the strategy. At the same time, Rouge metrics have less variability, a smaller range of values. For comparison, 8 different decoding methods for text generation, supported by the transformers library, were used. From all the results of the text comparison, it is clear that the metrically best method of song text generation is beam search and its variations, in particular beam sampling. Contrastive search usually outperformed the conventional greedy approach. The top-p and top-k methods are not clearly superior to each other, and in different situations gave different results.","PeriodicalId":518330,"journal":{"name":"Radio Electronics, Computer Science, Control","volume":"17 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140532516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}