Oleksandr V Lemeshko, Oleksandra Yeremenko, A. Mersni, M. Yevdokymenko, M. Persikov, Anastasiia Kruhlova
{"title":"Analysis of Proactive Models of Fault-Tolerant Routing under Load Balancing and Border Routers Availability","authors":"Oleksandr V Lemeshko, Oleksandra Yeremenko, A. Mersni, M. Yevdokymenko, M. Persikov, Anastasiia Kruhlova","doi":"10.1109/CADSM58174.2023.10076525","DOIUrl":"https://doi.org/10.1109/CADSM58174.2023.10076525","url":null,"abstract":"This paper analyzes mathematical solutions to the problem of proactive fault-tolerant routing. All models comply with the Traffic Engineering concept to provide high Quality of Service level, and two models consider the reliability level of border routers, namely, RATE and ResMetrTE. The calculation results confirmed the RATE and ResMetrTE routing solutions' sensitivity to the border routers' reliability level. It was proved that border routers' reliability level consideration when organizing load balancing between them using RATE or ResMetrTE solutions led to increased network links utilization upper bound. It has also been shown that the studied load-balancing solutions can be implemented using the GLBP in the weighted balancing mode when the weight of each border router is based on the calculation result in the RATE or ResMetrTE approaches.","PeriodicalId":196129,"journal":{"name":"2023 17th International Conference on the Experience of Designing and Application of CAD Systems (CADSM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115148041","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":"Meteorological Information Access and Decision-Making for UAS Flight Planning","authors":"M. Ivanytskyi, Yevheniia Znakovska, Y. Averyanova","doi":"10.1109/CADSM58174.2023.10076518","DOIUrl":"https://doi.org/10.1109/CADSM58174.2023.10076518","url":null,"abstract":"Nowadays, there are concepts and programs aimed to provide participants of air traffic with real-time and relevant (on-demand) meteorological information to avoid weather-related hazards and eliminate risks connected with them. At the same time, despite the fact of the rising number of flights and tasks for Unmanned Aircraft Systems there is rather a lack of programs for UAS meteorological support that considers the integration of weather information into operational decision-making processes. In this paper, a mobile application has been developed that gives selected users access to current spatial meteorological data within the area of UAS flights with ability to help to take the right decision when performing particular flight mission in planned area of flight. The UASs are considered not only as final customer of weather information, but also as elements of observing system that help to obtain operative meteorological data. The recommendations on decision making are based on risk-oriented approach.","PeriodicalId":196129,"journal":{"name":"2023 17th International Conference on the Experience of Designing and Application of CAD Systems (CADSM)","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124394567","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":"Academic Performance Prediction Model Based on Educational Similarity","authors":"YuanLin Wang, Y. Ouyang, M. Levkiv","doi":"10.1109/CADSM58174.2023.10076516","DOIUrl":"https://doi.org/10.1109/CADSM58174.2023.10076516","url":null,"abstract":"Academic performance is a direct assessment indicator of student learning achievement that aims to predict future learning outcomes based on historical student behavior data. Existing academic performance methods tend to ignore the influence of students' home education on academic performance. Therefore, to address the above issues, this paper proposes an academic performance prediction method based on educational similarity(APPES). We construct the similarity of students with the same home education background and use a graph convolutional neural network (GCN) to integrate it with student characteristics for student academic performance prediction. Our method outperforms existing methods through experiments on real student datasets.","PeriodicalId":196129,"journal":{"name":"2023 17th International Conference on the Experience of Designing and Application of CAD Systems (CADSM)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116114784","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":"Models of Recurrent Distributions Statistical Averaging for Electronic Components with Fluctuations","authors":"P. Kosobutskyy, V. Oksentyuk","doi":"10.1109/CADSM58174.2023.10076523","DOIUrl":"https://doi.org/10.1109/CADSM58174.2023.10076523","url":null,"abstract":"In the article, for the first time, general statistical relations for the generalized distribution of the parameters dispersion of the Fibonacci type were obtained. These ratios make it possible to model statistical mean of electronic parameters components (and in general, physical characteristics, on the basis of which sensor devices for generation and processing of selective information are designed) with partial distributions, such as Mersenne, Pella, Jacobstall distribution. The mean and variance of discrete random recurrence numbers are determined in the case $pgeq 1, qgeq 1$. It is shown that the mean and variance overestimate only on the parameters $p,q$ in the limit $nrightarrowinfty$. The practical implications of the research carried out consist in the possibility of calculating statistical parameters based on the formulas obtained in the article using other standard numbers of Mersenne, Jakobstal and Pella. In particular, for the number of Pella, the mean is equal to 1.71, variance is equal to 1.21 and mean square error (mse) is equal to 1.1. For the Jacobsthall numbers the mean is equal to 2, variance is equal to 2 and mse is equal to square root 2. For the Mersenne numbers the mean is equal to 1.4, variance is equal to 0.54 and mse is equal to square root 0.745.","PeriodicalId":196129,"journal":{"name":"2023 17th International Conference on the Experience of Designing and Application of CAD Systems (CADSM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129874333","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. Beshley, Volodymyr Kochan, H. Beshley, M. Medvetskyi, I. Kahalo, Yuriy Shkoropad
{"title":"QoS-Coordinated Adaptive Spectrum Management Method for Coexistence 5G-U and Wi-Fi Networks with Short-Term Channel Failures","authors":"M. Beshley, Volodymyr Kochan, H. Beshley, M. Medvetskyi, I. Kahalo, Yuriy Shkoropad","doi":"10.1109/CADSM58174.2023.10076520","DOIUrl":"https://doi.org/10.1109/CADSM58174.2023.10076520","url":null,"abstract":"5G on unlicensed band (5G-U) technology, which is a further long-term evolution on unlicensed band (LTE-U), is a promising solution to address spectrum deficits and increase data rates. The main task of 5G-U is to operate in the highly congested 5 GHz bands while ensuring harmonious coexistence with other wireless technologies such as Wi-Fi. For this reason, we propose a method of adaptive use of unlicensed spectrum by Wi-Fi and 5G-U networks to ensure the required quality of service (QoS) and fair coexistence. Based on the users' QoS requirements, this method centrally takes reasonable decisions concerning the part of unlicensed radio resource use by 5G-U mobile operators, which allows increasing spectral efficiency in the integrated 5G-U networks with the avoidance of inter-system interference. Simulation results show that the proposed approach, unlike the traditional CSAT (Carrier Sensing Adaptive Transmission) for LTE-U, allocates throughput according to the QoS requirements of users for both Wi-Fi and 5G-U networks. A modified packet queue management algorithm at the data link layer is developed to overcome the consequences of short-term channel failures (interference, low signal strength). This algorithm can occur in Wi-Fi networks under conditions of mass 5G-U deployment. As a result of the simulation, it is proved that the proposed algorithm improved the quality of the video image from 5% to 45% according to the MSE (Mean Squared Error) criterion in the integrated 5G-U/Wi-Fi network.","PeriodicalId":196129,"journal":{"name":"2023 17th International Conference on the Experience of Designing and Application of CAD Systems (CADSM)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121295798","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":"Hydrogen Adsorption in Porous Silicon: Simulation and Control Method","authors":"V. Skryshevsky, A. Manilov, I. Ivanov","doi":"10.1109/CADSM58174.2023.10076503","DOIUrl":"https://doi.org/10.1109/CADSM58174.2023.10076503","url":null,"abstract":"Well-known that porous silicon is currently under consideration as new promising material for solid state hydrogen reservoirs. In present work a hydrogen adsorption processes in porous silicon are simulated. A model of hydrogen passivation of the surface of silicon pores are developed using the methods of molecular dynamics. Hydrogen-like spherical Lennard-Jones particles are used as the adsorbate. Such choice is explained by the physical nature of the adsorption processes of hydrogen on initial chemically adsorbed H-monolayer, covered the pore walls. A distribution of potential energy for interaction of the drifting species with the pore walls is calculated. Current-voltage and impedance characteristics of free standing porous silicon layers were selected as control method to study hydrogen accumulation process. The charge transfer processes were analyzed based on dependence of the impedance of porous silicon samples on voltage in the atmosphere with H2 and during relaxation in air.","PeriodicalId":196129,"journal":{"name":"2023 17th International Conference on the Experience of Designing and Application of CAD Systems (CADSM)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115877061","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":"Outdoor Positioning for Industrial Workplace","authors":"Anastasiia Lebedieva-Dychko, Galina Shilo","doi":"10.1109/CADSM58174.2023.10076493","DOIUrl":"https://doi.org/10.1109/CADSM58174.2023.10076493","url":null,"abstract":"The advantages of the development of outdoor positioning systems based on RFID, GPS, WiFi technologies are considered in the paper. The effectiveness of these systems application at industrial workplaces are studied. The concept of developing the hybrid system are formulated for preset accuracy and industrial area conditions such as many metal structures and sources of electromagnetic radiation. The scalability and portability are allowed in the hybrid position system.","PeriodicalId":196129,"journal":{"name":"2023 17th International Conference on the Experience of Designing and Application of CAD Systems (CADSM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130176481","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":"A New Hybrid Method for Predicting Recommendations for Collaborative Recommender Systems","authors":"M. Lobur, Y. Stekh, R. Holovatskyy, Maria Kamiska","doi":"10.1109/CADSM58174.2023.10076527","DOIUrl":"https://doi.org/10.1109/CADSM58174.2023.10076527","url":null,"abstract":"In this article analyzes the current state of models and methods for building recommender systems. The main classes of problems solving recommender systems are identified. The features of the application of the method of collaborative (general) filtering are shown. A mixed numerical-categorical clustering method has been developed to search for user groups using numerical rating and demographic characteristics of users; a hybrid method for searching user groups has been developed using the sparsity coefficient of the user-subject matrix.","PeriodicalId":196129,"journal":{"name":"2023 17th International Conference on the Experience of Designing and Application of CAD Systems (CADSM)","volume":"372 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133180105","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. Rebot, V. Topilnytskyy, Tetyana Stefanovych, S. Shcherbovskykh
{"title":"Vibration Oscillations Modeling for Printed Boards of Machine Control Units during Their Operation","authors":"D. Rebot, V. Topilnytskyy, Tetyana Stefanovych, S. Shcherbovskykh","doi":"10.1109/CADSM58174.2023.10076529","DOIUrl":"https://doi.org/10.1109/CADSM58174.2023.10076529","url":null,"abstract":"The mathematical model is built to research vibration oscillations of printed circuit boards in transport control units. The methods of nonlinear mechanics, particularly the Van der Pol method and the wave motion concept, were used to get dependencies. The influence of external and internal factors on oscillatory processes in the printed circuit board is taken into account. The obtained results indicate that despite the initial parameters of the impact on the printed circuit board, the amplitude of its oscillation during the machine operation assumes a constant value. The value of the board layer's stable oscillations amplitude depends on the board's physical and mechanical characteristics and its constituent elements.","PeriodicalId":196129,"journal":{"name":"2023 17th International Conference on the Experience of Designing and Application of CAD Systems (CADSM)","volume":"2001 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123893888","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":"Automatic Diagnosis of Diabetic Retinopathy Based on EfficientNet","authors":"Wei Liu, Zetong Zhao, M. Levkiv","doi":"10.1109/CADSM58174.2023.10076511","DOIUrl":"https://doi.org/10.1109/CADSM58174.2023.10076511","url":null,"abstract":"Diabetic retinopathy (DR) is a microvascular complication of diabetes with a high incidence and one of the four major blind eye diseases recognized in the world. At present, in clinical practice, the analysis and diagnosis of fundus retinal photos are mainly carried out by professional doctors, but this process is very dependent on the clinical experience of doctors, which is time-consuming and labor-intensive, misdiagnosis. Based on this, this paper proposes a DR automatic classification method that integrates attention mechanism and EfficientNet to improve the accuracy of classification and discrimination. In view of the problems in the DR data set, processing such as elimination, amplification and normalization is performed; The attention mechanism is integrated into the EfficientNet network, the DR data set is used to learn and train the improved EfficientNet., and the features are extracted. At the same time, the hole convolution is added to increase the receptive field, and the DR images are divided into 5 categories according to their levels. The method proposed in this paper achieves good results in the DR image classification task, with accuracy, precision, sensitivity and F1 score of 0.857, 0.838, 0.886 and 0.767, respectively. The results show that the DR classification algorithm proposed in this paper has good classification performance.","PeriodicalId":196129,"journal":{"name":"2023 17th International Conference on the Experience of Designing and Application of CAD Systems (CADSM)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125072248","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}