S. Sveleba, I. Katerynchuk, I. Kuno, N. Sveleba, O. Semotyjuk
{"title":"Investigation of the Transition Mechanism to Chaos in Multilayer Neural Networks","authors":"S. Sveleba, I. Katerynchuk, I. Kuno, N. Sveleba, O. Semotyjuk","doi":"10.1109/aict52120.2021.9628919","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628919","url":null,"abstract":"Multilayer neural networks were considered. The program in the Python software environment was developed. The transition of the network to an unpredictable (chaotic) mode was described by a cascade of bifurcations that follow one another. The chaos was considered as consequence of the increase in the number of local minima in the area of the global minimum. Increasing of the number of layers of the neural network as well as the number of neurons in the hidden layer leads to an increase in the number of local minima when approaching the global minimum, and thus narrows the range of optimal solutions. Fractal structures on bifurcation diagram were observed. Therefore, the solution to the problem of automatic selection of the learning rate is related to the number of existing local minima.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"08 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125196052","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":"Implementation and Validation of LoRa-Based Systems in the 2.4 GHz Band","authors":"Manuel Schappacher, A. Dant, A. Sikora","doi":"10.1109/aict52120.2021.9628942","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628942","url":null,"abstract":"For the past few years Low Power Wide Area Networks (LPWAN) have emerged as key technologies for the connectivity of many applications in the Internet of Things (IoT) combining low-data rates with strict cost and energy restrictions. Especially LoRa/LoRaWAN enjoys a high visibility on today’s markets, because of its good performance and its open community. Originally LoRa was designed for operation within the Sub-GHz ISM bands for Industrial, Scientific and Medical applications. However, at the end of 2018, a LoRa-based solution in the 2.4GHz ISM-band was presented promising higher bandwidths and higher data rates. Furthermore, it overcomes the limited duty-cycle prescribed by the regulations in the ISM-bands and therefore also opens doors to many novel application fields. Also, due to higher bandwidths and shorter transmission times, the use of alternative MAC layer protocols becomes very interesting, i.e. for TDMA based-approaches. Within this paper, we propose a system architecture with 2.4GHz LoRa components combining two aspects. On the one hand, we present a design and an implementation of a 2.4GHz based LoRaWAN solution that can be seamlessly integrated into existing LoRaWAN back-hauls. On the other hand, we describe deterministic setup using a Time Slotted Channel Hopping (TSCH) approach as defined in the IEEE802.15.4-2015 standard for industrial applications. Finally, measurements show the performance of the system.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117074798","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}
Y. Onykiienko, P. Popovych, Anastasiia Mitsukova, Anna Beldyagina, R. Yaroshenko
{"title":"LoRa Evaluation for University Campus in Urban Conditions","authors":"Y. Onykiienko, P. Popovych, Anastasiia Mitsukova, Anna Beldyagina, R. Yaroshenko","doi":"10.1109/aict52120.2021.9628951","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628951","url":null,"abstract":"LoRa technology is widely used as a data collection network in IoT systems. The paper presents the analysis of signal power attenuation in the network deployment within the KPI Campus in urban conditions. Investigation of signal losses was made for scenarios of line of sight (LOS) and non-line of sight (NLOS) points. A model of path losses in urban conditions at distances typical for signal propagation within micro-and macrocells is obtained. The obtained model is compared with known empirical PL models, the efficiency of the LoRa network is estimated at different values of the spreading factor.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124729059","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":"Defects Detection in PCB with Ground Plane by Clustering and Flood-fill Algorithms","authors":"R. Melnyk, Yurii Havrylko, Mariia Levytska","doi":"10.1109/aict52120.2021.9628899","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628899","url":null,"abstract":"The known K-means clustering and flood-fill algorithms are implemented. To reduce the color number multilevel segmentation by clustering algorithm is realized. A number of levels are taken from user. The etalon PCB image can be used to determine coordinate of pixels forming contacts. The flood-fill algorithm is used to mark contacts, traces and ground plane. The flood-fill algorithm also is used to control contacts of chains. The model of marked chains is being used to detect defects of shot and open in the manufactured PCB.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130448911","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":"Investigating a Different Approaches to Resolve Binary Classification Task with Unbalanced Dataset","authors":"Dmytro Polokhach, V. Kushnir, Oleksandr Vashchuk","doi":"10.1109/aict52120.2021.9628984","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628984","url":null,"abstract":"This work represents methods and approaches for training artificial intelligence when dataset is unbalanced. It helps to use existing dataset instead of generating new one which can be very hard and complex. To measure such methods specific performance metrics were provided. Methods and approaches were applied and results were generated.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123446991","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. Ageyev, T. Radivilova, Oleg Bondarenko, Othman Mohammed
{"title":"Traffic Monitoring and Abnormality Detection Methods for IoT","authors":"D. Ageyev, T. Radivilova, Oleg Bondarenko, Othman Mohammed","doi":"10.1109/aict52120.2021.9628954","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628954","url":null,"abstract":"Monitoring network traffic is an important issues for the networks reliability and security. The statistical model of traffic is at the heart of many methods for detecting traffic anomalies. Existing modern methods of detecting attacks in several cases turn out to be insufficiently reliable, for example, due to the missed moment of the attack, which makes it possible for an attacker to introduce errors into the operation of the system and make it unusable (for example, to carry out a DDOS attack). The main direction of the study was to reduce the impact of the lack of computing resources of IoT devices in the implementation of mechanisms for detecting anomalies. The paper proposes to achieve this through the use of a distributed structure, including cloud computing.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123915387","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}
S. Zagorodnyuk, B. Sus', Anton Komisarov, O. Bauzha
{"title":"Access Control and Management System over Real Estate Objects as a Part of IoT Network Community","authors":"S. Zagorodnyuk, B. Sus', Anton Komisarov, O. Bauzha","doi":"10.1109/aict52120.2021.9628909","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628909","url":null,"abstract":"An overview of access control and management systems (ACMS), which are complex hardware and software systems designed to automate access to a given area or premises, a certain list of people or vehicles has been discussed. It is shown that any ACMS system consists of specific important components, has a certain structure and logic of operation. However, almost all industrial ACMS systems are configured with specialized software that is installed on a separate computer. Such software involves configuration settings, accumulation of logs and reports on the activity of the ACMS system, as well as its remote monitoring. Instead, a branch office is often connected to the Internet through a 3g / 4g mobile network, making it unavailable to an external network. The authors suggested a new scientific and technological procedure, which does not require a separate computer, as all the tools for setting up and monitoring the ACMS system are based on a general-purpose microcontroller Raspberry Pi. Because a microcontroller connected to the Internet through a 3g/4g mobile network maintains a permanent connection to the external SOCKS Proxy service, it is thus available to the external network. The new ACMS system provides full remote configuration and management, including viewing user ID logs over a specified time. The performance of the system by filling a test database and creating a program that generates an arbitrary number of network requests to this database to measure the response time of the system has been analyzed.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130934631","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}
V. Krasnobayev, A. Kuznetsov, Mykhaylo Bagmut, T. Kuznetsova
{"title":"Artificial Intelligence and Number System in Residual Classes","authors":"V. Krasnobayev, A. Kuznetsov, Mykhaylo Bagmut, T. Kuznetsova","doi":"10.1109/aict52120.2021.9628970","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628970","url":null,"abstract":"This article discusses a model of the process of information processing by the human brain, based on the assumption that the storage and processing of information is carried out in a non-positional number system in residual classes (RNS). When accepting the hypothesis about the holographic principle of information processing by the human brain, the expediency and effectiveness of building artificial intelligence systems based on the information processing model in the RNS is obvious. This is due to the fact that the principles and methods of information processing in the RNS are in good agreement with modern concepts and ideas about the process of information processing by the human brain. The accuracy of the description (representation) of the information object G depends on the number and values of the RNS bases. So, the larger the number of RNS bases and the larger they are in value, the more accurately the information object G is described by means of frames. This fact confirms the expediency of using the RNS.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125297903","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":"Model of Spatial-Frequency Characteristics of Video Application","authors":"S. Kiiko, O. Mazurkiewicz, V. Baliar","doi":"10.1109/aict52120.2021.9628922","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628922","url":null,"abstract":"Article presents investigation of spatial-frequency characteristics of video application. The linear model on video application system was proposed, which comprises path as a generalized spatio-frequency filter and allows to represent two models of aperture correction by modelling two-dimensional spatial-frequency characteristics consistent with the anisotropy of human vision and without the last one.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124974410","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 Post-Quantum Secure e-Health System for the Data Management","authors":"M. Iavich, R. Bocu, G. Iashvili, R. Odarchenko","doi":"10.1109/aict52120.2021.9628896","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628896","url":null,"abstract":"The concept of a smart city as a broad concept implies a versatile collection, storage and processing of data for the urban community. Obviously, health data is prioritized. The collection of such data is made possible by wearable medical devices. Generally, the mentioned devices do not store any data they, at best, perform limited processing basic functions and have little or no additional processing the capabilities for the collected information. In this article is described an integrated distributed eHealth system that collects the health information from registered city residents and securely stores and processes medical information in the cloud by means of a comprehensive data privacy encryption model that is based on NTRU public-key cryptosystem. A hash-based digital signature mechanism is used to verify that medical data is correctly assigned to the person concerned. The hash-based digital signature scheme is improved by mean of the novel random number generator. The user data is collected by system using the client application module installed on the user’s smart watch or smartphone and safely transfers them to the cloud server. Similar processing of an encrypted data is occurred by means of Apache Spark service. The IBM OpenWhisk Programming Service is responsible for running event-based handlers. The prototype was tested in a real-world example involving five hundred citizens of Brasov, Romania.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122637768","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}