Filters
total: 7595
-
Catalog
- Publications 5084 available results
- Journals 665 available results
- Conferences 38 available results
- People 178 available results
- Inventions 4 available results
- Projects 46 available results
- Laboratories 1 available results
- Research Teams 2 available results
- e-Learning Courses 479 available results
- Events 76 available results
- Open Research Data 1022 available results
displaying 1000 best results Help
Search results for: E-LEARING
-
Flow Maps and Flow Patterns of R1233zd(E) in a Circular Minichannel at Low, Medium and High Values of Saturation Pressure
PublicationThere is a gap in knowledge regarding the flow pattern of low-boiling working fluids in the range of high saturation temperatures (above 120°C) and medium and high reduced pressures (0.5-0.9). Data are present in the literature for similar values of reduced pressures, but for lower values of saturation temperature. This is due to the existing refrigeration applications of these working fluids. At high values of reduced pressure,...
-
Analysis of 2D Feature Spaces for Deep Learning-based Speech Recognition
Publicationconvolutional neural network (CNN) which is a class of deep, feed-forward artificial neural network. We decided to analyze audio signal feature maps, namely spectrograms, linear and Mel-scale cepstrograms, and chromagrams. The choice was made upon the fact that CNN performs well in 2D data-oriented processing contexts. Feature maps were employed in the Lithuanian word recognition task. The spectral analysis led to the highest word...
-
Evaluation of expanded uncertainty of instantaneous power measurement in a bearing diagnostic system.
PublicationThe paper presents the issues concerning the estimation of the expanded uncertainty in the system for the diagnosis of rolling bearings, consisting of transducers: voltage and current voltage, which is used for diagnostic bearing motors method based on the measurement and analysis of the instantaneous power signal consumed by the induction motor. It presents the methodology for assessing the measurement uncertainty and presents...
-
Deep Learning Optimization for Edge Devices: Analysis of Training Quantization Parameters
PublicationThis paper focuses on convolution neural network quantization problem. The quantization has a distinct stage of data conversion from floating-point into integer-point numbers. In general, the process of quantization is associated with the reduction of the matrix dimension via limited precision of the numbers. However, the training and inference stages of deep learning neural network are limited by the space of the memory and a...
-
Predictions of cervical cancer identification by photonic method combined with machine learning
PublicationCervical cancer is one of the most commonly appearing cancers, which early diagnosis is of greatest importance. Unfortunately, many diagnoses are based on subjective opinions of doctors—to date, there is no general measurement method with a calibrated standard. The problem can be solved with the measurement system being a fusion of an optoelectronic sensor and machine learning algorithm to provide reliable assistance for doctors...
-
The use of GFRP tubes as load-bearing jackets in concrete-composite columns
PublicationThe paper presents the fields of applications of polymer composites in building structures. The use of composite glass fibre tubes is discussed in more detail. The laboratory methods used to test the mechanical properties of these pipes are presented. An original research program is presented, including six concrete-filled glass fibre tubes. The cylinders and columns made in this way were tested for their axial load capacity. Conclusions...
-
Deep learning approach on surface EEG based Brain Computer Interface
PublicationIn this work we analysed the application of con-volutional neural networks in motor imagery classification for the Brain Computer Interface (BCI) purposes. To increase the accuracy of classification we proposed the solution that combines the Common Spatial Pattern (CSP) with convolutional network (ConvNet). The electroencephalography (EEG) is one of the modalities we try to use for controlling the prosthetic arm. Therefor in this...
-
Deep learning based thermal image segmentation for laboratory animals tracking
PublicationAutomated systems for behaviour classification of laboratory animals are an attractive alternative to manual scoring. However, the proper animals separation and tracking, especially when they are in close contact, is the bottleneck of the behaviour analysis systems. In this paper, we propose a method for the segmentation of thermal images of laboratory rats that are in close contact during social behaviour tests. For this, we are...
-
Autonomous pick-and-place system based on multiple 3Dsensors and deep learning
PublicationGrasping objects and manipulating them is the main way the robot interacts with its environment. However, for robots to operate in a dynamic environment, a system for determining the gripping position for objects in the scene is also required. For this purpose, neural networks segmenting the point cloud are usually applied. However, training such networks is very complex and their results are unsatisfactory. Therefore, we propose...
-
Real and Virtual Instruments in Machine Learning – Training and Comparison of Classification Results
PublicationThe continuous growth of the computing power of processors, as well as the fact that computational clusters can be created from combined machines, allows for increasing the complexity of algorithms that can be trained. The process, however, requires expanding the basis of the training sets. One of the main obstacles in music classification is the lack of high-quality, real-life recording database for every instrument with a variety...
-
Teams tools. Leading high-performance teams with different types of intelligence
PublicationThe subject of this paper is the analysis of necessary tools for global teams, image of the team leader, styles of leadership in global teams. The analysis is based on selected examples from high-performance teams with visible results. The purpose of the work is to answer for the following questions: What are the characteristics of the leading global teams? Which style of leadership use the global teams? Is a female leader different...
-
Bearing current path and pulse rate in PWM-inverter-fed induction
Publication -
Neon-Bearing Ammonium Metal Formates: Formation and Behaviour under Pressure
Publication -
Reward Learning Requires Activity of Matrix Metalloproteinase-9 in the Central Amygdala
Publication -
Efficient sampling of high-energy states by machine learning force fields
Publication -
Use of Neural Networks in Diagnostics of Rolling-Element Bearing of the Induction Motor
Publication -
Can the SARS-CoV-2 virus damage human hearing and balance?
Publication -
Sudden Hearing Loss Treated With Hyperbaric Oxygen (HBO) – Case Study
Publication -
Wear measurements of self lubricating bearing materials in small oscillatory movement
PublicationRosnące wymagania ekologiczne powodują wzrost tendencji wymiany klasycznych materiałów łożyskowych, wymagających dodatkowego czynnika smarnego, na materiały nie wymagające smarowania. Zamianie takiej może towarzyszyć obniżenie trwałości zmodernizowanego łożyska. Ten niekorzystny efekt nierzadko obserwuje się w węzłach łożyskowych kierownic turbin wodnych. Autorzy podjęli próbę wyjaśnienia zjawisk występujących w tego typu łożyskach....
-
Determination of the bearing capacity of pile foundations based on CPT test results
PublicationAnalityczne określanie pełnej krzywej obciążenie - osiadanie na podstawie parametrów geotechnicznych wciąż stanowi bardzo trudne zadanie naukowe i inżynierskie. W pracy przedstawiono metodę bezpośredniego wykorzystania oporów na stożku sondy statycznej do określania pełnej krzywej osiadania dla pali Vibro-Fundex. W sumie jako materiał weryfikacyjny wykorzystano 94 próbne obciążenia statyczne pali.
-
Learning from Imbalanced Data Using Over-Sampling and the Firefly Algorithm
Publication -
Improving of Cherry Fruit Quality and Bearing Regularity by Chemical Thinning with Fertilizer
Publication -
Deep learning approach for delamination identification using animation of Lamb waves
Publication -
Deep learning super-resolution for the reconstruction of full wavefield of Lamb waves
Publication -
OmicSelector: automatic feature selection and deep learning modeling for omic experiments
Publication -
Time-scale modification of speech signals for supporting hearing impaired schoolchildren
PublicationA study of time scale modification algorithmsapplied to hearing impaired schoolchildren supporting ispresented. Variety of algorithms are considered, namely:overlap and add, two variations of synchronized overlapand add, and the phase vocoder. Their effectiveness as wellas real-time processing capabilities are examined.
-
A Prototype of Educational Agent in Distance Learning Environment - Virtual Student Assistant
PublicationW zdalnym nauczaniu pojawia się wiele systemów wspierających, z których niezwykle ciekawym przykładem są agenty edukacyjne. Wśród wielu rodzajów agentów edukacyjnych wyróżnia się osobistych asystentów, których rolą jest organizacyjna pomoc osobie zdobywającej wiedzę. Artykuł jest poświęcony zaimplementowanemu na Wydziale ETI Politechniki Gdańskiej prototypowi agenta edukacyjnego o nazwie WAS (Wirtualny Asystent Studenta). Pokazana...
-
The Role of Dopaminergic Genes in Probabilistic Reinforcement Learning in Schizophrenia Spectrum Disorders
Publication -
Confirmation Bias in the Course of Instructed Reinforcement Learning in Schizophrenia-Spectrum Disorders
Publication -
Investigation of noise threats and their impact on hearing in selected schools - a pilot study.
PublicationNoise measurements conducted in selected schools in Gdansk area are presented in this paper. The main aim of this research was to determine noise threats at schools. Some objective measurements of the acoustic climate were performed employing a noise monitoring station engineered at the Multimedia System Department, Gdansk University of Technology. Simultaneously, subjective noise annoyance examinations were carried out among pupils...
-
Simulation of electric hearing - influence of simulation parameters on quality of output signal
PublicationW środowisku programistycznym Matlab stworzono symulację słuchu elektrycznego pacjenta implantowanego. W symulacji zastosowano algorytm przetwarzania wykorzystywany w komercyjnych systemach implantów ślimakowych - CIS (Continuous Interleaved Sampling). W pracy zbadano wpływ ilości kanałów, jak i innych parametrów sygnałów wyjściowych przy zastosowaniu sygału mowy jako sygnału wejściowego symulacji.
-
"FEM Parametric Study on Ultimate Bearing Capacity of CFST Arch Bridge
Publication -
IT support for OKNO broadband Internet-based distant learning system at WUT
Publication -
Modular machine learning system for training object detection algorithms on a supercomputer
PublicationW pracy zaprezentowano architekturę systemu służącego do tworzenia algorytmów wykorzystujących metodę AdaBoost i służących do wykrywania obiektów (np. twarzy) na obrazach. System został podzielony na wyspecjalizowane moduły w celu umożliwienia łatwej rozbudowy i efektywnego zrównoleglenia implementacji przeznaczonej dla superkomputera. Na przykład, system może być rozszerzony o nowe cechy i algorytmy ich ekstrakcji bez konieczności...
-
Beesybees-Agent-Based, Adaptive & Learning Workflow Execution Module for BeesyCluster
PublicationPrezentujemy projekt oraz implementację adaptacyjnego i uczącego się modułu przeznaczonego dowykonywania scenariuszy w środowisku BeesyCluster. BeesyCluster pozwala na modelowaniescenariuszy w formie acyklicznego grafu skierowanego, w którym wierzchołki oznaczają zadania,a krawędzie określają zależności między nimi. Przedstawiamy także kooperatywne wykonaniescenariusza przez grupę agentów zdolnych do zbierania, składowania i korzystania...
-
Cavitation wearing of the SUPERSTON alloy after laser treatment at cryogenic conditions
PublicationThe purpose of this paper is to demonstrate the method of laser remelting at cryogenic conditions of the SUPERSTON alloy and its influence on microstructure and cavitation wearing. The cavitation test was performed using the rotating disc facility in IPM PAN Gdansk. During the cavitation test, the mass loss of the material with different parameters of laser remelting was determined. Surface and cross-section microstructure of the...
-
Wear measurements of self-lubricating bearing materials in small oscillatory movement
Publication -
Stacking and rotation-based technique for machine learning classification with data reduction
Publication -
POPULATION-BASED MULTI-AGENT APPROACH TO SOLVING MACHINE LEARNING PROBLEMS
Publication -
Designing RBF Networks Using the Agent-Based Population Learning Algorithm
Publication -
Use of Neural Networks in Diagnostics of Rolling-Element Bearing of the Induction Motor
PublicationBearing defect is statistically the most frequent cause of an induction motor fault. The research described in the paper utilized the phenomenon of the current change in the induction motor with bearing defect. Methods based on the analysis of the supplying current are particularly useful when it is impossible to install diagnostic devices directly on the motor. The presented method of rolling-element bearing diagnostics used indirect...
-
Problems of analytical determination of journal bearing bush fatigue strength estimates
PublicationProblems connected with determination of stress distribution in sliding layer of thinwalled bearing bushes, investigated in bearing fatigue test rigs, have been presented. Using an example of plain bearings tested in the fatigue machine SMOK (built at the Gdask University of Technology) problems with obtaining a convergence of iterative procedure for determining the fatigue strength estimators of bearing alloy surface layer are...
-
Effect of Coating Material Properties on Tilting-pad Thrust Bearing Performance
PublicationPolymer lined tilting-pad bearings demonstrate many advantages over traditional bearing systems. Bearings with a polymer layer in comparison with a babbitted layer show, for example: lower value of friction coefficient (important during start/stops), higher fatigue strength of the coating, better distribution of the load on individual pads due to lower elasticity of the polymers, wider range of operational temperatures or the ability...
-
Noise measurements on low noise pavements - problems with inhomogeneity of wearing course
PublicationDuring the last several years, when performing numerous CPX noise measurements on low noise pavements,significant inhomogeneity of the wearing course was observed in numerous cases. Similar problems were almost not existing regarding to the dense pavements.In general three main reasons of inhomogeneity can be defined. The first one are imperfections in technology of production of a asphalt mix or/and errors made already during...
-
Measurement of the Development of a Learning IT Organization Supported by a Model of Knowledge Acquisition and Processing
PublicationThe paper presents a model of knowledge acquisition and processing for the development of learning organizations. The theory of a learning organization provides neither metrics nor tools to measure its development The authors' studies in this field are based on their experience gathered after projects realized in real IT organizations. The authors have described the construction of the model and the methods of its verification...
-
Bearing estimation using double frequency reassignment for a linear passive array
PublicationThe paper demonstrates the use of frequency reassignment for bearing estimation. For this task, signals derived from a linear equispaced passive array are used. The presented method makes use of Fourier transformation based spatial spectrum estimation. It is further developed through the application of two-dimensional reassignment, which leads to obtaining highly concentrated energy distributions in the joint frequency-angle domain...
-
Bearing capacity of working platform using distinct layout optimization method
PublicationBearing capacity of the working platforms from sandy soil resting on NC and OC clays was analyzed using LimitState GEO program. Different failure modes are considered using distinct layout optimization (DLO) method, which forms the upper bound solution of limit state analysis. Different mechanisms of failure were observed as a function of the platform thickness, angle of internal friction of the platform material and undrained...
-
Analysis of Failures of High Speed Shaft Bearing System in a Wind Turbine
PublicationDuring the operation of wind turbines with gearbox of traditional configuration, consisting of one planetary stage and two helical stages high failure rate of high speed shaft bearings is observed. Such a high failures frequency is not reflected in the results of standard calculations of bearing durability. Most probably it can be attributed to atypical failure mechanism. The authors studied problems in 1.5 MW wind turbines of...
-
ANALYSIS OF THE POSSIBILITIES OF HIGH SPEED SHAFT BEARING SYSTEM DURABILITY INCREASE
PublicationDuring the operation of wind turbines with a gearbox of traditional configuration, a high failure rate of high-speed shaft bearings is observed. Such a high failures frequency is not reflected in standard bearing durability calculation methods, which can be attributed to atypical failure mechanism. To avoid observed problems in the 1.5 MW wind turbine, the modification of the existing bearing system is proposed. Multiple options,...
-
Novel Analytic-Numerical Model of Free Convection: with Leading Edge Considered
PublicationA novel solution of the free convection boundary problem is represented in analytical form for velocity and temperature for an isothermal vertical plate, as an example. These fields are built as a Taylor Series in the x coordinate with coefficients as functions of the vertical coordinate (y). We restrict ourselves by cubic approximation for both functions. The basic Navier-Stokes and Fourier-Kirchhoff equations and boundary conditions...