Information, Computing and Intelligent systems, No. 1
Постійне посилання зібрання
Переглянути
Нові надходження
Документ Відкритий доступ Making an iot development platform from a simple microcontroller demonstration board(National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", 2020) Muraviov, Ihor; Taraniuk, Viktoriia; Klymenko, IrynaThe IOT is now in trend. Because of its huge popularity and business interest to it, IOT is only now coming massively to universities worldwide as a separate study. This article provides an IOT solution based on embedded technologies that were not specifically designed for IOT. The core of this solution - board is developed for studying peripherals of a particular general-purpose MCU. But we successfully adapted it to use in IOT and for study of IOT systems.Документ Відкритий доступ Road monitoring system based on iot technology for SmartCity(National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", 2020) Кopiika, Anton; Piskun, Roman; Tkachenko, Valentyna; Klymenko, IrynaThis work is devoted to the problem of automatic road quality control, which can be used by both road repair services and common drivers. This paper provides a survey of different known techniques and algorithms of finding potholes on the road and describe our own method, using accelerometer. It will be shown our device for detecting potholes on the road, which can be used, as a part of the IoT system of SmartCity. It uses data from an accelerometer for finding road bumps.Документ Відкритий доступ Petri-object simulation: technique and software(National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", 2020) Stetsenko, Inna; Dyfuchyn, AntonNowadays information systems tend to be including components for transforming data into information applying modelling and simulation. Combined with real-time data, discrete event simulation could create powerful making decision and control systems. For these purposes, simulation software should be concentrated on creation the model as a code which can be easy integrated with other components of software. In this regard, Petri-object simulation technique, the main concept of which is to compose the code of model of complicated discrete event system in a fast and flexible way, simultaneously providing fast running the simulation, is requisite. The behaviour description of the model based on stochastic multichannel Petri net while the model composition is grounded on object-oriented technology. The Petri-object simulation software provides scalable simulation algorithm, graphical editor, correct transformation graphical images into model, correct simulation results. Graphical editor helps to cope with error-prone process of linking elements with each other. For better understanding the technique, the Petri-object model of web information system has been developed. Investigation of the response time has been conducted. The experiment has revealed system parameters impact on the value of response time. Thus, the model can be useful to avoid long-running request.Документ Відкритий доступ The method of SDN clustering for controller load balancing(National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", 2020) Dolynnyi, Oleksandr; Nikolskiy, Serhiy; Kulakov, YuriiThe paper proposes the method of SDN clustering using connections density and controller load distribution that solves the problem of controller load balancing. Clustering efficiency criteria have been considered, including fault tolerance, controller-to-switch and intercontroller latency and network limitations. Review of the key clustering methods has been performed, and the base algorithm for modification has been chosen. Density-based controller placement algorithm is modified to solve the problem of multicontroller placement. Metric of the node boundary index is introduced to advance the efficiency of proposed algorithm. A software implementation of the developed algorithm has been created, and its performance has been tested. The algorithm’s modelling results have been compared with those of the other algorithms using the metrics of distribution of service traffic propagation delay and computational speed in relation to network topology size.Документ Відкритий доступ Hash search organization in e-dictionaries using block ciphers(National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", 2020) Markovskyi, Olexander; Humeniuk, Inna; Shevchenko, OlhaThe article is devoted to the problem of developing high-speed electronic dictionaries for systems computer translation. The method of organizing a high-speed electronic dictionary based on an ideal hash addressing, where the cryptographic cipher block acts as a hash transformation is proposed. This method was developed taking into account the multilevel memory structure of modern computer systems. It was testified theoretically and experimentally that the proposed organization of electronic dictionaries guarantees at least twice higher search rate compared to known technologies.Документ Відкритий доступ Protected discrete Fourier transform implementation on remote computer systems(National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", 2020) Mirataei, Alireza; Khalil, Hana; Markovskyi, OlexanderEffective method of the discrete Fourier transform acceleration with the use of cloud computing is theoretically substantiated and developed. The reigning feature of the suggested method is homomorphic encryption of the input signals, which provides efficient protection during the remote calculation. It has been shown theoretically and experimentally that the proposed method allows one to 1-2 orders of magnitude to speed up the processing of signals while maintaining their confidentiality. The proposed method can be applied for effective signal stream processing in clouds.Документ Відкритий доступ Loop parallelization automation for graphics processing units(National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", 2020) Doroshenko, Anatoliy; Beketov, Olexii; Yatsenko, OlenaA technology that allows extending GPU capabilities to deal with data volumes that outfit internal GPU’s memory capacity is proposed. It involves loop tiling and data serialization and can be applied to utilize clusters consisting of several GPUs. Applicability criterion is specified and a semi-automatic proof-of-concept software tool is implemented. The experiment to demonstrate the feasibility of the proposed technology is described.Документ Відкритий доступ USAK method for the reinforcement learning(National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", 2020) Novotarskyi, Mykhailo; Kuzmich, ValentinIn the field of reinforcement learning, tabular methods have become widespread. There are many important scientific results, which significantly improve their performance in specific applications. However, the application of tabular methods is limited due to the large amount of resources required to store value functions in tabular form under high-dimensional state spaces. A natural solution to the memory problem is to use parameterized function approximations. However, conventional approaches to function approximations, in most cases, have ceased to give the desired result of memory reduction in solving real world problems. This fact became the basis for the application of new approaches, one of which is the use of Sparse Distributed Memory (SDM) based on Kanerva coding. A further development of this direction was the method of Similarity-Aware Kanerva (SAK). In this paper, a modification of the SAK method is proposed, the Uniform Similarity-Aware Kanerva (USAK) method, which is based on the uniform distribution of prototypes in the state space. This approach has reduced the use of RAM required to store prototypes. In addition, reducing the receptive distance of each of the prototypes made it possible to increase the learning speed by reducing the number of calculations in the linear approximator.