Wyszukiwarka
Filtry
wszystkich: 1776
wybranych: 1360
-
Katalog
- Publikacje 1360 wyników po odfiltrowaniu
- Czasopisma 66 wyników po odfiltrowaniu
- Konferencje 64 wyników po odfiltrowaniu
- Osoby 67 wyników po odfiltrowaniu
- Projekty 3 wyników po odfiltrowaniu
- Kursy Online 21 wyników po odfiltrowaniu
- Wydarzenia 1 wyników po odfiltrowaniu
- Dane Badawcze 194 wyników po odfiltrowaniu
Filtry wybranego katalogu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: RECURRENT NEURAL NETWORKS
-
TOWARDS EXPLAINABLE CLASSIFIERS USING THE COUNTERFACTUAL APPROACH - GLOBAL EXPLANATIONS FOR DISCOVERING BIAS IN DATA
PublikacjaThe paper proposes summarized attribution-based post-hoc explanations for the detection and identification of bias in data. A global explanation is proposed, and a step-by-step framework on how to detect and test bias is introduced. Since removing unwanted bias is often a complicated and tremendous task, it is automatically inserted, instead. Then, the bias is evaluated with the proposed counterfactual approach. The obtained results...
-
Architecture and Basic Assumptions of RSMAD
PublikacjaThe study presents the architecture of Radio System for Monitoring and Acquisition of Data from Traffic Enforcement Cameras (in short RSMAD) which is used for transmission (realized using GSM, UMTS or TETRA networks, and through the Internet network), archiving and exploring image data of traffic offenses. The paper also presents selected basic assumptions of the RSMAD system, which are relevant to the implemented by the system...
-
Security Evaluation of IT Systems Underlying Critical Networked Infrastructures
PublikacjaCritical infrastructures have become highly dependent on information and communication technology (ICT). The drawback of this situation is that the consequences of disturbances of the underlying ICT networks may be serious as cascading effects can occur. This raises a high demand for security assurance, with a high importance assigned to security evaluations. In this paper we present an experiment-centric approach for the characterisation...
-
Qualitative Indicators Used to Select the Placement and Parameters of Energy Storage Installed in the Distribution Network
PublikacjaThe technology related to energy storage has developed in recent years. Continuous improvement of the solutions available on the market resulted in wider usability of energy storage. They are also increasingly used in a distribution network. This study contains a synthesised description of physical features of the energy storage used in distribution networks. Several criteria of algorithms used to determine the placement and...
-
Specyfikacja Systemu IP QoS opartego na architekturze DiffServ
PublikacjaArtykuł przedstawia ogólną specyfikację systemu IP QoS (ang. Internet Protocol Quality of Service), który to system jest obecnie implementowany w ramach projektu krajowego "Zarządzanie ruchemw sieciach IP". System ten jest zgodny z architekturą DiffServ (ang. Differentiated Services) i architekturą NGN (Next Generation Networks). W szczególności, artykuł pokrótce omawia architekturęsystemu, oferowane klasy usług w systemie oraz...
-
Multichannel Human Body Communication
PublikacjaHuman Body Communication is an attractive alternative for traditional wireless communication (Bluetooth, ZigBee) in case of Body Sensor Networks. Low power, high data rates and data security makes it ideal solution for medical applications. In this paper, signal attenuation for different frequencies, using FR4 electrodes, has been investigated. Performance of single and multichannel transmission with frequency modulation of analog...
-
Big Data from Sensor Network via Internet of Things to Edge Deep Learning for Smart City
PublikacjaData from a physical world is sampled by sensor networks, and then streams of Big Data are sent to cloud hosts to support decision making by deep learning software. In a smart city, some tasks may be assigned to smart devices of the Internet of Things for performing edge computing. Besides, a part of workload of calculations can be transferred to the cloud hosts. This paper proposes benchmarks for division tasks between an edge...
-
Modelowanie ryzyka inwestycyjnego przy użyciu OOBN
PublikacjaCelem artykułu jest przedstawienie sieci Bayesa zorientowanych obiektowo (ang. Object Oriented Bayesian Networks – OOBN). Umożliwiają one dekompozycję złożonego modelu na pojedyncze obiekty, które reprezentują nie tylko różne grupy zagadnień, ale także pozwalają na modelowanie zależności czasowychmiędzy obiektami.Wykorzystanie obiektowych sieci Bayesa zaprezentowano na przykładzie projektu rewitalizacji. Przedstawiono zarówno wady,...
-
GNSS INVENTORY OF HISTORIC NARROW-GAUGE RAILWAY LINE IN KOSZALIN UNDER EXTREMELY UNFAVORABLE MEASUREMENTS CONDITIONS FROM THE POINT OF VIEW OF SATELLITE SIGNALS AVAILABILITY
PublikacjaA team of academic researchers from the Gdańsk University of Technology, Gdynia Maritime University and the Polish Naval Academy have been working since 2009 on the methodology of using active GNSS geodetic networks for geodetic inventory of railways and on adapting this measurement technique for designing geometric layouts of railway and tram lines. Over the years, the team tested a variety of configurations of receivers and settings...
-
A Development of a Capacitive Voltage Divider for High Voltage Measurement as Part of a Combined Current and Voltage Sensor
PublikacjaThis article deals with the development of capacitive voltage divider for high voltage measurements and presents a method of analysis and optimization of its parameters. This divider is a part of a combined voltage and current sensor for measurements in high voltage power networks. The sensor allows continuous monitoring of the network distribution status and performs a quick diagnosis and location of possible network failures....
-
Zarządzanie zaufaniem w bezprzewodowych sieciach czujników - studium przypadku
PublikacjaW artykule przedstawiono studium przypadku dotyczące zastosowania bezprzewodowej sieci czujników do wspomagania pacjenta z nadwagą w jego środowisku domowym. Przyjęto, że sieć wykorzystuje metodę rozproszonego zarządzania zaufaniem i pokazano, że metoda ta umożliwia wykrycie i izolację czujników realizujących działania sprzeczne z polityką sieci. Ilościowe oszacowanie czasu niezbędnego do wykrycia takich...
-
Indykatory mobilne GIS w analizie ruchu miejskiego
PublikacjaW ramach artykułu autorzy przedstawią możliwości monitorowania sytuacji komunikacyjnej miasta z wykorzystaniem autorskiego i dedykowanego systemu monitorowania ruchu w mieście, opartego o pakiet oprogramowania stacjonarnego i mobilnego przeznaczonego dla korporacji taxi. Celem publikacji jest przedstawienie założeń optymalnych i minimalnych do realizacji monitoringu ruchu w mieście. Przywołane zostaną autorskie próby wdrożeń rozwiązań...
-
5G Millimeter Wave Network Optimization: Dual Connectivity and Power Allocation Strategy
PublikacjaThe fifth generation (5G) of mobile networks utilizing millimeter Wave (mmWave) bands can be considered the leading player in meeting the continuously increasing hunger of the end user demands in the near future. However, 5G networks are characterized by high power consumption, which poses a significant challenge to the efficient management of base stations (BSs) and user association. Implementing new power consumption and user...
-
Analysis of Denoising Autoencoder Properties Through Misspelling Correction Task
PublikacjaThe paper analyzes some properties of denoising autoencoders using the problem of misspellings correction as an exemplary task. We evaluate the capacity of the network in its classical feed-forward form. We also propose a modification to the output layer of the net, which we called multi-softmax. Experiments show that the model trained with this output layer outperforms traditional network both in learning time and accuracy. We...
-
Application of ANN and PCA to two-phase flow evaluation using radioisotopes
PublikacjaIn the two-phase flow measurements a method involving the absorption of gamma radiation can be applied among others. Analysis of the signals from the scintillation probes can be used to determine the number of flow parameters and to recognize flow structure. Three types of flow regimes as plug, bubble, and transitional plug – bubble flows were considered in this work. The article shows how features of the signals in the time and...
-
Intelligent Autonomous Robot Supporting Small Pets in Domestic Environment
PublikacjaIn this contribution, we present preliminary results of the student project aimed at the development of an intelligent autonomous robot supporting small pets in a domestic environment. The main task of this robot is to protect a freely moving small pets against accidental stepping on them by home residents. For this purpose, we have developed the mobile robot which follows a pet and makes an alarm signal when a human is approaching....
-
Architektury klasyfikatorów obrazów
PublikacjaKlasyfikacja obrazów jest zagadnieniem z dziedziny widzenia komputerowego. Polega na całościowej analizie obrazu i przypisaniu go do jednej lub wielu kategorii (klas). Współczesne rozwiązania tego problemu są w znacznej części realizowane z wykorzystaniem konwolucyjnych głębokich sieci neuronowych (convolutional neural network, CNN). W tym rozdziale opisano przełomowe architektury CNN oraz ewolucję state-of-the-art w klasyfikacji...
-
TensorHive: Management of Exclusive GPU Access for Distributed Machine Learning Workloads
PublikacjaTensorHive is a tool for organizing work of research and engineering teams that use servers with GPUs for machine learning workloads. In a comprehensive web interface, it supports reservation of GPUs for exclusive usage, hardware monitoring, as well as configuring, executing and queuing distributed computational jobs. Focusing on easy installation and simple configuration, the tool automatically detects the available computing...
-
Measurement Stand and Methodology for Research of the Off-Body and Body-to-Body Radio Channels in WBANs with Different Diversity Schemes
PublikacjaThe concept of an experimental test bed for system loss and channel impulse response measurements for off-body and body-to-body radio channels in wireless body area networks (WBANs) is fully described. The possible measurement scenarios that may occur in investigation of off-body and body-to-body channels are classified and described in detail. Additionally, an evaluation is provided of the standard and expanded uncertainties of...
-
Evaluation of a sat-type fairness mechanism implemented in a dual-ring network
PublikacjaThe fairness problem was presented. Popular fairness concepts and measures were shown. The RPR fairness mechanism and the SAT mechanism were described. A modification of the SAT algorithm, adapted to the possibilities of Ethernet cards used for implementation of a dual-ring RPR-based network, was proposed. Performance of the proposed modification was measured. Jain's and Chen's fairness indexes were calculated. Effectiveness comparison...
-
Is it all about networking? Building a sustainable value of a small enterprise in Polish context
PublikacjaIn this paper we aim to propose and outline key ingredients to a small enterprise success, emerging from the social capital of small business owner-managers and their business networks. We employ resource based view of an organization as well as an embeddedness perspective along with new approach transaction costs to outline the pillars of an advantage of a small business entity. The analysis of survey data leads us to conclusion,...
-
Interference aware Bluetooth scatternet (Re)configuration algorithm IBLUEREA
PublikacjaThe paper presents a new algorithm IBLUEREA, which enables reconfiguration of Bluetooth (BT) scatternet to reduce mutual interferences between BT and Wi-Fi (IEEE 802.11b) networks operating on the same area. IBLUEREA makes use of proposed procedure for modelling ISM environment around a given BT scatternet. The mechanism is based on estimation of the probabilities of successful (unsuccessful) frame transmissions. This determination...
-
Impact of radio wave polarisation on off-body communications in indoor environments
PublikacjaThis paper describes the measurements and the analysis of the impact of radio wave polarisation on off-body communications in Body Area Networks in indoor environments. Measurements on polarisation impact are briefly described. Five investigated scenarios with different body postures and different antenna placements are characterised. The difference between the vertical and horizontal components of the received radio signal are...
-
Asynchronous time difference of arrival (ATDOA) method
PublikacjaA new method for a location service in the asynchronous wireless sensor networks is outlined. This method, which is called asynchronous time difference of arrival (ATDOA), enables calculation of the position of a mobile node without knowledge of relative time differences (RTDs) between measuring sensors. The ATDOA method is based on the measurement of time difference of arrival between the node and the same sensor at the discrete...
-
Assessment and Optimization of Air Monitoring Network for Smart Cities with Multicriteria Decision Analysis
PublikacjaEnvironmental monitoring networks need to be designed in efficient way, to minimize costs and maximize the information granted by their operation. Gathering data from monitoring stations is also the essence of Smart Cities. Agency of Regional Air Quality Monitoring in the Gdańsk Metropolitan Area (pol. ARMAAG) was assessed in terms of its efficiency to obtain variety of information. The results on one-month average concentrations...
-
Modelling of MV and HV Cable Lines
PublikacjaOverhead and cable lines are fundamental elements of power systems. Participation of cable lines is smaller and their percentage decreases as voltage is increased. HV cable lines are often built with the use of cables which are composed of coaxial metallic sheaths. Such cables are also often used in MV networks. The sheath may operate in different confgurations. In the case of Polish MV network the sheaths are earthed at both ends....
-
Systematic Literature Review on Click Through Rate Prediction
PublikacjaThe ability to anticipate whether a user will click on an item is one of the most crucial aspects of operating an e-commerce business, and clickthrough rate prediction is an attempt to provide an answer to this question. Beginning with the simplest multilayer perceptrons and progressing to the most sophisticated attention networks, researchers employ a variety of methods to solve this issue. In this paper, we present the findings...
-
Superconductivity in Bismuth Pyrochlore Lattice Compounds RbBi2 and CsBi2: The Role of Relativistic Effects
PublikacjaSuperconducting properties of two bismuthide intermetallic compounds, RbBi2 and CsBi2, were studied by means of experimental measurements and ab initio calculations. We show that in both compounds, the superconductivity emerges from the pyrochlore Bi lattice and its formation is heavily influenced by relativistic effects. Based on our analysis of the effect of spin–orbit coupling on the electron–phonon coupling, we suggest a possible...
-
Collision-Free Network Exploration
PublikacjaA set of mobile agents is placed at different nodes of a n-node network. The agents synchronously move along the network edges in a collision-free way, i.e., in no round may two agents occupy the same node. In each round, an agent may choose to stay at its currently occupied node or to move to one of its neighbors. An agent has no knowledge of the number and initial positions of other agents. We are looking for the shortest possible...
-
Dynamic coloring of graphs
PublikacjaDynamics is an inherent feature of many real life systems so it is natural to define and investigate the properties of models that reflect their dynamic nature. Dynamic graph colorings can be naturally applied in system modeling, e.g. for scheduling threads of parallel programs, time sharing in wireless networks, session scheduling in high-speed LAN's, channel assignment in WDM optical networks as well as traffic scheduling. In...
-
High Isolation Metamaterial-based Dual-band MIMO Antenna for 5G Millimeter-wave Applications
PublikacjaThis article presents a high-isolation metamaterial-based dual-band multiple-input multiple-output (MIMO) antenna for 5G millimeter-wave communication networks. The proposed antenna is a pentagon-shaped monopole that provides a dual-band response with a wide operating bandwidth at 5G 28/28 bands. The antenna is printed on 0.508-mm-thick Rogers RT5880 substrate of relative permittivity ɛr =2.2. It exhibits a small physical size...
-
Simulator for Performance Evaluation of ASON/GMPLS Network
PublikacjaThe hierarchical control plane network architecture of Automatically Switched Optical Network with utilization of Generalized Multi-Protocol Label Switching protocols is compliant to next generation networks requirements and can supply connections with required quality of service, even with incomplete domain information. Considering connection control, connection management and network management, the controllers of this architecture...
-
MACHINE LEARNING APPLICATIONS IN RECOGNIZING HUMAN EMOTIONS BASED ON THE EEG
PublikacjaThis study examined the machine learning-based approach allowing the recognition of human emotional states with the use of EEG signals. After a short introduction to the fundamentals of electroencephalography and neural oscillations, the two-dimensional valence-arousal Russell’s model of emotion was described. Next, we present the assumptions of the performed EEG experiment. Detail aspects of the data sanitization including preprocessing,...
-
Hydrauliczna wiarygodność wyników pomiarów terenowych stosowanych do identyfikacji oporności hydraulicznej przewymiarowanych sieci wodociągowych
PublikacjaPublikacja zawiera zalecenia metodyczne dotyczące identyfikacji oporności hydraulicznej w przewymiarowanych sieciach wodociągowych na tle spotykanych nieprawidłowości. Krytycznie oceniono wyniki pomiarów terenowych, które zastosowano do tarowania komputerowych modeli przepływów (KMP) pomimo, że nie spełniały kryterium hydraulicznej wiarygodności. Ponadto zaproponowano spadek hydrauliczny jako obiektywny wskaźnik wiarygodności pomiarów,...
-
Dissecting gamma frequency activities during human memory processing
PublikacjaGamma frequency activity (30-150 Hz) is induced in cognitive tasks and is thought to reflect underlying neural processes. Gamma frequency activity can be recorded directly from the human brain using intracranial electrodes implanted in patients undergoing treatment for drug-resistant epilepsy. Previous studies have independently explored narrowband oscillations in the local field potential and broadband power increases. It is not...
-
Radio Simulcasting at a Glance: a New Look at Broadcasting and Streaming Services
PublikacjaRadio is by far one of the most popular and accessible medium. With its availability it attracts listeners all around the world. There are numerous ways of delivering content to consumers. The present situation is characterized by the convergence of acoustics, computer science and telecommunications. This paper reviews the current status of radio broadcasting and streaming services. It describes a subjective study concerning different...
-
A Model for Risk Assessment and Management of Construction Projects in Urban Conditions
PublikacjaThe authors are seeking new methods for improving the efficiency of the investments associated with the maintenance and operation of existing civil engineering structures. It is demonstrated how the knowledge about the elements of construction and operation phases and their relationships, combined with monitoring data can be used for more effective management of the risks associated with civil engineering projects. The methodology...
-
Consumer social network brand identification and personal branding. How do social network users choose among brand sites?
PublikacjaBrands’ social networking sites (fan pages) are increasingly attracting the attention of scientists and managers intrigued by their potential application for brand value creation. The aim of this research is to understand better how users choose among social networking sites as an act of brand identification. The study presents a new model whose structure of identification drivers for social networking brand sites varies for customer...
-
An Approach to Mean Path Loss Model Estimation for Off-Body Channels
PublikacjaThis paper presents an approach to estimation of the mean path loss model parameters in off-body Body Area Networks channels. In this approach, the path loss exponent is constrained to a value obtained for the line-of-sight (LoS) propagation in the co-polarised channel, considering a generalised static scenario. The comparison of the goodness of fit between the proposed approach and other approaches, for a set of measurements obtained...
-
Zastosowanie koncepcji SDN w warstwie transportowej sieci IMS/NGN
PublikacjaKoncepcja sieci Next Generation Network, wykorzystująca w warstwie usług architekturę IP Multimedia Subsystem, zakłada centralizację funkcji sterowania zasobami sieciowymi w warstwie transportowej. Analogiczne założenie jest podstawą koncepcji Software Defined Networks. Na podstawie tej analogii, zaproponowano integrację obu koncepcji, przedstawiono architekturę zintegrowanej sieci, scenariusze sterowania zasobami oraz przygotowano...
-
More Just Measure of Fairness for Sharing Network Resources
PublikacjaA more just measure of resource distribution in computer networks is proposed. Classic functions evaluate fairness only “on average”. The proposed new fairness score function ensures that no node is left without resources while on average everything looks good. It is compared with well-known and widely adopted function proposed by Jain, Chiu and Hawe and another one recently proposed fairness function by Chen and Zhang. The function...
-
Modelowanie przepływu ustalonego niejednostajnego w sieciach kanałów otwartych z uwzględnieniem obiektów hydrotechnicznych
PublikacjaW pracy sformułowano zagadnienie brzegowe dla równania energii opisującego przepływ ustalony niejednostajny i przedstawiono sposób jego rozwiązania przy pomocy metody różnicowej. Zaproponowana metoda obliczeń nadaje się do analizy przepływu w dendrycznych i pierścieniowych sieciach kanałów otwartych. Ponadto na przykładzie przelewu prostokątnego zaproponowano metodę uwzględnienia w obliczeniach zabudowy hydrotechnicznej. Słowa...
-
JAKOŚĆ USŁUG W ARCHITEKTURZE SIECI ASON/GMPLS A MECHANIZMY REZERWACJI ZASOBÓW
PublikacjaW artykule przedstawiono mechanizmy rezerwacji zasobów w architekturze sieci ASON/GMPLS, która spełnia wymagania nowoczesnych sieci optycznych, a jednocześnie umożliwia sterowanie siecią z gwarancją jakości usług. W artykule porównano dwa mechanizmy rezerwacji zasobów z gwarancją jakości i podejściem typu POOL. Efektywność prezentowanych mechanizmów zweryfikowano metodą symulacji komputerowej w środowisku OMNeT++.
-
LSA Is not Dead: Improving Results of Domain-Specific Information Retrieval System Using Stack Overflow Questions Tags
PublikacjaThe paper presents the approach to using tags from Stack Overflow questions as a data source in the process of building domain-specific unsupervised term embeddings. Using a huge dataset of Stack Overflow posts, our solution employs the LSA algorithm to learn latent representations of information technology terms. The paper also presents the Teamy.ai system, currently developed by Scalac company, which serves as a platform that...
-
Instance segmentation of stack composed of unknown objects
PublikacjaThe article reviews neural network architectures designed for the segmentation task. It focuses mainly on instance segmentation of stacked objects. The main assumption is that segmentation is based on a color image with an additional depth layer. The paper also introduces the Stacked Bricks Dataset based on three cameras: RealSense L515, ZED2, and a synthetic one. Selected architectures: DeepLab, Mask RCNN, DEtection TRansformer,...
-
MACHINE LEARNING SYSTEM FOR AUTOMATED BLOOD SMEAR ANALYSIS
PublikacjaIn this paper the authors propose a decision support system for automatic blood smear analysis based on microscopic images. The images are pre-processed in order to remove irrelevant elements and to enhance the most important ones - the healthy blood cells (erythrocytes) and the pathologic (echinocytes). The separated blood cells are analyzed in terms of their most important features by the eigenfaces method. The features are the...
-
Text Categorization Improvement via User Interaction
PublikacjaIn this paper, we propose an approach to improvement of text categorization using interaction with the user. The quality of categorization has been defined in terms of a distribution of objects related to the classes and projected on the self-organizing maps. For the experiments, we use the articles and categories from the subset of Simple Wikipedia. We test three different approaches for text representation. As a baseline we use...
-
Method for Clustering of Brain Activity Data Derived from EEG Signals
PublikacjaA method for assessing separability of EEG signals associated with three classes of brain activity is proposed. The EEG signals are acquired from 23 subjects, gathered from a headset consisting of 14 electrodes. Data are processed by applying Discrete Wavelet Transform (DWT) for the signal analysis and an autoencoder neural network for the brain activity separation. Processing involves 74 wavelets from 3 DWT families: Coiflets,...
-
Deep learning for recommending subscription-limited documents
PublikacjaDocuments recommendation for a commercial, subscription-based online platform is important due to the difficulty in navigation through a large volume and diversity of content available to clients. However, this is also a challenging task due to the number of new documents added every day and decreasing relevance of older contents. To solve this problem, we propose deep neural network architecture that combines autoencoder with...
-
Towards Cancer Patients Classification Using Liquid Biopsy
PublikacjaLiquid biopsy is a useful, minimally invasive diagnostic and monitoring tool for cancer disease. Yet, developing accurate methods, given the potentially large number of input features, and usually small datasets size remains very challenging. Recently, a novel feature parameterization based on the RNA-sequenced platelet data which uses the biological knowledge from the Kyoto Encyclopedia of Genes and Genomes, combined with a classifier...