Filtry
wszystkich: 2730
wybranych: 2179
-
Katalog
- Publikacje 2179 wyników po odfiltrowaniu
- Czasopisma 62 wyników po odfiltrowaniu
- Konferencje 55 wyników po odfiltrowaniu
- Wydawnictwa 1 wyników po odfiltrowaniu
- Osoby 70 wyników po odfiltrowaniu
- Projekty 5 wyników po odfiltrowaniu
- Kursy Online 21 wyników po odfiltrowaniu
- Wydarzenia 4 wyników po odfiltrowaniu
- Dane Badawcze 333 wyników po odfiltrowaniu
Filtry wybranego katalogu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: GRAPH NEURAL NETWORK
-
Accuracy Investigations of Turbine Blading Neural Models Applied to Thermal and Flow Diagnostics
PublikacjaPossibility of replacing computional fluid dynamics simulations by a neural model for fluid flow and thermal diagnostics of steam turbines is investigated. Results of calculations of velocity magnitude of steam for 3D model of the stator of steam turbine is presented.
-
Neural Networks, Support Vector Machine and Genetic Algorithms for Autonomous Underwater Robot Support
PublikacjaIn this paper, artificial neural networks, a classification technique called support vector machine and meta-heuristics genetic algorithm have been considered for development in autonomous underwater robots. Artificial neural networks have been used for seabed modelling as well as support vector machine has been applied for the obstacles classification to avoid some collision problems. Moreover, genetic algorithm has been applied...
-
Berkeley Open Infrastructure for Network Computing
PublikacjaZaprezentowano system BOINC (ang. Berkeley Open Infrastructure for Network Computing) jako interesujące rozwiązanie integrujące rozproszone moce obliczeniowe osobistych komputerów typu PC w Internecie. Przedstawiono zasadę działania opisywanej platformy. W dalszej części zaprezentowano kilka wybranych projektów naukowych wykorzystujących BOINC, które są reprezentatywne w zakresie zastosowania systemu w ujęciu założonego paradygmatu...
-
Network Protection Against Node Attacks Based on Probabilistic Availability Measures
Publikacja -
Transmission Protocol Simulation Framework For The Resource-Constrained Wireless Sensor Network
PublikacjaIn this paper a prototype framework for simulation of wireless sensor network and its protocols are presented. The framework simulates operation of a sensor network with data transmission, which enables simultaneous development of the sensor network software, its hardware and the protocols for wireless data transmission. An advantage of using the framework is converging simulation with the real software. Instead of creating...
-
Investigation of continuous wave jamming in an IEEE 802.15.4 network
PublikacjaThis paper presents how continuous wave jamming affects IEEE 802.15.4 network. To this end, an office-based measurement setup has been proposed. Within the measurement area, 25 nodes have been set up in order to create a IEEE 802.15.4 tree-based test network structure. A dedicated jamming device that generates and transmits a continuous wave signal has been developed. Several tests have been conducted and presented to demonstrate...
-
Graph Vertex Embeddings: Distance, Regularization and Community Detection
Publikacja -
Greedy algorithms for backbone graph coloring in KOALA library
Publikacja -
Nordhaus-Gaddum results for the convex domination number of a graph
PublikacjaPraca dotyczy nierówności typu Nordhausa-Gadduma dla dominowania wypukłego.
-
On the complexity of distributed graph coloring with local minimality constraints
PublikacjaArtykuł traktuje o zachłannym kolorowaniu grafów w modelu rozproszonym. Omówiono algorytmy rozproszone, dające w wyniku pokolorowanie spełniające warunki dla pokolorowań sekwencyjnych typu S oraz Largest-First (LF). Udowodniono również, że każda rozproszona implementacja algorytmu S wymaga co najmniej Omega(log n / log log n) rund, a algorytmu LF co najmniej Omega (n^{1/2}) rund, gdzie n oznacza liczbę wierzchołków grafu.
-
Determination of Odour Interactions in Gaseous Mixtures Using Electronic Nose Methods with Artificial Neural Networks
PublikacjaThis paper presents application of an electronic nose prototype comprised of eight sensors, five TGS-type sensors, two electrochemical sensors and one PID-type sensor, to identify odour interaction phenomenon in two-, three-, four- and five-component odorous mixtures. Typical chemical compounds, such as toluene, acetone, triethylamine, α-pinene and n-butanol, present near municipal landfills and sewage treatment plants were subjected...
-
A survey on network resiliency methodologies against weather-based disruptions
PublikacjaDue to the increasing dependence on network services of our society, research has recently been concentrating on enhancing traditional protection strategies to withstand large-scale failures, as in case of disaster events. The recently-formed EU-funded RECODIS project aims at coordinating and fostering research collaboration in Europe on disaster resiliency in communication networks. In particular, the Working Group (WG) 2 of the...
-
Application of spatial neural simulators of turbine blade rows to fluid flow diagnostics
PublikacjaThis chapter presents the results of neural modelling of fluid flow in steam turbine row. In modelling working conditions of the flow channel varied, thus the aim of the work was to reconstruct the reference state - distributions of velocity, pressure, and losses in flow channel - with high accuracy for fluid flow diagnostics.
-
Analysis of energy efficiency of suburban railway transport network
PublikacjaRising numbers of agglomeration residents cause increased need for people movement on daily basis. Because of congestion of local roads, air pollution and limited parking space, providing mass transit based on electric traction is reasonable. While the electric rail vehicles are considered highly efficient in themselves, they need to be analyzed as a part of a transport network, because energy consumption depends on operating conditions...
-
Quality of Service in ASON/GMPLS Network with Hierarchical Control Plane Structure
PublikacjaThe paper presents the problem of quality of service for hierarchical control plane structure of Automatically Switched Optical Network (ASON) utilizing Generalized Multi-Protocol Label Switching (GMPLS). The approach is implemented to control the multidomain network with required quality of service, in a use case of incomplete domain network information. The authors examine different factors, including resource reservation algorithms...
-
PROGRAMMABLE YANG - BASED INTERFACE IN CONTROL OF OPTICAL TRANSPORT NETWORK
PublikacjaSince over a decade we observe intensive effort of research institutions and industrial consortia on extending flexibility and automation of the transport network control also known under the term network programmability. Key aspect of each programming interface is ability to evolve but also sensitivity to future modifications. As indicated in the past work in the specific context of optical transport networks an important criterion...
-
The Performance of ASON/GMPLS Network with Hierarchical Control Plane Structure
PublikacjaThe paper regards the problem of ASON/GMPLS network performance with hierarchical control plane structure in condition of incomplete domain network information. The authors propose the hierarchical ASON/GMPLS control plane architecture, which fulfills the requirements of modern optical networks and allows to control the multidomain network with requirement quality of service. The authors examine the scalability and properties of...
-
Next generation ITS implementation aspects in 5G wireless communication network
PublikacjaIn the paper the study of Intelligent Transportation systems implementation in the 5G wireless communication network is presented. Firstly, small-cell concept in Ultra Dense Heterogeneous network was analyzed. Secondly, the 5G network requirements were presented which are important from the point of view of transportation systems development. Next, the study on the 5G network architectures proposals dedicated to the ITS systems...
-
Switched-capacitor DC-DC converters in arbitrary switching mode - topologically derived resistive models based on incremental graph approach.
PublikacjaIn the preceding paper we reviewed some of modeling approaches aimed at systematic formulation and solution of switched capacitor DC-DC converters. In our review, special attention was paid to computationally efficient and mathematically elegant methods. In so doing we had tried to demonstrate the virtues of unified Incremental Graph (IG) approach. Incremental Graph is, in concept, a tool originally created for analysis and synthesis...
-
Application of BAN Network to Increase Security in Transport Systems
PublikacjaIn the article general characteristics of the BAN network with M2M communications are presented. These are networks that enable the implementation of wireless transmission of signals using special sensors located on the body or implanted subcutaneously. These sensors allow monitoring of different type life parameters of a human. In the next part of work there is proposed the implementation of BAN networks to transport systems as...
-
Fusion-based Representation Learning Model for Multimode User-generated Social Network Content
PublikacjaAs mobile networks and APPs are developed, user-generated content (UGC), which includes multi-source heterogeneous data like user reviews, tags, scores, images, and videos, has become an essential basis for improving the quality of personalized services. Due to the multi-source heterogeneous nature of the data, big data fusion offers both promise and drawbacks. With the rise of mobile networks and applications, UGC, which includes...
-
The Central European GNSS Research Network (CEGRN) dataset
PublikacjaThe Central European GNSS Research Network (CEGRN) collects GNSS data since 1994 from contributors which today include 42 Institutions in 33 Countries. CEGRN returns a dataset of coordinates and velocities computed according to international standards and the most recent processing procedures and recommendations. We provide a dataset of 1229 positions and velocities resulting from 3 or more repetitions of coordinate measurements...
-
A compact smart sensor based on a neural classifier for objects modeled by Beaunier's model
PublikacjaA new solution of a smart microcontroller sensor based on a simple direct sensor-microcontroller interface for technical objects modeled by two-terminal networks and by the Beaunier’s model of anticorrosion coating is proposed. The tested object is stimulated by a square pulse and its time voltage response is sampled four times by the internal ADC of microcontroller. A neural classifier based on measurement data classifies the...
-
Evaluation of Facial Pulse Signals Using Deep Neural Net Models
PublikacjaThe reliable measurement of the pulse rate using remote photoplethysmography (PPG) is very important for many medical applications. In this paper we present how deep neural networks (DNNs) models can be used in the problem of PPG signal classification and pulse rate estimation. In particular, we show that the DNN-based classification results correspond to parameters describing the PPG signals (e.g. peak energy in the frequency...
-
From Scores to Predictions in Multi-Label Classification: Neural Thresholding Strategies
PublikacjaIn this paper, we propose a novel approach for obtaining predictions from per-class scores to improve the accuracy of multi-label classification systems. In a multi-label classification task, the expected output is a set of predicted labels per each testing sample. Typically, these predictions are calculated by implicit or explicit thresholding of per-class real-valued scores: classes with scores exceeding a given threshold value...
-
Enhancing Renal Tumor Detection: Leveraging Artificial Neural Networks in Computed Tomography Analysis
PublikacjaRenal cell carcinoma is one of the most common cancers in Europe, with a total incidence rate of 18.4 cases per 100 000 population. There is currently significant overdiagnosis (11% to 30.9%) at times of planned surgery based on radiological studies. The purpose of this study was to create an artificial neural network (ANN) solution based on computed tomography (CT) images as an additional tool to improve the differentiation of...
-
5G Technologies in Intelligent Transport Systems - Architectures, Virtualization and Network Slicing
PublikacjaIn the paper, 5G communication technologies implemented for Intelligent Transport Systems are discussed. Firstly, the essence of the 5G system concept is presented, and the problem of network functions virtualization (NFV) is analyzed. Moreover, the principle of virtualization is explained. Secondly, the analysis of network slicing is performed, from the point of view of transport systems implementation in the...
-
Digital Audio Broadcasting or Webcasting: A Network Quality Perspective
PublikacjaIn recent years, many alternative technologies of delivering audio content have emerged, with different advantages and disadvantages. In this paper pros and cons of digital audio broadcasting and webcasting transmission techniques in a network quality perspective are described. A case study of user expectations with respect to currently available services is analyzed, and the perceived quality of real digital broadcasted and webcasted...
-
Cellular network quality evaluation at a university campus on the eve of 5G
PublikacjaThanks to the availability of mobile devices and the spread of broadband access around the world, the number of network users continues to grow. This has raised user awareness when it comes to the quality of content they consume. Many service providers and operators focus on monitoring QoN (Quality of Network) and QoS (Quality of Service) parameters, particularly those influenced by bandwidth and latency. However, for most end-users,...
-
Research on protection mechanisms of Resilient Packet Ring Network.
PublikacjaPaper describes iSteering - a new method to control traffic in case of RPR network failure. There's comparison of packet wrapping, steering and our proposed method iSteering, which can be used in case of transmitter/receiver or fiber failure. Numerical analysis for even and random traffic flow has been made in order to compare packet wrapping, steering and iSteering. The results of all the tests are included.
-
Modelling of energy flow in mechatronic systems. A bond graph approach
PublikacjaW referacie przedstawiono w sposób jednoliy modelowanie systemów mechatroniki metodą grafów wiązań (GW) w aspekcie symulacji przepływu energii. Omówiono ogólne założenia modelowania w ujęciu GW. Modelowanie przepływu energii rozważano na przykładzie napędu pojazdu hybrydowego PH-MAK.
-
Tighter bounds on the size of a maximum P3-matching in a cubic graph
PublikacjaW pracy pokazano, że największe P3-skojarzenie dla dowolnego grafu o n>16 wierzchołkach składa się z przynajmniej 117n/152 wierzchołków.
-
Modelling of energy flow in electrical machines. A bond graph approach
PublikacjaPrzedstawiono w ujęcia grafów wiązań model przepływu energii/mocy w maszynach elektrycznych pracujących w hybrydowych systemach przetwarzania energii. Jako przykład do rozważań przyjęto system napędu trakcyjnego pojazdów hybrydowych.
-
Self-stabilizing algorithms for graph coloring with improved performance guarantees
PublikacjaW pracy rozważa się rozproszony model obliczeń, w którym struktura systemu jest reprezentowana przez graf bezpośrednich połączeń komunikacyjnych. W tym modelu podajemy nowy samostabilizujący algorytm kolorowania grafów oparty na konstrukcji drzewa spinającego. Zgodnie z naszą wiedzą jest to pierwszy algorytm z gwarantowaną wielomianową liczbą ruchów, który dokładnie koloruje grafy dwudzielne.
-
Towards explainable motion prediction using heterogeneous graph representations
Publikacja -
USING ARTIFICIAL NEURAL NETWORKS FOR PREDICTING SHIP FUEL CONSUMPTION
PublikacjaIn marine vessel operations, fuel costs are major operating costs which affect the overall profitability of the maritime transport industry. The effective enhancement of using ship fuel will increase ship operation efficiency. Since ship fuel consumption depends on different factors, such as weather, cruising condition, cargo load, and engine condition, it is difficult to assess the fuel consumption pattern for various types...
-
A Comprehensive Analysis of Deep Neural-Based Cerebral Microbleeds Detection System
PublikacjaMachine learning-based systems are gaining interest in the field of medicine, mostly in medical imaging and diagnosis. In this paper, we address the problem of automatic cerebral microbleeds (CMB) detection in magnetic resonance images. It is challenging due to difficulty in distinguishing a true CMB from its mimics, however, if successfully solved it would streamline the radiologists work. To deal with this complex three-dimensional...
-
Investigation of Continuous Wave Jamming in an IEEE 802.15.4 Network
PublikacjaThis paper presents how continuous wave jamming affects IEEE 802.15.4 network. To this end, an office-based measurement setup has been proposed. Within the measurement area, 25 nodes have been set up in order to create a IEEE 802.15.4 tree-based test network structure. A dedicated jamming device that generates and transmits a continuous wave signal has been developed. Several tests have been conducted and presented to demonstrate...
-
Smart Approach for Glioma Segmentation in Magnetic Resonance Imaging using Modified Convolutional Network Architecture (U-NET)
PublikacjaSegmentation of a brain tumor from magnetic resonance multimodal images is a challenging task in the field of medical imaging. The vast diversity in potential target regions, appearance and multifarious intensity threshold levels of various tumor types are few of the major factors that affect segmentation results. An accurate diagnosis and its treatment demand strict delineation of the tumor affected tissues. Herein, we focus on...
-
Modelling of network schedule including priority of selected technical resources
PublikacjaThe paper presents a method of network planning CPM – Critical Path Method. The author compares models of optimal solutions to design deadlines for individual works, taking various leading technical resources such as is labor and a tower crane into account.
-
Performance Evaluation of a Multidomain IMS/NGN Network Including Service and Transport Stratum
PublikacjaThe Next Generation Network (NGN) architecture was proposed for delivering various multimedia services with guaranteed quality. For this reason, the elements of the IP Multimedia Subsystem (IMS) concept (an important part of 4G/5G/6G mobile networks) are used in its service stratum. This paper presents comprehensive research on how the parameters of an IMS/NGN network and traffic sources influence mean Call Set-up Delay (E(CSD))...
-
Traffic Type Influence on QoS Network Performance of Streaming Traffic Class
PublikacjaFeasibility study on QoS routing proved that the traffic type influence the network performance. The performance is defined here as a number of packets serviced by the network. In the paper additional element - buffers lengths used in service system was verified in terms of dependencies with routing performance. We present results obtained by simulation for many simulation scenarios. Analysis was done for two different network...
-
The application of neural networks in forecasting the influence of traffic-induced vibrations on residential buildings
PublikacjaTraffic-induced vibrations may cause the cracking of plaster, damage to structural elements and, in extreme cases, may even lead to the structural collapse of residential buildings. The aim of this article is to analyse the effectiveness of a method of forecasting the impact of vibrations on residential buildings using the concept of artificial intelligence. The article presents several alternative forecasting systems for which...
-
A method of the UMTS-FDD network design based on universal load characteristics
PublikacjaIn the paper an original method of the UMTS radio network design was presented. The method is based on simple way of capacity-coverage trade-off estimation for WCDMA/FDD radio interface. This trade-off is estimated by using universal load characteristics and normalized coverage characteristics. The characteristics are useful for any propagation environment as well as for any service performance requirements. The practical applications...
-
Pathological brain network activity: memory impairment in epilepsy
PublikacjaOur thinking, memory and cognition in general, relies upon precisely timed interactions among neurons forming brain networks that support cognitive processes. The surgical evaluation of drug-resistant epilepsy using intracranial electrodes provides a unique opportunity to record directly from human brain and to investigate the coordinated activity of cognitive networks. In this issue of Neurology®, Kleen and colleagues1 implicate...
-
Global Digital Technology Convergence: Driving Diffusion via Network Effects
PublikacjaSince the 1970s, we have witnessed unprecedented diffusion of digital technologies in both speed and geographic coverage. These technologies are pervasive and disruptive, and lead to profound shifts and transformations in societies and economies. Many claim that emerging network externalities are the principal phenomenon driving the process of technology diffusion and determining its in-time dynamics. This book analyses the unique...
-
Multi Queue Approach for Network Services Implemented for Multi Core CPUs
PublikacjaMultiple core processors have already became the dominant design for general purpose CPUs. Incarnations of this technology are present in solutions dedicated to such areas like computer graphics, signal processing and also computer networking. Since the key functionality of network core components is fast package servicing, multicore technology, due to multi tasking ability, seems useful to support packet processing. Dedicated...
-
Brand loyalty creation in the social network. Does the product category matter?
PublikacjaThe final goal of all marketers’ effort is to achieve a high level of loyalty toward their brands. Social network brand sites are increasingly attracting the attention of scientists and managers intrigued by their potential application for brand loyalty creation. The aim of this research, based on European sample, is to fill the gap in understanding the product category loyalty and brand loyalty relation as an output of brand identification...
-
Sensing Direction of Human Motion Using Single-Input-Single-Output (SISO) Channel Model and Neural Networks
PublikacjaObject detection Through-the-Walls enables localization and identification of hidden objects behind the walls. While numerous studies have exploited Channel State Information of Multiple Input Multiple Output (MIMO) WiFi and radar devices in association with Artificial Intelligence based algorithms (AI) to detect and localize objects behind walls, this study proposes a novel non-invasive Through-the-Walls human motion direction...
-
Non-isolated resonant quasi-Z-source network DC–DC converter
PublikacjaA novel non-isolated resonant quasi-impedance (quasi-Z)-source network DC–DC converter is proposed. The resonant impedance source network is derived from the quasi-Z-source network by including the autotransformer-based resonant cell instead of the second inductor of the quasi-Z-network. The leakage inductance of the autotransformer and two resonant capacitors connected in series with the autotransformer windings constitute a high-frequency...