Computational linguistics and intelligent systems
Permanent URI for this communityhttps://ena.lpnu.ua/handle/ntb/39447
Browse
Item A method of construction of automated basic ontology(National Technical University «KhPI», 2017) Lytvyn, Vasyl; Vysotska, Victoria; Wojcik, Waldemar; Dosyn, Dmytro; Lviv Polytechnic National University; Institute of Electronics and Information Technology, Lublin University of Technology; Systems Analysis Laboratory, Karpenko Physico-Mechanical Institute of the NAS of UkraineThe paper describes an approach to development of a computer system that automatically constructs an ontology base. Basic modules of the system and its operation are described, as well as the choice of software tools for implementation. Application of the proposed system allows to fill the domain ontology in an automatic mode. Therefore, this paper introduces an approach to development of an automated basic ontology composition. An architecture of synthesis of the ontology system is created using CROCUS (Cognition Relations or Concepts Using Semantics) software model. The main system modules and their functions are described. A decision of SDK for system realization is justified. Application of the proposed system can fill an ontology of subject area automatically.Item A sensor of solar panels imitation(онлайн, 2020) Pliasun BohdanModern life is impossible without energy, which helps to create cosy and comfortable things necessary for human existence. Traditional energy sources (better known as thermal ones) convert natural resources into energy. This type of energy source is used most of all. But its biggest disadvantage is that sooner or later the deposits are depleted and humanity will have to find new ways to get energy for its needs. Scientists suggest looking for another ways to get energy. And here came the help of alternative energy, which uses the energy of the wind, the sun, the ebb and the flow, and even thermal energy of the planet. The last one looks pretty lucrative because it uses the planet's heat. But, unfortunately, its usage leads to disruption of the Earth's heat balance and greatly affects its ecosystem. After using the equipment that produces such an electricity in the places where it was installed, it disturbs the normal natural balance and increases the lack of appropriate conditions for the development of nature. Scientists are increasingly turning to the development of equipment capable of op erating on solar energy with minimal damage to nature.Item A(n) Assumption in machine learning(Lviv Politechnic Publishing House, 2019-04-18) Klyushin, Dmitry; Lyashko, Sergey; Zub, Stanislav; Taras Shevchenko National University of KyivThe commonly used statistical tools in machine learning are two-sample tests for verifying hypotheses on homogeneity, for example, for estimation of corpushomogeneity, testing text authorship and so on. Often, they are effective only for sufficiently large sample (n> 100) and have limited application in situations where the size of samples is small (n < 30). To solve the problem for small samples, methods of reproducing samples are often used: jackknife and bootstrap. We propose and investigate a family of homogeneity measures based on A(n) assumption that are effective both for small and large samples.Item Algorithm of text recognizing in Ukrainian on the video mode(онлайн, 2020) Tymoshenko Kateryna; Vysotska VictoriaOCR technology for recognizing text in Ukrainian is imperfect. The Android operating system contains a character repository of many languages, but not the Ukrainian. Therefore, we propose a method and algorithm for recognizing text in Ukrainian and modifying it for video mode.[1].Item An Algorithm of Automated Identification of the Noun “думка” + Verb and Verb + Noun “думка” Metaphorical Model Meaning (Based on the Novel Музей покинутих секретів Written by Oksana Zabuzhko)(2021-05-04) Karasov, Vitalii; Levchenko, Olena; Lviv Polytechnic National UniversityThe principles of automated identification of metaphoric combination of Noun “думка” + Verb and vice versa have been described in the thesis. The research has been carried out on the novel Музей покинутих секретів written by Oksana Zabuzhko and Grac v.10 corpus that served as the source of the research material. According to the search results in the text corpora, it was found that with the help of the models of two groups, both figurative and direct meaning can be realized. It should be noted that basically 71% of cases has figurative meaning and only rarely we come across a direct one. Such a feature of the considered metaphor’s models is due to the fact that the concept of “думка” is an abstract in itself. Due to this, the search field is significantly expanded and does not require preliminary screening of direct meanings of the lexeme “думка”. It should also be noted that the noun “думка” has such a semantic category t:ment r:abstr.Item An Approach to Extraction of Verb-Noun Patterns from News Data Stream(2021-05-04) Romanova, Uliana; Petrasova, Svitlana; National Technical University “Kharkiv Polytechnic Institute”The paper describes an approach to extraction of Verb-Noun patterns from news data stream. The linguistic tagging, namely algorithms for parsing, and methods for extracting collocations are analyzed. The algorithm for the automatic extraction of Verb collocations from the designed corpus of news texts is proposed. The Stanford Universal Dependencies parser is applied to identify Verb-Noun patterns. Then t-score is implemented for extracting collocations.Item An index of authors’ popularity for Internet encyclopedia(National Technical University «KhPI», 2017) Lande, Dmitry; Andrushchenko, Valentyna; Balagura, Iryna; Institute for information Recording of NAS of Ukraine, KyivThe new index of the author‘s popularity estimation is represented in the paper. The index is calculated on the basis of Wikipedia encyclopedia analysis (Wiki-Index–WI). Unlike the conventional existed citation indices, the suggested mark allows to evaluate not only the popularity of the author, as it can be done by means of calculating the general citation number or by the Hirsch index, which is often used to measure the author‘s research rate. The index gives an opportunity to estimate the author‘s popularity, his/her influence within the sought-after area ―knowledge area‖ in the Internet – in the Wikipedia. There are proposed algorithms and the technique of the Wiki-Index calculation through the network encyclopedia sounding, the exemplified calculations of the index for the prominent researchers, and also the methods of the information networks formation – models of the subject domains by the automatic monitoring and networks information reference resources analysis.Item An overview of existing automated methods definition of the author of the written text identification characteristics(онлайн, 2020) Sliusarieva Yuliia; Borysova Natalia; Melnyk KarinaAbstract. The paper presents an overview of the existing methods for solving the problem of automated identification of the author of the written text: substantiated the relevance of the research topic, analyzed the existing methods of solving the task, identified their advantages and disadvantages, selected the direction of further program implementation.Item An Overview of Existing Machine Learning Methods for Gender Classification of Names(2021-05-04) Shleiko, Anna; Borysova, Natalia; Kochuieva, Zoia; Melnyk, Karina; National Technical University "Kharkiv Polytechnic Institute"The paper presents an overview of the existing machine learning methods for solving the problem of gender classification of the authors of the written texts by names: substantiates the relevance of the research topic, analyzes the existing methods of solving the task and selects the direction of further research.Item Analysis of existing German Corpora(National Technical University «KhPI», 2017) Olifenko, Inna; Borysova, NataliaItem Analysis of game process information flows(онлайн, 2020) Mykytin Nataliya; Lozytskyi Oleksandr; Oleksiv NazarItem Analysis of Vulnerabilities of IoT-Devices and Methods of Their Elimination(2021-05-04) Liashenko, Oleksii; Kazmina, Darina; Rosinskiy, Dmytro; Dukh, Yana; Kharkiv National University of Radio-ElectronicsRelevance and the problem setting: at present, vulnerabilities in the firmware of IoT-devices pose a serious threat, as attackers, who at first have exploited the vulnerabilities, gain remote access to devices which allows them to form botnets that are then used to capture new devices or organize serious DDos attacks. Therefore, currently, there is an urgent need to increase the effectiveness of vulnerability detection methods in the firmware. The purpose of this work is to analyze and define the term “vulnerability”, to provide the classification of vulnerabilities of IoT-devices, the causes of vulnerabilities of IoT-devices, to analyze the stages of vulnerability detection, and to present the example of a search algorithm for vulnerable IoT-devices.Item Analytical service for choosing a medical drug(онлайн, 2020) Kleban Kateryna; Andrunyk Vasyl; Kempnyk Roman; Chyhura VladyslavTechnological progress has greatly simplified the life of mankind. At the moment, we have every opportunity to upgrade and develop something that would not simply be an application for spending time or playing with incredible graphics, but something really useful, something that helps people understand their most important problem in life - health. Therefore, in the future we will discuss the creation of a system for choosing medicines, which will allow ordinary users, people interested in medicine, interns and doctors to find the necessary information about the medicines that exist in Ukraine, detailed information about them, their analogues, prices and feedbacks. My task was to make it innovative and easy to use.Item Application of the method of hierarchy analysis for decision making in conditions of definition(онлайн, 2020) Mahis OksanaPerson makes decisions based on known information and using a certain method every day. The hierarchy analysis method is viewed as the general theory of measurement; it is used to derive the ratio scales from both discrete and continuous pair comparisons in multilevel hierarchical structures. Comparisons can be made on the basis of real or alleged values reflecting possible preferences. The method is widely used in problems of multi-criteria decision making, strategic planning, forecasting, and even in conflict resolution problems. Moreover, it is intended for the analysis of nonlinear structures to perform both deductive and inductive inferences.Item Applying Recurrence Plots to Classify Time Series(2021-05-04) Kirichenko, Lyudmyla; Radivilova, Tamara; Stepanenko, Juliia; Kharkiv National University of Radio ElectronicsThe article describes a new approach to the classification of time series based on the construction of their recurrence plots. After transforming the time series into recurrence plots, two approaches are applied for classification. In the first case, quantitative recurrence characteristics are used for classification as features. In the second case, the time series is presented in the form of a black and white image of its recurrence plot. A convolutional neural network is used as an image classifier. The data for the classification are the electrocardiograms realizations of 100 values, which contained records of healthy people and patients with a diagnosis of ischemia. Research results showed the advantages of classifying images of recurrence plots, indicate a good classification accuracy in comparison with other methods and the potential capabilities of this approach.Item Architectural patterns in front-end development(онлайн, 2020) Martyn OlehSoftware technologies tend to change, but many patterns remain the same. Nowadays in software development we use modern frameworks and libraries, but often it is hard to answer a question – why certain framework was choosen. A large number of design patterns were developed decades ago, at a time when desktop and enterprise application development were popular. They were designed by engineers to reduce the complexity of processing large amounts of information within applications. Browser applications have become increasingly popular today, but a need to process a large amount of data remains relevant. Patterns, designed ten years ago, can greatly simplify development of client side of web applications today.Item Author index(Lviv Polytechnic National University, 2018-06-25)Item Author index, Reviewers(Lviv Politechnic Publishing House, 2019-04-18)Item Automated analysis and detection of optimal number of buses on the route depending on hours and type of day(онлайн, 2020) Sarakhman KhrystynaTransportation system always is the one of top-hot topics to discuss in Ukraine, especially in big cities. The relevance of the topic can be explained by huge arguments between bus drivers, population and government. The problem is discrepancy between the number of buses and the number of passengers and it depends on which part of day it is. Research of the topic involves Queueing Theory, Operations research, Statistical analysis and also methods of Machine Learning.Item Automated building and analysis of Ukrainian Twitter corpus for toxic text detection(Lviv Politechnic Publishing House, 2019-04-18) Bobrovnyk, Kateryna; Taras Shevchenko National University of KyivToxic text detection is an emerging area of study in Inter-net linguistics and corpus linguistics. The relevance of the topic can be explained by the lack of Ukrainian social media text corpora that are publicly available. Research involves building of the Ukrainian Twitter corpus by means of scraping; collective annotation of 'toxic/non-toxic' texts; construction of the obscene words dictionary for future feature engineering; and models training for the task of text classi cation (com-paring Logistic Regression, Support Vector Machine, and Deep Neural Network).