Today, due to the extended worldwide pandemic, socialization of persons with same interests is an enormously crucial step in isolating people. Moreover, most individuals are always attempting to simplify and automate all of the essential everyday routines that use a significant amount of free time. The same may be said about the individual's socialization process. In the situation of decision support system (DSS) development and large data analysis, machine learning and SEO technologies are presently increasingly significant. Almost any DSS that has a substantial user base employs proper socializing method. In this example, a unique algorithm based on Levenstein's algorithm, sample extension, N-grams, and the Noisy Channel model was developed. Based on current Levenstein algorithms, sample expansion, N-grams, and the Channel model, the researchers developed a new algorithm for assessing user information and determining the most apposite IP users based on the inspected text of profile messages. A active socialization DSS was created using an asynchronous programming framework. The convolutional neural network was upgraded, allowing for more effective searching for human faces in photos and checking for existent persons in the DSS database. The DSS will enable efficient and quick text data selection, analysis, processing, and final result generation. For systematic and high-quality intelligent search and processing of applicable information for the needs of a specific user, the DSS employs SEO technologies. By using a neural network, you may accurately identify a user based on his photo. The methods employed in general allow you to develop a convenient DSS socialization employing the relevant techniques. It is worth mentioning the importance of optimizing the current DSS; first and foremost, it is total asynchrony of system, which will eliminate any long waits and difficulties in processing and analyzing requests; second, the system allows efficient and active work with various volumes of large data. DSS users require more data. We also use the cloud platform, which allows for data dispersion. For example, all of the most challenging data may be stored in the cloud environment, and all of the necessary data can be downloaded using a simple basic DSS interface with data queries. As a result, it can be claimed that the development of this DSS is critical both in terms of societal impact and in terms of executing all of the algorithms that the DSS requires. Ontology, Levenshtein distance, Convolutional neural network, Social network, Noisy
Noisy
Developing an intelligent personal socialization system is a critical task since, in today's society, individuals are attempting to optimize all life activities in order to save time and, as a result, spend that time more effectively. Users, rather than other people, prioritize programs that save user’s time,
2022 Copyright for this paper by its authors. optimize work, and are automated enough to conduct most activities while searching for certain applications. The information system combines two fundamental tasks: user socialization and socialization process improvement and automation. Because no such system exists today, developing an intelligent system that allows for fast analysis and user selection is a critical challenge. On the Internet, social systems will improve the process of locating and meeting individuals. To put this system together, you'll need to search for human faces in photographs using a convolutional neural network. To assess user data and build a list of relevant users, a fuzzy search algorithm and a noisy channel model are also necessary. The most significant issue in effectively creating an intelligent social system of persons with mutual interests is to properly comprehend and conduct the process of user socialization.
Today, due to the extended worldwide pandemic, socialization of persons with same interests is an
enormously crucial step in isolating people. Moreover, most individuals are always attempting to
simplify and automate all of the essential everyday routines that use a significant amount of free time.
There are several articles on this theme, for example, [
Individual socialization systems with similar interests based on SEO technology and machine learning methods have an exterior nature, which includes users and their four fundamental internal organisms: browsers, system controllers, databases, and system services, according to system analysis.
The external entity and the internal entity are always interacting during the operation of the system, so when the system initializes the external entity, the user accesses the system via the internal entity, the browser. If the user is already registered or otherwise registered, the browser entity authorizes current user in the midst of the system, and authorisation and registration are completed using the internal instance system controller. During the session, the system controller instance transmits a session token to the browser object and saves the current token in the browser. The User then uses the Browser object to submit a photo to authenticate it, which is subsequently added to the System Controller object. The essence of the System Controller checks for the presence of a face in the User's photo and searches the system for comparable images [18-32], after which the essence of the System Controller saves all received user data and transmits the created data to another internal object. After that, the Database entity saves all of the information using the System Service's internal essence, and the System Service processes it and generates a list of the system's unique users. The fuzzy search algorithms utilize the System Service entity to produce a list of users based on present user data, and the fuzzy search algorithms to use System Service entity to examine the data of users now operating within the system and other registered users.
It's made by decreasing the amount of overlap between users' interests. The System Service's subject then performs a last check of the incoming data for the existence of damaged or erroneous data before saving it with the Database entity. The data created by the Database entity is subsequently sent to the User object via the user's query. Using the basis of the Service system, the user evaluates the offered information and picks the user profile that he likes most.
Next, the core of the User is to exploit another user's advantage so that another system user may see that the present user has picked him. Once the configuration procedure is complete, the system service entity starts communicating with the other user, forming a dialog box that is recorded as stored knowledge with the system controller and repository entities and exists as a stream of stored messages within the system. A session that runs on the system to automatically display all user messages and information, as well as a session which starts at a set time to display data. Because one of the most essential components of the system is the protection of users and the security of needed information, the System Service entity makes a request to the core of the Database to validate the availability of data. In the event of specific data processing issues, it is also required to enable entirely asynchronous analysis and information transfer for the program's fastest functioning, allowing users to use the system as rapidly as possible. It's also worth paying much more attention to the database's essence, because dealing with data is a critical component of the system, and how this object should operate and what components it should have, in this instance, internal, should be properly studied. The database's essence is made up of seven primary components that will allow you to handle user data safely and fast, namely: Check for backup files and validate the data; Data saving dialog box for the user; Make a data packet with the information you've gathered so far; Verify if the request is valid; On request, send data. The System Controller entity then proposes a system provider and an asynchronous data entity. The system service entity employs dynamic events to continually monitor the status of the system in which it lives and responds to any system changes at any given moment, and the essence of the System Service periodically examines the system for faults in exceptions that have not been recorded in the system log and attempts to repair them or sends logs to the System Controller for further processing in a separate thread. It's also required to go through the functions of the System Controller in further depth, which include: Data processing for users; Data processing for systems; Data verification; Checking the session's availability; Identifiers must be verified; Show the error message; Checking for updates; Saving system links; Checking user tokens. It is also required to discuss the essence of the Service system in further depth, which includes the following functions: Generating a user list; Using algorithms to analyse a list; Calculating a percentage; Processing user interaction; Create a message flow; Process the message flow; Create individual markers. It's also required to go over the substance of the browser, which isn't fundamental but does have the following features: Authorization; Registration; Token storage; Session monitoring; User messages are shown; Custom messages are read; A photo of the user is added; Send requests to the server from users; Client Error Display. After generating a message flow request, the current system service object sends a system controller entity request to the system service object, which asks a new dialog token, and the system service object sends a current token with information about the current session. Following that, the System Controller's Essence, via the Browser essence, presents the User essence's created dialog, after which the User can either continue working or log out. We describe classes, subclasses, property-relations, and property-data based on ontology approach [33-41].
Figure 6a shows the property-relationship make, its Domains and Ranges, conditionally it can be represented as a relationship one to many, for example Admin make Message - The administrator creates a message. Figure 6b shows the property-relationship of the post, its Domains and Ranges, conditionally it can be represented as a relationship one to many, for example Moderator post Album Moderator publishes Album.
a) b) Figure 6: a) Property-relationship «make» and b) Property-relationship «post»
Figure 7a shows the property-relationship save, its Domains and Ranges, conditionally it can be represented as a relationship one to many, such as Friend save Message - Friend saves the Message.
Figure 7b shows the property-relationship share, its Domains and Ranges, conditionally it can be represented as a relationship one to many, for example User share Comment - User shares Comment.
Figure 8a shows the take-property property, its Domains, and Ranges, which can be thought of as one-to-many, such as Friend take Photo. Figure 8b shows the property-relationship upload, its Domains and Ranges, conditionally it can be represented as a relationship one to many, such as Admin upload Tag - Admin uploads Tag.
Figure 9a shows the property-relationship write, its Domains and Ranges, conditionally this can be represented as a relationship one to many, for example User write MainText - User writes Main Text.
a) b) Figure 8: a) Property-relationship «take» and b) Property-relationship «upload»
Figure 9b shows the amount property-data, its Domains and Ranges, Domains the classes that contain the data property, and Ranges the type of data that will be stored in the data property. For example, amount - Quantity has data type long. Figure 10a shows the data property property, its Domains and Ranges, Domains the classes that contain the data property, and Ranges the type of data that will be stored in the data property. For example, content - Content has a data type string. Figure 10b shows the data property createdDate, its Domains and Ranges, Domains the classes that contain the data property, and Ranges the type of data that will be stored in the data property. For example, createdDate - Date created has data type dateTime.
a) b) Figure 9: a) Property-relationship «write» and b) Property-data «amount»
Figure 11a shows the email data property, its Domains and Ranges, Domains the classes that contain the data property, and Ranges the type of data that will be stored in the data property. For example, email - Email has the data type string. Figure 11b shows the messageId data property, its Domains and Ranges, Domains the classes that contain the data property, and Ranges the type of data that will be stored in the data property. For example, messageId - The message ID has the data type int.
Figure 12a shows the data property name, its Domains and Ranges, Domains the classes that contain the data property, and Ranges the type of data that will be stored in the data property. For example, name - The name has a data type string. Figure 12b shows the password data property, its Domains and Ranges, Domains the classes that contain the data property, and Ranges the type of data that will be stored in the data property. For example, password - The password has a token data type.
Figure 13a shows the pictureId data property, its Domains and Ranges, Domains the classes that contain the data property, and Ranges the type of data that will be stored in the data property. For example, pictureId - Image ID has data type int. Figure 13b shows the roleId data property, its Domains and Ranges, Domains the classes that contain the data property, and Ranges the type of data that will be stored in the data property. For example, roleId - Role ID has data type int.
Figure 14a shows the data property type, its Domains and Ranges, Domains the classes that contain the data property, and Ranges the type of data that will be stored in the data property. For example, type - Type has a string data type. Figure 14b shows the userId data property, its Domains and Ranges, Domains the classes that contain the data property, and Ranges the type of data that will be stored in the data property. For example, userId - User ID has data type int.
Figure 15 shows the OntoGraf ontology graph, which shows all available ontology relationships and also shows the dependence of classes and their instances (objects), and Figure 16 shows the OWLViz ontology graph showing the general view of ontology classes. Figure 17 shows the operation of the Reasoner mechanism, which is responsible for running the existing ontology and checking for errors, Figure 18 shows the preservation of the ontology in another format, namely Turtle syntax.
a) b) Figure 19: a) An instance of the class «user1» and b) An instance of the class «album1» a) b) Figure 20: a) An instance of the class «photo3» and b) An instance of the class «comment5»
Fig. 19b shows an instance of the Album class - album1, showing its relationship-properties and data-properties, for example album1 pictureId 1 - album1 has Picture ID 1. Fig. 20a shows an instance of the Photo class - photo3, showing its relationship properties and data properties, for example photo3 content - photo3 has a photo caption. Fig. 20b shows an instance of the Comment-comment5 class, its relationship-properties and data-properties, for example comment5 is subText5, comment5 content “ddd”. Fig. 21a shows an instance of the MainComment class - mainComment2, showing its relationship properties and data properties, such as mainComment2 amount 2. Fig. 21b shows an instance of the SubComment class - subComment3, its relationship properties and data properties, such as subComment3 amount 3. a) b) Figure 21: An instance of the class a) «mainComment2» and b) «subComment3»
Fig. 22a shows an instance of the Tag class - tag1, shows its properties-relationships and propertiesdata, such as tag1 pictureId 1. Fig. 22b shows an instance of the Dialog class - dialog1, its relationship properties and data properties, such as dialog1 save text1, dialog1 createdDate “2021-01-05”.
a) b) Figure 22: An instance of the class a) «tag1» and b) «dialog1»
a) b) Figure 23: An instance of the class a) «message3» and b) «relation5»
Fig. 23a shows an instance of the Message-message3 class, showing its relationship properties and data properties, such as message3 share relation3, message3 messageId 3. Fig. 23b shows an instance of the Relation class - relation5, its relationship-properties and data-properties, such as relation5 type “eee”. Fig. 24a shows an instance of the Type class - type1, its property-relationship and property-data, such as type1 pictureId 1. Fig. 24b shows an instance of the Friend class - friend1, showing its relationship properties and data properties, such as friend1 is common1, friend1 name “david”.
Figure 25a shows an instance of the Best class - best1, its relationship properties and data properties, such as best1 email “a@gmail.com”. Figure 25b shows an instance of the Common class - common1, its property-relationship and property-data, such as common1 createdDate “2021-01-05”.
a) b) Figure 25: An instance of the class a) «best1» and b) «common1»
a) b) Figure 26: An instance of the class a) «post1» and b) «picture1»
Figure 26a shows an instance of the Post class - post1, its relationship-properties and data-properties, for example post1 has picture1, post1 amount 1. Figure 26b shows an instance of the Picture class picture1, its relationship-properties and data-properties, such as picture1 amount 1. Figure 27a shows an instance of the Rate class - rate4, its relationship-properties and data-properties, such as rate4 createdDate “2021-01-05”. Figure 27b shows an instance of the Text-text2 class, its relationshipproperties, and data-properties, such as text2 is subText2, text2 messageId 2.
Figure 28a shows an instance of the MainText class - mainText3, its relationship-properties and data-properties, such as mainText3 createdDate “2021-01-05”. Figure 28b shows an instance of the SubText class, subText5, and its relationship properties and data properties, such as subText5 messageId 5. Figure 29a shows an instance of the TextTag class - texTag1, its relationship-properties and data-properties, such as texTag1messageId 1. Figure 29b shows an instance of the Role class role1, its property-relationship and property-data, such as role1 add admin1, role1 roleId 1.
Figure 30a shows an instance of the Admin class - admin3, its properties-relationships and properties-data, such as admin3 post rate3, admin3 password 2222. Figure 30b shows an instance of the CommonUser class - commonUser2, its relationship-properties and data-properties, such as commonUser2 createdDate “2021-01-05”. a) b) Figure 30: An instance of the class a) «admin3» and b) «commonUser2»
Figure 31a shows an instance of the Moderator class - moderator3, its properties-relationships and properties-data, such as moderator3 write tag3, moderator3 password 3221. Figure 31b shows an instance of the UpUser class - upUser2, its relationship-properties and data-properties, for example upUser2 has picture2, upUser2 email “b@gmail.com”. a) b) Figure 31: An instance of the class a) «moderator3» and b) «upUser2»
Figure 32a shows an instance of the PremiumUser class - premiumUser1, its relationship-properties and data-properties, such as premiumUser1 roleId 1. Figure 32b shows an instance of the VipUser class - vipUser3, its relationship-properties and data-properties, such as vipUser3 type 3.
a) b) Figure 32: An instance of the class a) «premiumUser1» and b) «vipUser3»
The listing presents the text of the information system ontology saved in RDFS format.
Fig. 35 shows an RDF graph in the form of a trio "resource-property-value" ("subject-predicateobject").
domain save domain member has CommonUser
UpUser subClassOf
subClassOf Role type User range range
range make
range MainText
range subClassOf write
Rate
Picture
Post range range range
upload subPropertyOf SubText
Text
range subClassOf
type Message subClassOf
TextTag
RDFS
RDF
The ontological model of the information system was tested in Protégé with the help of SPARQLqueries, Figures 36-47 show the screens of execution of SPARQL-queries and the obtained results. SPARQL-query has the following structure: PREFIX - reference to the data schemas needed to execute queries and reference to the ontology to which queries are made, SELECT - data sampling, specify the class and its properties for which the query occurs, WHERE - specify which properties- relations and data properties must be obtained, FILTER is an additional condition to the query. a) b) Figure 37: a) SPARQL-request to receive all users and b) result of SPARQL query to receive all users a) b) Figure 38: a) SPARQL query of more than 2 users and b) result of a SPARQL query of more than 2 users a) b) Figure 39: SPARQL-request for a) all comments and b) comments with ID less than 4 a) b) Figure 42: SPARQL-query of a) the main type of messages and b) the main type messages a) b) Figure 45: All messages for a) the creation time as more than 21:00 and b) the number as less than 5
a) b) Figure 48: a) The main program window and b) buttons of the main program window
Figure 49a shows the user registration form. Figure 49b shows the user's authorization, login and password, Figure 49c shows the successful authorization message. a) b) c) Figure 49: a) User registration form, b) User authorization and c) Successful authorization message Figure 50a shows the user profile settings, Figure 50b shows the completed user profile.
Almost any DSS that has a substantial user base employs proper socializing method. In this example, a unique algorithm based on Levenstein's algorithm, sample extension, N-grams, and the Noisy Channel model was developed [42-49]. Based on current Levenstein algorithms, sample expansion, N-grams, and the Noisy Channel model, the researchers developed a new algorithm for assessing user information and determining the most apposite IP users based on the inspected text of profile messages for web page/content/resource management [50-64]. An active socialization DSS was created using an asynchronous programming framework. The convolutional neural network was upgraded, allowing for more effective searching for human faces in photos and checking for existent persons in the DSS database. The DSS will enable efficient and quick text data selection, analysis, processing, and final result generation. For systematic and high-quality intelligent search and processing of applicable information for the needs of a specific user, the DSS employs SEO technologies. By using a neural network, you may accurately identify a user based on his photo. The methods employed in general allow you to develop a convenient DSS socialization employing the relevant techniques. It is worth mentioning the importance of optimizing the current DSS; first and foremost, it is total asynchrony of system, which will eliminate any long waits and difficulties in processing and analysing requests; second, the system allows efficient and active work with various volumes of large data. DSS users require more data. We also use the cloud platform, which allows for data dispersion. For example, all of the most challenging data may be stored in the cloud environment, and all of the necessary data can be downloaded using a simple basic DSS interface with data queries. As a result, it can be claimed that the development of this DSS is critical both in terms of societal impact and in terms of executing all of the algorithms that the DSS requires. Figure 51a shows the process of uploading photos to the system, you can upload 1 or more photos at a time by dragging them manually or using Explorer. Figure 51b shows uploaded photos of the user, you can delete all photos except the current main photo and the neural networks processed all the photos, and those where no faces were found are not available for display by the main photos of the user.
Figure 52a shows the generated list of users using word processing algorithms and sorted by descending percentage of user similarity. Figure 52b shows the use of search filters in an existing list. Figure 53a shows the user profile selection, the ability to view the user's profile, like and write a private message. Figures 53b-53c show a tab of information about the preferences of users who have chosen us and whom we have chosen. Figures 54-55 show basic profile information of the selected user, a tab with user interests, and a tab with all user photos.
a) b) c) Figure 53: a) User selection, b) Users who have chosen us and c) Users we have selected a) b) Figure 54: a) Basic user information and b) The interests of the user a) b) Figure 56: a) Received messages and b) Sent messages
Figures 57 show the login from the profile of another user who was selected as the first user of the system and view the list of users who chose us, which allows you to start private correspondence between two users. That chose each other. Figure 57c shows the private correspondence with the initial user, on behalf of the selected user of the system. a) b) c) Figure 57: a) Another user 's login to system, b) Users who have selected the current user and c) Private correspondence of users
Nowadays, the socialization of individuals with common interests is an extremely important process, as most people try to simplify and automate all basic life processes, which usually take up a lot of free time, the same applies to the socialization process based on SEO-technologies and machine learning methods plays an important role in this, as it optimizes the process of socialization. During the implementation, an analytical review of literature sources was conducted, among which was briefly described all aspects of modern socialization of individuals, namely information about neural networks for facial recognition and fuzzy search algorithms for processing textual information. It was also described the main purpose of the created system, why it was created, what are the main problems solved by creating this type of system. The reasons and factors that are important for the creation of this system were analysed. The systems that already exist and analogy of the created system were described; their advantages and disadvantages and concerning the created system of socialization of individuals on common interests were described. A systematic analysis of the object of study was conducted, the methodology of research of the subject area was described in detail and new information on the creation of this system was supplemented, important statement and substantiation of the problem of creating this system was made. The shortcomings of the use of the created information system, the object and subject of research of the system and their description were indicated. The necessary diagrams were also constructed, namely use case and activity diagrams, entity-relationship diagrams and state transition diagrams, which allowed to fully carry out a systematic analysis of the system of socialization of individuals by common interests, which allows further implementation of the software product. 8. References [14] S. M. Elaheebocus, M. Weal, L. Morrison, Peer-based social media features in behavior change interventions: Systematic review, Journal of Medical Internet Research 20(2) (2018) 1–20. doi: 10.2196/jmir.8342. [15] F. De-Gregorio, Y. Sung, Understanding attitudes toward and behaviors in response to product placement, Journal of Advertising 39(1) (2010) 83–96. doi: 10.2753/JOA0091-3367390106. [16] A. N. Geurin-Eagleman Communicating via photographs: A gendered analysis of Olympic athletes’ visual self -presentation on Instagram, Sport Management Review 19(2) (2015) 133–145. doi: 10.1016/j.smr.2015.03.002. [17] S. C. Chu, Y. Sung, Using a consumer socialization framework to understand electronic word-ofmouth (eWOM) group membership among brand followers on Twitter, Electronic Commerce Research and Applications 14(4) (2016) 251–260. doi: 10.1016/j.elerap.2015.04.002. [18] B. Rusyn, O. Lutsyk, R. Kosarevych, Y. Obukh, Application Peculiarities of Deep Learning Methods in the Problem of Big Datasets Classification, Lecture Notes in Electrical Engineering 831 (2022). doi: 10.1007/978-3-030-92435-5_28. [19] B. Rusyn, O. Lutsyk, R. Kosarevych, Evaluation the informativity of a training sample for image classification by deep learning methods, Cybernetics and System Analysis 57(6) (2021) 853–863. doi:10.1007/s10559-021-00411-4. [20] R. Kosarevych, O. Lutsyk, B. Rusyn, Detection of pixels corrupted by impulse noise using random patterns, The Visual Computer, 2021.doi:10.1007/s00371-021-02207-1. [21] B. Rusyn, R. Kosarevych, O. Lutsyk, V. Korniy, Segmentation of atmospheric cloud images by remote sensing, in: Proceedings of the14th international conference TCSET' 2018, pp. 213–216. doi: 10.1109/TCSET.2018.8336189. [22] S. Voloshyn, R. Peleshchak, I. Peleshchak, V. Vysotska, Big Data Analysis for Multispectral Images Recognition Based on Deep Learning, in: Proceedings of the IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT), 22–25 Sept., Lviv, Ukraine, 2021, pp.160–170. doi: 10.1109/CSIT52700.2021.9648650. [23] A. Sartiukova, R. Peleshchak, I. Peleshchak, V. Vysotska, The Multiclass Classification of Objects Based on Multispectral Images Recognition, in: Proceedings of the IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT), 22-25 Sept., Lviv, Ukraine, 2021, pp. 52–60. doi: 10.1109/CSIT52700.2021.9648719. [24] S. Tchynetskyi, R. Peleshchak, I. Peleshchak, V. Vysotska, A Neural Network Development for Multispectral Images Recognition, in: Proceedings of the IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT), 22-25 Sept., Lviv, Ukraine, 2021, pp. 278–284. doi: 10.1109/CSIT52700.2021.9648735. [25] O. Veres, B. Rusyn, A. Sachenko, I. Rishnyak, Choosing the method of finding similar images in the resverse seach system, CEUR WorkshopProceedings 2136 (2018) 99–107. [26] P. Zdebskyi, V. Vysotska, R. Peleshchak, I. Peleshchak, A. Demchuk, M. Krylyshyn, An Application Development for Recognizing of View in Order to Control the Mouse Pointer, CEUR Workshop Proceedings Vol-2386 (2019) 55–74. [27] V. Lytvyn, I. Peleshchak, R. Peleshchak, The compression of the input images in neural network that using method diagonalization the matrices of synaptic weight connections, in: Proceedings of the 2nd International Conference on Advanced Information and Communication Technologies, AICT, 2017, pp. 66–70. doi:. 10.1109/AIACT.2017.8020067. [28] V. Lytvyn, I. Peleshchak, R. Peleshchak, R. Holoshchuk, Detection of multispectral input images using nonlinear artificial neural networks, in: Proceedings of the 14th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering, TCSET, 2018, pp. 119–122. doi:. 10.1109/TCSET.2018.8336169. [29] R. Peleshchak, V. Lytvyn, N. Kholodna, I. Peleshchak, V. Vysotska, Two-Stage AES Encryption Method Based on Stochastic Error of a Neural Network, in: Proceedings of 2022 IEEE 16th International conference on Advanced trends in radioelectronics, telecommunications and computer engineering, TCSET, Lviv-Slavske, Ukraine, Feb. 22–26, 2022. [30] N. Shakhovska, L. Nych, R. Kaminskyj, The identification of the operator’s systems images using the method of the phase portrait, Advances in Intelligent Systems and Computing 512 (2017), 241253. doi: 10.1007/978-3-319-45991-2_16. [31] O. Kosar, N. Shakhovska, An Overview of Denoising Methods for Different Types of Noises Present on Graphic Images, Advances in Intelligent Systems and Computing 871 (2019) 38-47. doi: 10.1007/978-3-030-01069-0_4. [32] O. Kosar, N. Shakhovska, The methods for evaluating the quality of images with different types of noise, in: International Scientific and Technical Conference on Computer Sciences and Information Technologies, CSIT, 2018, pp. 326-329. doi: 10.1109/STC-CSIT.2018.8526693. [33] T. Lendyuk, O. Bodnar, S. Rippa, A. Sachenko, Ontology application in context of mastering the knowledge for students, in: Proceedings of the 13th IEEE International Conference on Computer Science and Information Technologies (CSIT’2018), Lviv, 11-14 September 2018, vol. 2, pp. 123126. doi: 10.1109/STC-CSIT.2018.8526710.I. [34] N. Garanina, E. Sidorova, I. Kononenko, S. Gorlatch, Using multiple semantic measures for coreference resolution in ontology population, International Journal of Computing 16(3) (2017) 166-176. [35] Y. Burov, V. Vysotska, P. Kravets, Ontological approach to plot analysis and modeling, CEUR
Workshop Proceedings Vol-2362 (2019) 22-31. [36] V. Lytvyn, V. Vysotska, B. Rusyn, L. Pohreliuk, P. Berezin, O. Naum, Textual Content Categorizing Technology Development Based on Ontology, CEUR Workshop Proceedings Vol2386 (2019) 234-254. [37] V. Lytvyn, V. Vysotska, P. Pukach, M. Vovk, D. Ugryn, Method of functioning of intelligent agents, designed to solve action planning problems based on ontological approach, EasternEuropean Journal of Enterprise Technologies 3/2(87) (2017) 11-17. doi: 10.15587/17294061.2017.103630. [38] V. Vysotska, V. Lytvyn, Y. Burov, P. Berezin, M. Emmerich, V. B. Fernandes, Development of Information System for Textual Content Categorizing Based on Ontology, CEUR Workshop Proceedings Vol-2362 (2019) 53-70. [39] C. Shu, D. Dosyn, V. Lytvyn, V. Vysotska, A. Sachenko, S. Jun, Building of the Predicate Recognition System for the NLP Ontology Learning Module, in: Proceedings of the International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, IDAACS, 2, 2019, pp. 802-808. doi: 10.1109/IDAACS.2019.8924410. [40] V. Lytvyn, V. Vysotska, Y. Burov, A. Demchuk, Architectural ontology designed for intellectual analysis of e-tourism resources, in: Proceedings of the International Conference on Computer Sciences and Information Technologies, CSIT, 2018, pp. 335-338. doi: 10.1109/STCCSIT.2018.8526623. [41] P. Kravets, Y. Burov, V. Lytvyn, V. Vysotska, Gaming method of ontology clusterization,
Webology 16(1) (2019) 55-76. [42] T. Batiuk, V. Vysotska, V. Lytvyn, Intelligent System for Socialization by Personal Interests on the Basis of SEO-Technologies and Methods of Machine Learning, CEUR workshop proceedings Vol-2604 (2020) 1237–1250. [43] V. Lytvyn, V. Vysotska, I. Peleshchak, I. Rishnyak, R. Peleshchak, Time Dependence of the Output Signal Morphology for Nonlinear Oscillator Neuron Based on Van der Pol Model, International Journal of Intelligent Systems and Applications 10 (2018) 8-17. doi: 10.5815/ijisa.2018.04.02. [44] V. Lytvyn, V. Vysotska, V. Mykhailyshyn, I. Peleshchak, R. Peleshchak, I. Kohut, Intelligent system of a smart house, in: 3rd International Conference on Advanced Information and Communications Technologies, AICT, 2019, pp. 282-287. doi: 10.1109/AIACT.2019.8847748. [45] V. Lytvyn, I. Peleshchak, R. Peleshchak, V. Vysotska, Information Encryption Based on the Synthesis of a Neural Network and AES Algorithm, in: 3rd International Conference on Advanced Information and Communications Technologies, AICT, 2019, pp. 447-450. doi: 10.1109/AIACT.2019.8847896. [46] R. Peleshchak, V. Lytvyn, I. Peleshchak, V. Vysotska, Stochastic Pseudo-Spin Neural Network with Tridiagonal Synaptic Connections, in: IEEE International Conference on Smart Information Systems and Technologies (SIST), Nur-Sultan, Kazakhstan, 2021. doi: 10.1109/SIST50301.2021.9465998. [47] V. Vysotska, Linguistic Analysis of Textual Commercial Content for Information Resources Processing, in: Proceedings of the Modern Problems of Radio Engineering, Telecommunications and Computer Science, TCSET, 2016, pp. 709-713. doi: 10.1109/TCSET.2016.7452160. [48] V. Lytvyn, V. Vysotska, A. Rzheuskyi, Technology for the Psychological Portraits Formation of Social Networks Users for the IT Specialists Recruitment Based on Big Five, NLP and Big Data Analysis, CEUR Workshop Proceedings Vol-2392 (2019) 147-171. [49] Lytvyn Vasyl, Vysotska Victoria, Dosyn Dmytro, Holoschuk Roman, Rybchak Zoriana, Application of Sentence Parsing for Determining Keywords in Ukrainian Texts, in: Proceedings of the International Conference on Computer Sciences and Information Technologies, CSIT, 2017, pp. 326-331. doi: 10.1109/STC-CSIT.2017.8098797. [50] B. Polishchuk, A. Berko, L. Chyrun, M. Bublyk, V. Schuchmann, The rain prediction in Australia based Big Data analysis and machine learning technology, in: Proceedings of IEEE 16th International conference on computer science and information technologies 2021, 97–100. [51] A. Demchuk, B. Rusyn, L. Pohreliuk, A. Gozhyj, I. Kalinina, L. Chyrun, N. Antonyuk, Commercial content distribution system based on neural network and machine learning, CEUR Workshop Proceedings 2516 (2019) 40–57. [52] V. Lytvynenko, W. Wojcik, A. Fefelov, I. Lurie, N. Savina, M. Voronenko, O. Boskin, S.
Smailova, Hybrid Methods of GMDH-Neural Networks Synthesis and Training for Solving Problems of Time Series Forecasting, Lecture Notes in Computational Intelligence and Decision Making 1020 (2020) 513–531. [53] A. Safonyk, M. Mishchanchuk, V. Lytvynenko, Intelligent information system for the determination of iron in coagulants based on a neural network, CEUR Workshop Proceedings 2853 (2021) 142–150. [54] O., Ivanov, L. Koretska, V. Lytvynenko, Intelligent modeling of unified communications systems using artificial neural networks, CEUR Workshop Proceedings 2623 (2020) 77–84. [55] S. Babichev, B. Durnyak, O. Sharko, A. Sharko, Technique of metals strength properties diagnostics based on the complex use of fuzzy inference system and hybrid neural network, Communications in Computer and Information Science 1158 (2020) 114–126. [56] P. Mukalov, O. Zelinskyi, R. Levkovych, P. Tarnavskyi, A. Pylyp, N. Shakhovska, Development of System for Auto-Tagging Articles, Based on Neural Network, CEUR Workshop Proceedings Vol-2362 (2019) 106–115. [57] S. Leoshchenko, A. Oliinyk, S. Skrupsky, S. Subbotin, T. Zaiko, Parallel Method of Neural Network Synthesis Based on a Modified Genetic Algorithm Application, CEUR Workshop Proceedings Vol-2386 (2019) 11–23. [58] I. Tsmots, M. Medykovskyy, O. Skorokhoda, Synthesis of hardware components for vertical-group parallel neural networks, in: Proceedings of the International Conference on Computer Sciences and Information Technologies, CSIT, 2015, 1–4. [59] M. O. Medykovskyi, I. G. Tsmots, O. V. Skorokhoda, Spectrum neural network filtration technology for improving the forecast accuracy of dynamic processes in economics, Actual Problems of Economics 162(12) (2014) 410–416. [60] A. Gozhyj, L. Chyrun, A. Kowalska-Styczen, O. Lozynska, Uniform method of operative content management in web systems, CEUR Workshop Proceedings 2136 (2018) 62–77. [61] L. Chyrun, Y. Burov, B. Rusyn, L. Pohreliuk, O. Oleshek, A. Gozhyj, І. Bobyk, Web resource changes monitoring system development, CEUR Workshop Proceedings 2386 (2019) 255–273. [62] L. Chyrun, A. Kowalska-Styczen, Y. Burov, A. Berko, A. Vasevych, I. Pelekh, Y. Ryshkovets, Heterogeneous data with agreed content aggregation system development, CEUR Workshop Proceedings 2386 (2019) 35–54. [63] B. Rusyn, L. Pohreliuk, A. Rzheuskyi, R. Kubik, Y. Ryshkovets, L. Chyrun, S. Chyrun, A.
Vysotskyi, V.B. Fernandes, The mobile application development based on online music library for socializing in the world of bard songs and scouts’ bonfires, Advances in Intelligent Systems and Computing 1080 (2020) 734–756. doi: 10.1007/978-3-030-33695-0_49. [64] N. Antonyuk, L. Chyrun, V. Andrunyk, A. Vasevych, S. Chyrun, A. Gozhyj, I. Kalinina, Y.
Borzov, Medical news aggregation and ranking of taking into account the user needs, CEUR Workshop Proceedings 2488 (2019) 369–382.