Filtry
wszystkich: 33415
-
Katalog
- Publikacje 11273 wyników po odfiltrowaniu
- Czasopisma 326 wyników po odfiltrowaniu
- Konferencje 77 wyników po odfiltrowaniu
- Osoby 232 wyników po odfiltrowaniu
- Projekty 8 wyników po odfiltrowaniu
- Kursy Online 487 wyników po odfiltrowaniu
- Wydarzenia 7 wyników po odfiltrowaniu
- Dane Badawcze 21005 wyników po odfiltrowaniu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: training , adaptation models , uncertainty , image color analysis , semantics , estimation , predictive models
-
Image-based Analysis of Emotional Facial Expressions in Full Face Transplants
Publikacja -
Image based analysis of emotional expression development in facial transplant patient
Publikacja -
Recognition of two-phase flow patterns with the use of dynamic image analysis
Publikacja -
Two-phase flow structure assessment based on dynamic image analysis
Publikacja -
Decisions Analysis 2023/2024
Kursy OnlineThis is content to the subject: "Decisions Analysis" to be used as a template for futher courses.
-
Qualitative data analysis methods
Kursy OnlineThis is the continuation of Qualitatative Data Analysis Methods course provided online
-
Novel method of estimation of inertial and dissipative parameters of a railway pantograph model
PublikacjaAn increase in electric railway vehicles service velocity requires that correct interaction between the pantograph and the catenary is ensured. This implies the need for developing mathematical models of pantographs and catenaries and determining their parameters. The article presents a method to determine parameters of mechanical joints of a railway pantograph based on analysis of pantograph subassemblies in swinging motion. The...
-
Mathematical Models and Computer Simulations
Czasopisma -
Time Delay Estimation in Two-Phase Flow Investigation Using the γ-Ray Attenuation Technique.
PublikacjaTime delay estimation is an important research question having many applications in a range of technologies. Measurement of a two-phase flow in a pipeline or an open channel using radioisotopes is an example of such application. For instance, the determination of velocity of dispersed phase in that case is based on estimation of the time delay between two stochastic signals provided by scintillation probes. The proper analysis...
-
Image Classification Based on Video Segments
PublikacjaIn the dissertation a new method for improving the quality of classifications of images in video streams has been proposed and analyzed. In multiple fields concerning such a classification, the proposed algorithms focus on the analysis of single frames. This class of algorithms has been named OFA (One Frame Analyzed).In the dissertation, small segments of the video are considered and each image is analyzed in the context of its...
-
Improved Design Closure of Compact Microwave Circuits by Means of Performance Requirement Adaptation
PublikacjaNumerical optimization procedures have been widely used in the design of microwave components and systems. Most often, optimization algorithms are applied at the later stages of the design process to tune the geometry and/or material parameter values. To ensure sufficient accuracy, parameter adjustment is realized at the level of full-wave electromagnetic (EM) analysis, which creates perhaps the most important bottleneck due to...
-
The effect of sunscreen 4‐methylbenzylidene camphor in different and reproductive models, its bioaccumulation and molecular effects on ligand‐receptor interaction, and protein expression
Publikacja4-Methylbenzylidene camphor (4-MBC) is a photo-absorbing UV filter prevalently used in cosmetics, which can be absorbed into circulation and cause systemic effects. 4-MBC is continued to be released in the environment despite the growing knowledge about its bioaccumulation and endocrine disrupting effects. Previous reviews have mentioned UV-filter together but this review considers 4-MBC alone, due to its prevalence and concerning...
-
Vehicle detector training with minimal supervision
PublikacjaRecently many efficient object detectors based on convolutional neural networks (CNN) have been developed and they achieved impressive performance on many computer vision tasks. However, in order to achieve practical results, CNNs require really large annotated datasets for training. While many such databases are available, many of them can only be used for research purposes. Also some problems exist where such datasets are not...
-
Mispronunciation Detection in Non-Native (L2) English with Uncertainty Modeling
PublikacjaA common approach to the automatic detection of mispronunciation in language learning is to recognize the phonemes produced by a student and compare it to the expected pronunciation of a native speaker. This approach makes two simplifying assumptions: a) phonemes can be recognized from speech with high accuracy, b) there is a single correct way for a sentence to be pronounced. These assumptions do not always hold, which can result...
-
Results of modeling of pharmaceuticals mixtures toxicity with deviation ratio and best-fit functions models using Aliivibrio fischeri bacterium as model organism
Dane BadawczeThe research was concerned with verifying the impact of mixtures of nine pharmaceuticals against a selected organism, i.e., the bacterium Aliivibrio fischeri. A. fisheri is used as a model organism in the monitoring of acute toxicity in environmental and reference samples in Microtox® systems. Tested pharmaceuticals, namely: diclofenac (sodium salt),...
-
Machine-Learning-Based Global Optimization of Microwave Passives with Variable-Fidelity EM Models and Response Features
PublikacjaMaximizing microwave passive component performance demands precise parameter tuning, particularly as modern circuits grow increasingly intricate. Yet, achieving this often requires a comprehensive approach due to their complex geometries and miniaturized structures. However, the computational burden of optimizing these components via full-wave electromagnetic (EM) simulations is substantial. EM analysis remains crucial for circuit...
-
Improving css-KNN Classification Performance by Shifts in Training Data
PublikacjaThis paper presents a new approach to improve the performance of a css-k-NN classifier for categorization of text documents. The css-k-NN classifier (i.e., a threshold-based variation of a standard k-NN classifier we proposed in [1]) is a lazy-learning instance-based classifier. It does not have parameters associated with features and/or classes of objects, that would be optimized during off-line learning. In this paper we propose...
-
Extreme weather layer method for implementation of nature-based solutions for climate adaptation: Case study Słupsk
PublikacjaOne of the most severe climate risks that is expected to affect all regions is related to stormwater. Climate models, constructed based on long-term trends, show that extreme weather events such as storms, cloudbursts and a large rise in sea level will be significant in the coming decades. Moreover, even the frequency and intensity of “normal” rainfall events, such as microbursts, are expected to be remarkably higher than today...
-
Spatiotemporal Assessment of Satellite Image Time Series for Land Cover Classification Using Deep Learning Techniques: A Case Study of Reunion Island, France
PublikacjaCurrent Earth observation systems generate massive amounts of satellite image time series to keep track of geographical areas over time to monitor and identify environmental and climate change. Efficiently analyzing such data remains an unresolved issue in remote sensing. In classifying land cover, utilizing SITS rather than one image might benefit differentiating across classes because of their varied temporal patterns. The aim...
-
The conception of uncertainty analysis of reliability assessment of the MC type diesel engine lubricating oil system
PublikacjaOmówiono elementy składające się na niepewność oszacowania niezawodności instalacji oleju smarowego dla silników typu MC. Przedstawiono, posługując się przykładem obliczeniowym, koncepcję analizy niepewności oceny rozpatrywanej instalacji. Ponadto zaproponowano sposób interpretacji otrzymanego wyniku, obarczonego dużą niepewnością, przy użyciu liczb rozmytych.
-
The issue of uncertainty of visual measurement techniques for long distance measurements based on the example of applying electric traction elements in diagnostics and monitoring
PublikacjaRail transport is the most economical and energy-effective in the field of land transport, in particular electrified. In order to ensure efficient and reliable operation of electrified rail transport, the issues of monitoring and diagnostics of the traction infrastructure and vehicles are extremely important. The most critical point in the transmission of electric energy to the vehicle is the sliding contact of the current collector...
-
Volatile Compound Emissions from Stereolithography Three-Dimensional Printed Cured Resin Models for Biomedical Applications
PublikacjaStereolithography three-dimensional printing is used increasingly in biomedical applications to create components for use in healthcare and therapy. The exposure of patients to volatile organic compounds (VOCs) emitted from cured resins represents an element of concern in such applications. Here, we investigate the biocompatibility in relation to inhalation exposure of volatile emissions of three different cured commercial resins...
-
Wear estimation of current collector contact strips by analysis of a 3D scanning results
PublikacjaThe technical condition of current collector contact strips is very important when operational reliability of railway transportation is considered. The authors proposed a novel measurement system based on a 3D camera to register the shape and dimensions of the current collector contact strips surface. The system was installed above the railway track for tests in target ambient. During the trial operation a few dozen of contact...
-
The Simulation of Activated Sludge System for Optimization of Predictive Aeration at Large WWTP
PublikacjaEffective use of biodegradable substrates as an internal carbon sources (ICS) for denitrification and EBPR and predicting performance of aeration systems during nitrification in activated sludge bioreactors, may be useful in realization the sustainable development by potentially saving energy consumption at WWTPs. A large number of WWTPs use activated sludge systems with an integrated removal of carbon, nitrogen and phosphorus...
-
Overhead wires detection by FPGA real-time image processing
PublikacjaThe paper presents design and hardware implementation of real-time image filtering for overhead wires detection divided on image processing and results presentation blocks. The image processing block was separated from the whole implementation, and its delay and hardware complexity was analysed. Also the maximum frequency of image processing of the proposed implementation was estimated.
-
Benchmarking Deep Neural Network Training Using Multi- and Many-Core Processors
PublikacjaIn the paper we provide thorough benchmarking of deep neural network (DNN) training on modern multi- and many-core Intel processors in order to assess performance differences for various deep learning as well as parallel computing parameters. We present performance of DNN training for Alexnet, Googlenet, Googlenet_v2 as well as Resnet_50 for various engines used by the deep learning framework, for various batch sizes. Furthermore,...
-
Vocational training
Czasopisma -
JOURNAL OF RISK AND UNCERTAINTY
Czasopisma -
Дуальные модели Лотмана и Милоша – в анализах истории России и в автобиографии [Lotman’s and Miłosz’s Dual Models – in Analysis of History of Russia and in Autobiography]
Publikacja -
A system for singing training
PublikacjaThe system proposed is aimed at the vocal students and persons who want to improve emission of their voices. The goal is not to substituite a singing teacher but to provide a tool for automatic teaching of voice emission basics. In this way singers can develop their vocal skills and improve them. By a visual feedback a student can control and modify vocal tract maximas (resonances) of a chosen vowel to match the resonances of the...
-
Identification of Emotions Based on Human Facial Expressions Using a Color-Space Approach
PublikacjaHCI technology improves human-computer interaction. Such communication can be carried out with the use of emotions that are visible on the human face since birth. In this paper the Emotion system for detecting and recognizing facial expressions, developed in the MSc work, is presented. The system recognizes emotion from webcam video in real time. It is based on color segmentation and morphological operations. The system uses a...
-
Normalization of face illumination using basic knowledge and information extracted from a single image
PublikacjaThis paper presents a method for face image normalization that can be applied to the extraction of illumination invariant facial features or used to remove bad lighting effects and produce high-quality, photorealistic results. Most of the existing approaches concentrate on separating the constant albedo from the variable light intensity; that concept, however, is based on the Lambertian model, which fails in the presence of specularities...
-
RSS-Based DoA Estimation for ESPAR Antennas Using Support Vector Machine
PublikacjaIn this letter, it is shown how direction-of-arrival (DoA) estimation for electronically steerable parasitic array radiator (ESPAR) antennas, which are designed to be integrated within wireless sensor network nodes, can be improved by applying support vector classification approach to received signal strength (RSS) values recorded at an antenna's output port. The proposed method relies on ESPAR antenna's radiation patterns measured...
-
Integrated Control in High-Speed Networks Using Constrained Model Predictive Control
PublikacjaThis paper studies congestion control in high-speed communication networks using Model Predictive Control (MPC). Network traffic is assumed to consist of best-effort and priority traffic sources. An integrated controller consisting of two control parts is designed. The controller calculates the capacity for priority sources and the input rate of best-effort sources. MPC is desirable as it can take into account the constraints on...
-
Wide-field magnetometry using nitrogen-vacancy color centers with randomly oriented micro-diamonds
PublikacjaMagnetometry with nitrogen-vacancy (NV) color centers in diamond has gained significant interest among researchers in recent years. Absolute knowledge of the three-dimensional orientation of the magnetic field is necessary for many applications. Conventional magnetometry measurements are usually performed with NV ensembles in a bulk diamond with a thin NV layer or a scanning probe in the form of a diamond tip, which requires a...
-
Selected Technical Issues of Deep Neural Networks for Image Classification Purposes
PublikacjaIn recent years, deep learning and especially Deep Neural Networks (DNN) have obtained amazing performance on a variety of problems, in particular in classification or pattern recognition. Among many kinds of DNNs, the Convolutional Neural Networks (CNN) are most commonly used. However, due to their complexity, there are many problems related but not limited to optimizing network parameters, avoiding overfitting and ensuring good...
-
Machine Learning and Deep Learning Methods for Fast and Accurate Assessment of Transthoracic Echocardiogram Image Quality
PublikacjaHigh-quality echocardiogram images are the cornerstone of accurate and reliable measurements of the heart. Therefore, this study aimed to develop, validate and compare machine learning and deep learning algorithms for accurate and automated assessment of transthoracic echocardiogram image quality. In total, 4090 single-frame two-dimensional transthoracic echocardiogram...
-
Identification of nonstationary multivariate autoregressive processes– Comparison of competitive and collaborative strategies for joint selection of estimation bandwidth and model order
PublikacjaThe problem of identification of multivariate autoregressive processes (systems or signals) with unknown and possibly time-varying model order and time-varying rate of parameter variation is considered and solved using parallel estimation approach. Under this approach, several local estimation algorithms, with different order and bandwidth settings, are run simultaneously and compared based on their predictive performance. First,...
-
Reducing the Uncertainty of the Moving Object Location Measurement with the Method of Quasi-Multiple Measurement in GNSS Technology in Symmetrical Arrangement
PublikacjaThe article presents a solution to the problem of limited accuracy of dynamic measurements performed with GNSS receivers. The proposed measurement method is a response to the needs related to the assessment of the measurement uncertainty of the position of the track axis of the rail transport line. However, the problem of reducing the measurement uncertainty is universal for many different situations where high accuracy of positioning...
-
CMOS implementation of an analogue median filter for image processing in real time
PublikacjaAn analogue median filter, realised in a 0.35 μm CMOS technology, is presented in this paper. The key advantages of the filter are: high speed of image processing (50 frames per second), low-power operation (below 1.25 mW under 3.3 V supply) and relatively high accuracy of signal processing. The presented filter is a part of an integrated circuit for image processing (a vision chip), containing: a photo-sensor matrix, a set of...
-
Comparison of Language Models Trained on Written Texts and Speech Transcripts in the Context of Automatic Speech Recognition
Publikacja -
Effects of different hydraulic models on predicting longitudinal profiles of reactive pollutants in activated sludge reactors
PublikacjaW pracy przedstawiono wpływ dyspersji na prognozowanie stężeń azotu amonowego w komorach osadu czynnego w oczyszczalni ścieków Gdańsk-Wschód. W tym celu wykorzystano jednowymiarowe równanie adwekcji-dyspersji z członem źródłowym (szybkością nitryfikacji). Współczynnik dyspersji został wyznaczony na podstawie pomiarów znacznika fluoroscencyjnego. Model został zweryfikowany w oparciu o pomiary stężeń azotu w 6 sekcjach komory tlenowej...
-
Construction and Validation of Simulation Models of Samples Made from 316L Steel by Applying Additive Technique
Publikacja -
Hydrophobic hydration and pairwise hydrophobic interaction of Lennard-Jones and Mie particles in different water models
Publikacja -
Serum trace elements in animal models and human depression: Part III. Magnesium. Relationship with copper
Publikacja -
Fast Multi-Objective Antenna Optimization Using Sequential Patching and Variable-Fidelity EM Models
PublikacjaIn this work, a technique for fast multi-objective design optimization of antenna structures is presented. In our approach, the initial approximation of the Pareto set representing the best possible trade-offs between conflicting design objectives is obtained by means of sequential patching of the design space. The latter is a stencil-based search that aims at creating a path that connects the extreme Pareto-optimal designs (obtained...
-
Conception of selecting reliability models for taking operating decisionsrelated to sea-going ship´s systems
PublikacjaPrzedstawiono możliwości podejmowania decyzji dotyczących sytuacji, gdy decydent dysponuje informacją aprioryczną o stanie technicznym urządzeń, na przykład uzyskaną z badań niezawodności urządzeń niezbędnych do wykonania zadania, wyrażoną w formie prawdopodobieństwa. Do opracowania modelu umożliwiającego podejmowanie takich decyzji eksploatacyjnych wykorzystano elementy bayesowskiej statystycznej teorii decyzji.
-
Aktywne modele kształtu i ich biometryczne zastosowania = Active shape models and their biometric applications
PublikacjaAktywne modele kształtu zostały zaproponowane w latach 90 XX wieku jako uniwersalna metoda lokalizowania i rozpoznawania obiektów. Koncepcje teoretyczne, na których metoda ta została oparta, wydają się obiecujące, jednak ich praktyczna wartość nie została jeszcze do końca zweryfikowana. Autorzy niniejszej pracy przeprowadzili testy aktywnych modeli kształtu za pomocą własnego systemu lokalizacji obiektów, szczególną uwagę zwracając...
-
Estimation and Prediction of Vertical Deformations of Random Surfaces, Applying the Total Least Squares Collocation Method
PublikacjaThis paper proposes a method for determining the vertical deformations treated as random fields. It is assumed that the monitored surfaces are subject not only to deterministic deformations, but also to random fluctuations. Furthermore, the existence of random noise coming from surface’s vibrations is also assumed. Such noise disturbs the deformation’s functional models. Surface monitoring with the use of the geodetic levelling...
-
Customization of UWB 3D-RTLS Based on the New Uncertainty Model of the AoA Ranging Technique
PublikacjaThe increased potential and effectiveness of Real-time Locating Systems (RTLSs) substantially influence their application spectrum. They are widely used, inter alia, in the industrial sector, healthcare, home care, and in logistic and security applications. The research aims to develop an analytical method to customize UWB-based RTLS, in order to improve their localization performance in terms of accuracy and precision. The analytical...