{"title":"The software solution for precise agriculture using the NDVI index","authors":"Serhiy Verovka, Z. Veres","doi":"10.1109/CSIT56902.2022.10000634","DOIUrl":"https://doi.org/10.1109/CSIT56902.2022.10000634","url":null,"abstract":"The issue of food security and providing the population with food products is more relevant than ever. This work examines existing approaches and modern information technology usage in agriculture. Specifically, the NDVI vegetation index’s use, benefits, and shortcomings. This paper reviews existing methods and proposes the concept and direction of an improved software solution targeted at improving crop productivity, considering heterogeneities within a field, and combining data from multiple sources.","PeriodicalId":282561,"journal":{"name":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121758806","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":"Adapting the Size of Artificial Neural Networks Using Dynamic Auto-Sizing","authors":"Vojtech Cahlík, P. Kordík, Miroslav Cepek","doi":"10.1109/CSIT56902.2022.10000471","DOIUrl":"https://doi.org/10.1109/CSIT56902.2022.10000471","url":null,"abstract":"We introduce dynamic auto-sizing, a novel approach to training artificial neural networks which allows the models to automatically adapt their size to the problem domain. The size of the models can be further controlled during the learning process by modifying the applied strength of regularization. The ability of dynamic auto-sizing models to expand or shrink their hidden layers is achieved by periodically growing and pruning entire units such as neurons or filters. For this purpose, we introduce weighted L1 regularization, a novel regularization method for inducing structured sparsity. Besides analyzing the behavior of dynamic auto-sizing, we evaluate predictive performance of models trained using the method and show that such models can provide a predictive advantage over traditional approaches.","PeriodicalId":282561,"journal":{"name":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128092212","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}
Roman Voliansky, Ataliya Krasnoshapka, Oleksii Statsenko, Nina Volianska, O. Sinkevych, F. Dwiyanto
{"title":"The Symmetry Principle Usage to Design the Previously Disturbed Linear Control Systems","authors":"Roman Voliansky, Ataliya Krasnoshapka, Oleksii Statsenko, Nina Volianska, O. Sinkevych, F. Dwiyanto","doi":"10.1109/CSIT56902.2022.10000725","DOIUrl":"https://doi.org/10.1109/CSIT56902.2022.10000725","url":null,"abstract":"The paper deals with developing backgrounds to design the control systems for electrical motors and actuators. We offer to design controllers by using the known approach based on the control systems symmetry principle. This principle similar to the feedback linearization approach allows us to fully compensate for the inner dynamic of a plant but contrary to feedback linearization it forms the system’s desired motion by defining desired transfer function of the open-loop control system. Since the used approach operates with the transfer functions apparatus we offer to generalize these functions by taking into account the plant’s non-zero initial state while performing the Laplace-Carson’s transformation. Such an approach gives us the possibility to consider the generalized transfer function as some matrix differential operator which defines free and perturbed system’s motions. We study this operator in our paper and show the patterns of its determination and implementation. Our study allows us to supplement the definition of direct and inverse dynamic problems and consider the last one as the problem with the two solutions which define the plant’s control signal and its initial conditions. We use them to define the generalized inverse transfer function and, in conjunction with the desired transfer function for an open-loop system, find the controller transfer function. This method is applied to design a control system for the angular position of a DC electric drive. Our results show that the designed control system is an asymptotically stable one for various initial conditions.","PeriodicalId":282561,"journal":{"name":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125461550","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}
M. Slabinoha, S. Melnychuk, I. Manuliak, Bohdan Pashkovskyi
{"title":"Comparative analysis of embedded databases performance on single board computer systems using Python","authors":"M. Slabinoha, S. Melnychuk, I. Manuliak, Bohdan Pashkovskyi","doi":"10.1109/CSIT56902.2022.10000475","DOIUrl":"https://doi.org/10.1109/CSIT56902.2022.10000475","url":null,"abstract":"The article deals with comparative analysis of SQL and NoSQL embedded databases performance on single-board computer systems, such as SQLite, LMDB and UnQLite. The aim of the article is to perform comparative testing of CRUD operations performance through database connection software implemented using Python, on single-board computer systems that need to store data in local storage without continuous running of database server process in system tray. The analysis of the related publications was done and the aim of work was set. The hardware and software was chosen to hold the experiment. The experiment details were described. The results were obtained, highlighting strong and weak features of SQL and NoSQL databases as well as key-value stores. Received results can be used when designing Python software for single-board computers with ability to store large amount of data in device local memory.","PeriodicalId":282561,"journal":{"name":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","volume":"53 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127888857","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":"An improved approach to the development of software with increased requirements for flexibility and reliability in terms of creating small and medium-sized projects","authors":"Vladyslav Lakhai, O. Kuzmych, M. Seniv","doi":"10.1109/CSIT56902.2022.10000787","DOIUrl":"https://doi.org/10.1109/CSIT56902.2022.10000787","url":null,"abstract":"The use of new and improved software development approaches is becoming a necessity due to high quality requirements and increasing development complexity. This paper analyzes the most common approaches to the development of flexible and reliable software as well as determines their weaknesses and strengths. Based on the analysis, possible improvements to the existing approaches were proposed and the idea of an improved approach to software development with increased requirements for flexibility and reliability was formed. This approach, unlike the existing ones, provides comprehensive recommendations to software developers regarding the use of the most common practices in the conditions of creating small and medium-sized projects.","PeriodicalId":282561,"journal":{"name":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127918151","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}
Lubomyr Sikora, N. Lysa, R. Martsyshyn, Yulia Miyushkovych
{"title":"Information Technology for Assessing the Impact of Cognitive Risks in Decision-Making by Operational Personnel in the Process of Energy-Active Object Managing","authors":"Lubomyr Sikora, N. Lysa, R. Martsyshyn, Yulia Miyushkovych","doi":"10.1109/CSIT56902.2022.10000543","DOIUrl":"https://doi.org/10.1109/CSIT56902.2022.10000543","url":null,"abstract":"The paper substantiates and develops a model of an active goal-oriented management system of technogenic structure. The synthesis of laws for the management of active objects (which are components of technogenic, organizational and administrative structures with certain goals of functioning) was performed. A method for assessing risks arising from the cognitive component of the operator, taking into account its intellectual characteristics, has been developed. A table of cognitive coefficients of intellectual activity is constructed.","PeriodicalId":282561,"journal":{"name":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","volume":"10 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130443220","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":"The Possibility of Post-industrial Landscapes Reclamation Based on the Study of Soil Quality Indicators and Variance Analysis","authors":"Elvira Dzhumelia, Oksana Spodaryk","doi":"10.1109/CSIT56902.2022.10000800","DOIUrl":"https://doi.org/10.1109/CSIT56902.2022.10000800","url":null,"abstract":"Elucidation of the ecological situation in the territories affected by mining and chemical works is a primary task for the formation of a strategy for the restoration of the natural environment. Total organic carbon is one of the most important components of soils. It is evaluated the level of total organic carbon in the soils of post-industrial landscapes. A software tool was created that examines the influence of factors on measurement results on the basis of laboratory studies. As a result of one-factor and two-factor analysis of variance, it was established that depth and distance do not affect the results of measurements, and the presence of systematic errors in the results of measurements is insignificant.","PeriodicalId":282561,"journal":{"name":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133913608","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 software tools for testing the autonomous navigation system of UAVs","authors":"Mykyta S. Klymenko, A. Shevchenko","doi":"10.1109/CSIT56902.2022.10000442","DOIUrl":"https://doi.org/10.1109/CSIT56902.2022.10000442","url":null,"abstract":"In this paper the testing environment for the artificial intelligence system that operates the unmanned aerial vehicle (UAV) is considered. The approach given in this paper covers developing part of the computer software that will reflect the structure and functional behavior of the UAV. This software implements simulation modeling of processes that occur on different UAV’s subsystems. To implement this kind of software that will model UAV’s actions in real-world environment and time, the hybrid dynamic models will be used. These models will consist of probability component such as weather conditions, availability of cellular data or any other kind of connection, so they could be called stochastic. The main point of this research is to develop a visual, mathematical and analytical representation of the processes that take place in artificial intelligence system.","PeriodicalId":282561,"journal":{"name":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132053540","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}
D. Pastukhov, Stanislav Kuznetsov, Vojtěch Vančura, P. Kordík
{"title":"Offline evaluation of the serendipity in recommendation systems","authors":"D. Pastukhov, Stanislav Kuznetsov, Vojtěch Vančura, P. Kordík","doi":"10.1109/CSIT56902.2022.10000782","DOIUrl":"https://doi.org/10.1109/CSIT56902.2022.10000782","url":null,"abstract":"Offline optimization of recommender systems is a difficult task. Popular optimization criteria such as RMSE, Recall, and NDCG do not correlate much with online performance, especially when the recommendation algorithm is largely different from the one used to generate the offline data. An exciting direction of research to mitigate this problem is to use more robust optimization criteria. Serendipity is reported to be a promising proxy. However, more variants exist, and it is unclear whether they can be used as a single criterion to optimize. This paper analyzes how serendipity relates to other optimization criteria for three different recommendation algorithms. Based on our findings, we propose to modify the way serendipity is computed. We conduct experiments using three collaborative filtering algorithms: K-Nearest Neighbors, Matrix Factorization, and Embarrassingly Shallow Autoencoder $(EASE^{R})$. We also employ and evaluate the ensemble learning approach and analyze the importance of the individual components of serendipity.","PeriodicalId":282561,"journal":{"name":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130757888","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}
I. Novakivskyi, I. Kulyniak, Yu.P. Bondarenko, Y. Dziurakh, Halyna Rachynska
{"title":"Modeling the Minimization of Accommodation Costs while Developing a Tourist Route","authors":"I. Novakivskyi, I. Kulyniak, Yu.P. Bondarenko, Y. Dziurakh, Halyna Rachynska","doi":"10.1109/CSIT56902.2022.10000837","DOIUrl":"https://doi.org/10.1109/CSIT56902.2022.10000837","url":null,"abstract":"a linear programming model was built to reduce the cost of a trip when developing a tourist route by minimizing the accommodation costs (overnight stay) considering the distance travel limitation for drivers. The model was tested on the example of building an international tourist route, which is designed for 5 days (overnight stays) and involves visiting five countries Ukraine, Hungary, Austria, the Czech Republic and Poland.","PeriodicalId":282561,"journal":{"name":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","volume":"926 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114058258","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}