Filters
total: 3175
filtered: 2614
-
Catalog
- Publications 2614 available results
- Journals 87 available results
- Conferences 86 available results
- Publishing Houses 1 available results
- People 105 available results
- Projects 8 available results
- e-Learning Courses 30 available results
- Events 3 available results
- Open Research Data 241 available results
Chosen catalog filters
displaying 1000 best results Help
Search results for: NETWORK RECONFIGURATION
-
Tool Wear Monitoring Using Improved Dragonfly Optimization Algorithm and Deep Belief Network
PublicationIn recent decades, tool wear monitoring has played a crucial role in the improvement of industrial production quality and efficiency. In the machining process, it is important to predict both tool cost and life, and to reduce the equipment downtime. The conventional methods need enormous quantities of human resources and expert skills to achieve precise tool wear information. To automatically identify the tool wear types, deep...
-
Dataset Related Experimental Investigation of Chess Position Evaluation Using a Deep Neural Network
PublicationThe idea of training Articial Neural Networks to evaluate chess positions has been widely explored in the last ten years. In this paper we investigated dataset impact on chess position evaluation. We created two datasets with over 1.6 million unique chess positions each. In one of those we also included randomly generated positions resulting from consideration of potentially unpredictable chess moves. Each position was evaluated...
-
Predicting Ice Phenomena in a River Using the Artificial Neural Network and Extreme Gradient Boosting
PublicationForecasting ice phenomena in river systems is of great importance because these phenomena are a fundamental part of the hydrological regime. Due to the stochasticity of ice phenomena, their prediction is a difficult process, especially when data sets are sparse or incomplete. In this study, two machine learning models—Multilayer Perceptron Neural Network (MLPNN) and Extreme Gradient Boosting (XGBoost)—were developed to predict...
-
An automatic selection of optimal recurrent neural network architecture for processes dynamics modelling purposes
PublicationA problem related to the development of algorithms designed to find the structure of artificial neural network used for behavioural (black-box) modelling of selected dynamic processes has been addressed in this paper. The research has included four original proposals of algorithms dedicated to neural network architecture search. Algorithms have been based on well-known optimisation techniques such as evolutionary algorithms and...
-
Study of Multi-Class Classification Algorithms’ Performance on Highly Imbalanced Network Intrusion Datasets
PublicationThis paper is devoted to the problem of class imbalance in machine learning, focusing on the intrusion detection of rare classes in computer networks. The problem of class imbalance occurs when one class heavily outnumbers examples from the other classes. In this paper, we are particularly interested in classifiers, as pattern recognition and anomaly detection could be solved as a classification problem. As still a major part of...
-
Selection of an artificial pre-training neural network for the classification of inland vessels based on their images
PublicationArtificial neural networks (ANN) are the most commonly used algorithms for image classification problems. An image classifier takes an image or video as input and classifies it into one of the possible categories that it was trained to identify. They are applied in various areas such as security, defense, healthcare, biology, forensics, communication, etc. There is no need to create one’s own ANN because there are several pre-trained...
-
Prediction of antimicrobial activity of imidazole derivatives by artificial neural networks
Publication -
Water hammer analysis in pipe networks by the method of characteristics (MOC).
PublicationZastosowano w pracy metodę charakterystyk do analizy zjawiska uderzenia hydraulicznego w sieci wodociągowej pierścieniowej.
-
A practical approach to restoration in survivable IP/WDM mesh networks
PublicationW pracy omówiono warstwową architekturę: IP na optycznej sieci transportowej (OTN). Węzły mają zintegrowaną funkcjonalność: rulerów IP i przełącznic optycznych (OXC). Dopuszcza się możliwość konwersji długości fal na ścieżkach optycznych. Autor rozważa zagadnienie znalezienia ścieżek optycznych o możliwie najniższym koszcie przy spełnieniu ograniczeń przepustowości, wymaganych strumieni zapotrzebowań i zabezpieczonych z góry na...
-
Proposal of improvement to fairness mechanism of Resilient Packet Ring networks
Publication.
-
Application of neural networks for description of pressure distribution in slide bearing.
PublicationBadano rozkład ciśnienia hydrodynamicznego w łożysku ślizgowym dla wybranych wariantów łożyska. Wykazano, że zastosowanie sieci neuronowych umożliwia opis rozkładu ciśnienia hydrodynamicznego z uwzględnieniem zmian geometrycznych (bezwymiarowa długość - L) i mechanicznych (mimośrodowość względem H) łożyska.
-
Identification of slide bearing main parameters using neural networks.
PublicationWykazano, że sieci neuronowe jak najbardziej nadają się do identyfikacji głównych parametrów geometrycznych i ruchowych hydrodynamicznych łożysk ślizgowych.
-
Estimation the rhythmic salience of sound with association rules and neural networks
PublicationW referacie przedstawiono eksperymenty mające na celu automatyczne wyszukiwanie wartości rytmicznych we frazie muzycznej. W tym celu wykorzystano metody data mining i sztuczne sieci neuronowe.
-
Exploring Neural Networks for Musical Instrument Identification in Polyphonic Audio
PublicationThe purpose of this paper is to introduce neural network-based methods that surpass state-of-the-art (SOTA) models, either by training faster or having simpler architecture, while maintaining comparable effectiveness in musical instrument identification in polyphonic music. Several approaches are presented, including two authors’ proposals, i.e., spiking neural networks (SNN) and a modular deep learning model named FMCNN (Fully...
-
Buck-Boost Inverters with Symmetrical Passive Four-terminal Networks
Publication -
Numerical modeling of force and contact networks in fragmented sea ice
Publication -
Gesture Recognition With the Linear Optical Sensor and Recurrent Neural Networks
PublicationIn this paper, the optical linear sensor, a representative of low-resolution sensors, was investigated in the multiclass recognition of near-field hand gestures. The recurrent neural network (RNN) with a gated recurrent unit (GRU) memory cell was utilized as a gestures classifier. A set of 27 gestures was collected from a group of volunteers. The 27 000 sequences obtained were divided into training, validation, and test subsets....
-
Trade-offs in multiparty Bell-inequality violations in qubit networks
PublicationTwo overlapping bipartite binary input Bell inequalities cannot be simultaneously violated as this would contradict the usual no-signalling principle. This property is known as monogamy of Bell inequality violations and generally Bell monogamy relations refer to trade-offs between simultaneous violations of multiple inequalities. It turns out that multipartite Bell inequalities admit weaker forms of monogamies that allow for violations...
-
On the Disaster Resiliency within the Context of 5G Networks : The RECODIS Experience
PublicationNetwork communications and the Internet pervade our daily activities so deeply that we strongly depend on the availability and quality of the services they provide. For this reason, natural and technological disasters, by affecting network and service availability, have a potentially huge impact on our daily lives. Ensuring adequate levels of resiliency is hence a key issue that future network paradigms, such as 5G, need to address. This...
-
Using neural networks to examine trending keywords in Inventory Control
Publication -
Bin-packing based optimisation of EON Networks with S-BVTs
Publication -
Protecting Wireless Mesh Networks Against Adverse Weather Conditions
Publication -
A Review of Traffic Analysis Attacks and Countermeasures in Mobile Agents' Networks
PublicationFor traditional, message-based communication, traffic analysis has been already studied for over three decades and during that time various attacks have been recognised. As far as mobile agents’ networks are concerned only a few, specific-scope studies have been conducted. This leaves a gap that needs to be addressed as nowadays, in the era of Big Data, the Internet of Things, Smart Infrastructures and growing concerns for privacy,...
-
Generation-recombination and 1/f noise in carbon nanotube networks
PublicationThe low-frequency noise is of special interest for carbon nanotubes devices, which are building blocks for a variety of sensors, including radio frequency and terahertz detectors. We studied noise in as-fabricated and aged carbon nanotube networks (CNNs) field-effect transistors. Contrary to the majority of previous publications, as-fabricated devices demonstrated the superposition of generation-recombination (GR) and 1/f noise...
-
Disaster Resilience of Optical Networks: State of the Art, Challenges, and Opportunities
PublicationFor several decades, optical networks, due to their high capacity and long-distance transmission range, have been used as the major communication technology to serve network traffic, especially in the core and metro segments of communication networks. Unfortunately, our society has often experienced how the correct functioning of these critical infrastructures can be substantially hindered by massive failures triggered by natural...
-
Explainable AI for Inspecting Adversarial Attacks on Deep Neural Networks
PublicationDeep Neural Networks (DNN) are state of the art algorithms for image classification. Although significant achievements and perspectives, deep neural networks and accompanying learning algorithms have some important challenges to tackle. However, it appears that it is relatively easy to attack and fool with well-designed input samples called adversarial examples. Adversarial perturba-tions are unnoticeable for humans. Such attacks...
-
An SDN-based technique for reducing handoff times in WiFi networks
Publication -
Modeling of Wireless Traffic Load in Next Generation Wireless Networks
Publication -
Measurement of Coherence Bandwidth in UHF Radio Channels for Narrowband Networks
PublicationThis paper presents results of investigation on the coherence bandwidth of narrowband radio channels in 430MHz band. The coherence bandwidth values were estimated froma power delay profile obtained by recording CDMA2000 forward channel signals during real-fieldmeasurements in various environments:mediumcity, flat terrain, and hilly terrain in northern Poland.The results of measurements are compared with characteristic parameters...
-
Exploring the role of social networks among entrepreneurial Polish immigrants
PublicationThe paper reports on the explanatory case study among seven Polish enterprising migrants from Aberdeen Scotland. The aim of the paper is to examine role of social support structure and social networks for enterprising Poles. It also attempts to extend of Waldinger et al (2000) ethnic business development model in the context of entrepreneurial strategies taken from by immigrants from their country of origin, claiming that transition...
-
Interdependence between Power Grids and Communication Networks: A Resilience Perspective
PublicationPower network resilience is increasingly dependent on communication networks. Besides traditional generation, power networks need to accommodate increasingly high penetration levels of dispersed micro generation, mostly based on renewable sources, and increasing and challenging demand, such as electric vehicles. At the same time the deployment of enabling technologies throughout the power grid makes available new demand resources...
-
The structural face of competition, cooperation and coopetition inside business networks
Publication -
Discouraging Traffic Remapping Attacks in Local Ad Hoc Networks
PublicationQuality of Service (QoS) is usually provided in ad hoc networks using a class-based approach which, without dedicated security measures in place, paves the way to various abuses by selfish stations. Such actions include traffic remapping attacks (TRAs), which consist in claiming a higher traffic priority, i.e., false designation of the intrinsic traffic class so that it can be mapped onto a higher-priority class. In practice, TRAs...
-
Practical issues for the implementation of survivability and recovery techniques in optical networks
PublicationFailures in optical networks are inevitable. They may occur during work being done for the maintenance of other infrastructures, or on a larger scale as the result of an attack or large-scale disaster. As a result, service availability, an important aspect of Quality of Service (QoS), is often degraded. Appropriate fault recovery techniques are thus crucial to meet the requirements set by the Service Level Agreements (SLAs) between...
-
Neural networks based NARX models in nonlinear adaptive control
Publication -
Forecasting demand for products in distribution networks using R software
Publication -
Review of Diameter protocol implementations for realization of communication in NGN networks
PublicationIn the paper Diameter protocol as well as its applications in the context of Next Generation Network (NGN) are described. Diameter message content and Attribute-Value Pairs (AVPs) concept are presented. Critical review of open source Diameter implementations is carried out. The performed analysis takes into consideration programming language, availability, support and documentation aspects. Basing on the review project fulfilling...
-
Fast Service Recovery under Shared Protection in WDM Networks
PublicationNiniejszy artykuł dotyczy zagadnienia doboru tras przeżywalnych dla ruchu statycznego w zorientowanych połączeniowo sieciach WDM, przy wykorzystaniu idei współdzielonych ścieżek zabezpieczających. Pierwsza część jest poświęcona warunkom koniecznym oraz charakterystykom typowej metody współdzielenia zasobów ścieżek zabezpieczających, ze szczególnym uwzględnieniem uzyskiwanej średniej długości ścieżek zabezpieczających oraz wartości...
-
Imminent threats analysis and security level evaluation in social networks
PublicationRozprawa doktorska poświęcona jest analizie nadciągających zagrożeń w sieciach społecznych. Dotyczy to takich zjawisk jak spam, phishing, kradzież tożsamości czy ataki na systemy reputacji w serwisach aukcji internetowych. W pracy zaproponowano metodę pozwalającą na wczesne wykrycie zagrożeń w sieciach społecznych w oparciu o zdefiniowane modele zachowań aktorów sieci. Modele zachowań tworzone są za pomocą podgrafów wzorcowych...
-
Routing decisions independent of queuing delays in broadband leo networks
PublicationThis paper presents an analysis of queuing and propagation delays of Inter-Satellite Links (ISLs) in broadband Low-Earth Orbit (LEO) satellite networks. It is shown that queuing delays are negligible in all reasonable working conditions of the broadband ISL network. This fact makes it possible to simplify the routing protocols in such networks and permits using already known multi-commodity flow solutions for routing. The performance...
-
Application of Artificial Neural Networks in Investigations of Steam Turbine Cascades
PublicationZaprezentowano wyniki badań numerycznych zastosowania sieci neuronowych przy obliczeniach przepływów w palisadach turbin parowych. Na podstawie uzyskanych wyników wykazano, że sieci neuronowe mogą być używane do szacowania przestrzennego rozkładu parametrów przepływu, takich jak entalpia, entropia, ciśnienie czy prędkość czynnika w kanale przepływowym. Omówiono również zastosowania tego typu metod przy projektowaniu palisad, stopni...
-
Localization in wireless sensor networks using switched parasitic antennas
PublicationA switched parasitic monopole antenna for 2.4 GHz ISM applications is design and investigated in this paper. One of the most promising applications for such switched-beam antennas is localization in wireless sensor networks (WSN). It is demonstrated that the use of this antenna improves accuracy of localization algorithms and allows for reduction of the number of reference nodes in localization system.
-
Joint optimization of anycast and unicast flows in survivable optical networks
PublicationZnane z literatury dotychczasowe prace związane z ochroną ruchu przed awarią elementów sieci dotyczą transmisji typu unicast (jeden-do-jednego). Niniejszy artykuł jest pierwszym prezentującym rozwiązanie jednoczesnej ochrony transmisji anycast (jeden-do-jednego-z-wielu) oraz transmisji unicast. Proponowane podejście wykorzystuje model ochrony ścieżki (ang. path protection). Zagadnienie zostało sformułowane w postaci odpowiedniego...
-
Grade of service determination methodology in IP networks with SIP protocol
PublicationAlthough Grade of Service is very important in VoIP providers evaluation, We wasn't able to find any paper regarding the topic of measuring GoS variables for IP networks utilizing SIP, which are defined like for PSTN/ISDN/GSM networks (post-selection delay, answering delay, release delay, or probability of end-to-end blocking). Due to the lack of research in this field, it was necessary to start from defining measures and cover...
-
Directed percolation effects emerging from superadditivity of quantum networks
PublicationEntanglement-induced nonadditivity of classical communication capacity in networks consisting of quantum channels is considered. Communication lattices consisting of butterfly-type entanglement-breaking channels augmented, with some probability, by identity channels are analyzed. The capacity superadditivity in the network is manifested in directed correlated bond percolation which we consider in two flavors: simply directed and...
-
Performance of FAN conception of traffic control in IP QoS networks
PublicationIn this paper we present the architectural implementation of Flow Aware Networking (FAN), a new approach for realizing QoS guarantees in the Internet. We also propose FAN traffic control algorithm which performs traffic control on flow level. Using the proposed FAN node model, we conduct simulation research to prove if FAN can be a new approach for realizing QoS guarantees. The basis of this research is finding a way to guarantee...
-
Cost minimization in wireless networks with a bounded and unbounded number of interfaces
PublicationPraca dotyczy problemu minimalizacji energii poprzez selektywne odłączanie urządzeń komunikacyjnych w wielointerfejsowych sieciach bezprzewodowych w taki sposób, by zapewnić realizację wymaganego grafu połączeń. Sformułowano problem optymalizacyjny, podano wyniki dotyczące jego trudności i zaproponowano algorytmy optymalizacyjne. Rozważono zarówno wariant, w którym liczba interfejsów komunikacyjnych jest parametrem stałym (narzuconym...
-
Support networks in Poland and other countries - making for cooperation or support?
PublicationPraca prezentuje przykłady instytucji wspierających przedsiębiorczość i kooperację między małymi przedsiębiorstwami i/lub przedsiębiorcami w Polsce i innych krajach. Przedstawione są również konkretne działania jakich podejmują się te odgórnie lub oddolnie tworzone instytucje podejmują.
-
Hydraulic transients analysis in pipe networks by the method of characteristics (MOC)
PublicationW pracy przedstawiono wyniki badań eksperymentalnych i analizy numerycznej zjawiska przepływów nieustalonych w przewodach pojedynczych oraz symulacji numerycznych w sieci pierścieniowej. Model matematyczny stanowi układ dwóch równań różniczkowych cząstkowych typu hiperbolicznego, które rozwiązano za pomocą metody charakterystyk. Badania eksperymentalne przeprowadzono na modelu w skali laboratoryjnej. Uzyskano dobrą zgodność obliczeń...
-
Forecasting of currency exchange rates using artificial neural networks
PublicationW rozdziale tym autor przedstawił wyniki swoich badań nad wykorzystaniem sztucznych sieci neuronowych do prognozowania kursu walut (na przykładzie pary walutowej PLN-USD).Głównym celem badań było porównanie skuteczności przewidywania kursu złotówki w latach 1997 - 2005 przy pomocy różnych rodzajów sieci neuronowych.