Search
Filters
total: 10197
-
Catalog
displaying 1000 best results Help
Search results for: learning curve analysis
-
EFFICIENT LINE DETECTION METHOD BASED ON 2D CONVOLUTION FILTER
PublicationThe article proposes an efficient line detection method using a 2D convolution filter. The proposed method was compared with the Hough transform, the most popular method of straight lines detection. The developed method is suitable for local detection of straight lines with a slope from -45˚ to 45˚. Also, it can be used for curve detection which shape is approximated with the short straight sections. The new method is characterized...
-
Model-free and Model-based Reinforcement Learning, the Intersection of Learning and Planning
PublicationMy doctoral dissertation is intended as the compound of four publications considering: structure and randomness in planning and reinforcement learning, continuous control with ensemble deep deterministic policy gradients, toddler-inspired active representation learning, and large-scale deep reinforcement learning costs.
-
Financial Analysis exercises - New
e-Learning CoursesTo obtain theoretical and practical experience of financial and economic analysis. Methods of economic analysis: Elements of production and human resources analysis, tangible assets analysis, inventory analysis, which would enable to understand the business case, to measure them and find suitable decision. To obtain theoretical and practical experience of financial analysis.
-
Blended Learning Model for Computer Techniques for Students of Architecture
PublicationAbstract: The article summarizes two-year experience of implementing hybrid formula for teaching Computer Techniques at the Faculty of Architecture at the Gdansk University of Technology. Original educational e-materials, consisting of video clips, text and graphics instructions, as well as links to online resources are embedded in the university e-learning educational platform. The author discusses technical constraints associated...
-
Modeling variable curvature on the turnout diverging track length
PublicationThe paper presents three variants of variable curvature application on the entire length of the turnout diverging track. One linear and two nonlinear curvature cases: described the function of C1 and C0 class were considered. It turned out that both linear curve and the function of C1 class requires a significant (even twice) length of diverging track extending with respect to the base turnout. The curvature described by the function...
-
Deep Learning: A Case Study for Image Recognition Using Transfer Learning
PublicationDeep learning (DL) is a rising star of machine learning (ML) and artificial intelligence (AI) domains. Until 2006, many researchers had attempted to build deep neural networks (DNN), but most of them failed. In 2006, it was proven that deep neural networks are one of the most crucial inventions for the 21st century. Nowadays, DNN are being used as a key technology for many different domains: self-driven vehicles, smart cities,...
-
Electron-scattering cross sections for selected alkyne molecules: Measurements and calculations
PublicationWe report cross-section results from experimental and theoretical studies on electron collisions with 1-butyne (HC≡C–CH2CH3) and acetylene (HC≡CH) molecules and from computations for a propyne (HC≡C–CH3) molecule. Absolute grand -total electron-scattering cross sections (TCSs) were measured at impact energies ranging from about 0.5 to 300 eV using the linear electron-transmission method. The TCS energy curve for 1-butyne has a...
-
Shoreline Extraction Based on LiDAR Data Obtained Using an USV
PublicationThis article explores the use of Light Detection And Ranging (LiDAR) derived point clouds to extract the shoreline of the Lake Kłodno (Poland), based on their geometry properties. The data collection was performed using the Velodyne VLP‐16 laser scanner, which was mounted on the HydroDron Unmanned Surface Vehicle (USV). A modified version of the shoreline extraction method proposed by Xu et al. was employed, comprising of the following...
-
ENGINEERING FAILURE ANALYSIS
Journals -
15th Conference on Calorimetry and Thermal Analysis
EventsWe've updated the registration deadline because we know how easy it is you can lose track of time! Check your calendar and register for CCTA15. This is the last chance - deadline: July 15, 2024 (details). We kindly inform you that posters should be prepared in size B1 (707 x 1000 mm). Soon, we will make available a template on the CCTA15 website...
-
Wear of electroplated diamond tools in lap-grinding of Al2O3 ceramic materials
PublicationCurrent development of modern products, together with ever-increasing demands for their operation and usage, necessitate the search for new processing methods. Abrasive machining is widely used in many industrial areas, especially for processing difficult-to-machine materials such as advanced ceramics. Grinding with lapping kinematics, also called lap-grinding, is still one of the innovative methods of abrasive processing being...
-
Exact resultant equilibrium conditions in the non-linear theory of branching and self-intersecting shells
PublicationWe formulate the exact, resultant equilibrium conditions for the non-linear theory of branching and self-intersecting shells. The conditions are derived by performing direct through-the-thickness integration in the global equilibrium conditions of continuum mechanics. At each regular internal and boundary point of the base surface our exact, local equilibrium equations and dynamic boundary conditions are equivalent, as expected,...
-
A Review of Hyperelastic Constitutive Models for Dielectric Elastomers
PublicationDielectric elastomers are smart materials that are essential components in soft systems and structures. The core element of a dielectric elastomer is soft matter, which is mainly rubber-like and elastomeric. These soft materials show a nonlinear behaviour and have a nonlinear strain-stress curve. The best candidates for modelling the nonlinear behaviour of such materials are hyperelastic strain energy functions. Hyperelastic functions...
-
The effect of current signal filtering method on the value of cutting power while sawing wood
PublicationThe goal of this work was to investigate an effect of various signal pre-processings on the outline of the electrical power curve and its influence on the measured cutting force estimation. Two signal processing methods were selected for the needs of the experiment, including digital filter and wavelet transform. The filter used was Butterworth, 3rd order band-stop with the cut-out band from 45 Hz to 55 Hz. The second approach...
-
Social learning in cluster initiatives
PublicationPurpose – The purpose of the paper is to portray social learning in cluster initiatives (CIs), namely: 1) to explore, with the lens of the communities of practice (CoPs) theory, in what ways social learning occurs in CIs; 2) to discover how various CoPs emerge and evolve in CIs to facilitate a collective journey in their learning process. Subsequently, the authors address the research questions: In what ways does social learning...
-
Financial Analysis exercises - New (copy)
e-Learning CoursesTo obtain theoretical and practical experience of financial and economic analysis. Methods of economic analysis: Elements of production and human resources analysis, tangible assets analysis, inventory analysis, which would enable to understand the business case, to measure them and find suitable decision. To obtain theoretical and practical experience of financial analysis.
-
TensorHive: Management of Exclusive GPU Access for Distributed Machine Learning Workloads
PublicationTensorHive 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...
-
Decisions Analysis 2023/2024
e-Learning CoursesThis is content to the subject: "Decisions Analysis" to be used as a template for futher courses.
-
Qualitative data analysis methods
e-Learning CoursesThis is the continuation of Qualitatative Data Analysis Methods course provided online
-
Introduction to the special issue on machine learning in acoustics
PublicationWhen we started our Call for Papers for a Special Issue on “Machine Learning in Acoustics” in the Journal of the Acoustical Society of America, our ambition was to invite papers in which machine learning was applied to all acoustics areas. They were listed, but not limited to, as follows: • Music and synthesis analysis • Music sentiment analysis • Music perception • Intelligent music recognition • Musical source separation • Singing...
-
Model szkolenia "Blended learning" z wykorzystaniem platformy Oracle I-learning.
PublicationW artykule zaproponowano modele organizacyjne szkoleń "blended learning", które pokazują możliwości współpracy firm prywatnych z instytucjami edukacyjnymi w dziedzinie e-learningu. W ramach wspólnego eksperymentu firm Oracle, Incenti S.A., WiedzaNet Sp. z o.o. oraz Centrum Edukacji Niestacjonarnej Politechniki Gdańskiej w semestrze letnim roku akademickiego 2003/2004 udostępniony będzie kurs dla studentów Wydziału Inzynierii Lądowej...
-
The use of GIS tools for road infrastructure safety management
PublicationThere are many factors that influence accidents and their severity. They can be grouped within the system of man, vehicle and environment. The article focuses on how GIS tools can be used to manage road infrastructure safety. To ensure a better understanding and identification of road factors, GIS tools help with the acquisition of road parameter data. Their other role is helping with a clear and effective presentation of risk...
-
Fast bubble dynamics and sizing
PublicationSingle bubble sizing is usually performed by measuring the resonant bubble response using the Dual Frequency Ultrasound Method. However, in practice, the use of millisecond-duration chirp-like waves yields nonlinear distortions of the bubble oscillations. In comparison with the resonant curve obtained under harmonic excitation, it was observed that the bubble dynamic response shifted by up to 20 percent of the resonant frequency...
-
Influence of temperature and nitrogen pressure on the test without active gases for high-temperature proton exchange membrane fuel cells
PublicationHigh-Temperature Proton-Exchange Membrane Fuel Cells (HT-PEMFCs) are a candidate for electrical energy supply devices in more and more applications. Most notably in the aeronautic industry. Before any use, an HT-PEMFC is preheated and after that supplied with its active gases. Only at this state, the diagnostics can be performed. A method of testing not requiring a complete start-up would be beneficial for many reasons. This article...
-
The elasto-plastic numerical study of crack initiation in notched PMMA specimens under uniaxial loading conditions – Tension and torsion
PublicationThis paper presents the results of FEM numerical calculations aimed at describing the plastic strain and stress fields under critical loading conditions: tensile force or torsional moment. The calculations were carried out with reference to the results of experimental tensile and torsional tests of flat PMMA specimens weakened with V-notches of different root radii: 0.5, 2 and 10 mm. The procedure for conducting nonlinear numerical...
-
E-learning versus traditional learning - Polish case
PublicationE-learning jest współczesnym fenomenem, który pozwala na dostęp do kształcenia i treści edukacyjnych, niezależnie od czasu i miejsca, dla każdego użytkownika. E-learnig tworzy ogromne możliwości dla uczelni akademickich, organizacji, instytucji komercyjnych i szkoleniowych, dostarczając na żądanie kształcenia i szkoleń w wirtualnym środowisku. Student może stworzyć własny plan kształcenia, dostosowując go do swojej pracy i sytuacji...
-
Displacement piles - classification and methods for the calculation of bearing capacity.
PublicationDisplacement piles belong to a group of technologies whose main idea is to install or make a pile without extracting ground material. According to definition, contained in PN-EN:1997-1:2008, displacement piles should be considered as driven, pressed in using vibrators and made with the use of spread augers. The classification of piles used so far with regard to the technology of execution is modified. An additional element is the...
-
Determination of free tyrosine in equestrian supplements by LC–MS/MS and comparison of its quantity with total free amino acids content in view of doping control
PublicationThe reports on the probable beneficial impact of tyrosine (TYR) supplementation on performance enhancement have contributed to the growth of interest in TYR in equestrian sports field and related industries, such as the manufacture of dietary and nutritional supplements. In this study, the first attempt to the assessment of horses exposure to TYR during nutritional supplementation was demonstrated by quantification of unbound TYR...
-
Raw data of AuAg nanoalloy plasmon resonances used for machine learning method
Open Research DataRaw data used for machine learning process. UV-vis measurements of AuAg alloyed nanostructures created from thin films. Plasmonic band position dependence on fabrication parameters. Small presentation reviewing achieved structures and their properties.
-
EXTRAORDINARY RAINFALLS IN GDANSK (NORTHERN POLAND) IN THE 21ST CENTURY
PublicationIn the 21st century Gdansk had been affected by two rainfall events with a total precipitation amount of over 120 mm each. Rainfall parameters exceeded the regional values of the rain occurring once every 100 years. At the meteorological station of Gdansk University of Technology, July 9th 2001 was recorded 123.5 mm and July 14th 2016, 150.8 mm rainfall (within 24 hours observation period). Despite the same seasons of summer months...
-
Decisions Analysis STAC 22/23
e-Learning CoursesThis is content to the subject: "Decisions Analysis" 22/23
-
Electron scattering from tin tetrachloride (SnCl4) molecules
PublicationAbsolute grand-total cross section (TCS) for electron scattering from a tin tetrachloride, SnCl4, molecule was measured at electron-impact energies ranging from 0.6 to 300 eV, in the linear electron-transmission experiment. The measured TCS energy dependence shows two very pronounced enhancements peaking near 1.2 eV and around 9.5 eV, separated with a deep minimum centered close to 3 eV. The low energy structure is attributed to...
-
Pressure-induced phase transitions in LnTe (Ln=La, Gd, Ho, Yb) and AmTe
PublicationThe structural behaviour under compression of different lanthanide (La, Gd, Ho, Yb) and actinide (Am) monochalcogenides is studied by means of in situ high-pressure x-ray diffraction. All the investigated compounds crystallize at ambient conditions within a cubic (B1) NaCl-type structure but show different behaviours at high pressures. LaTe and AmTe undergo B1 to B2 (CsCl-type structure) phase transitions, starting at 9 GPa and...
-
Static and dynamic concrete calculations: Breakable aggregates in DEM model
PublicationThe paper deals with the calculations of a 3-point bending beam under static and dynamic loads. The real microstructure was obtained from laboratory tests using micro-tomography images. The quasi-static results were compared directly with experimental data at both macro and micro levels. Subsequently, higher strain rates were applied to investigate dynamic effects. The study focused on the influence of dynamic loading on the macroscopic...
-
Towards hand grip force assessment by using EMG estimators
PublicationThe purpose of this study was to propose a method to assess individual regression (calibration) curves to establish a relationship between an isometric grip force and surface electromyography (EMG) estimator. In this study 18 healthy volunteers (12 male (23.0 ± 2.0 years) and 6 female (23.2 ± 0.7 years)) had been examined. Ten EMG estimators (mean absolute value, root mean square, entropy, energy, turns per second, mean of zero...
-
Detection of Closing Crack in Beam Based on Responses Induced by Harmonic Excitation
PublicationThe non-linear contact model was chosen to simulate the closed crack in the cantilever beam. The study examines the shape and characteristics of the phase diagram of a cantilever beam with closed cracks. It investigates how various crack properties influence the geometry of the phase diagram and proposes a method for identifying cracks based on their features. The area of each closed curve in the phase diagram is determined using...
-
Electronic structure and rovibrational predissociation of the 2^1Π state in KLi
PublicationAdiabatic potential energy curves of the 3^1Σ^+, 3^3Σ^+, 2^1Π and 2^3Π states correlating for large internuclear distance with the K(4s) + Li(2p) atomic asymptote were calculated. Very good agreement between the calculated and the experimental curve of the 2^1Π state allowed for a reliable description of the dissociation process through a small (∼20 cm−1 for J = 0) potential energy barrier. The barrier supports several rovibrational...
-
A Simulation Model for Risk and Pricing Competition in the Retail Lending Market
PublicationWe propose a simulation model of the retail lending market with two types of agents: borrowers searching for low interest rates and lenders competing through risk-based pricing. We show that individual banks observe adverse selection, even if every lender applies the same pricing strategy and a credit scoring model of comparable discrimination power. Additionally, the model justifies the reverse-S shape of the response rate curve....
-
Interactions between hydration spheres of two different solutes in solution: The least squares fitting with constraints as a tool to determine water properties in ternary systems
PublicationBiological systems are complex and the problem of their description lies in mutual interactions between their components. This paper is focused on model experiment-based studies which can reduce these difficulties. The ternary aqueous N-methylacetamide (NMA)–Na2HPO4 system has been studied by means of the FTIR spectroscopy. A novel difference spectra method aimed to extract the spectral contribution of water affected simultaneously...
-
How Machine Learning Contributes to Solve Acoustical Problems
PublicationMachine learning is the process of learning functional relationships between measured signals (called percepts in the artificial intelligence literature) and some output of interest. In some cases, we wish to learn very specific relationships from signals such as identifying the language of a speaker (e.g. Zissman, 1996) which has direct applications such as in call center routing or performing a music information retrieval task...
-
Neural networks and deep learning
PublicationIn this chapter we will provide the general and fundamental background related to Neural Networks and Deep Learning techniques. Specifically, we divide the fundamentals of deep learning in three parts, the first one introduces Deep Feed Forward Networks and the main training algorithms in the context of optimization. The second part covers Convolutional Neural Networks (CNN) and discusses their main advantages and shortcomings...
-
Blended Learning in Teaching Safety of Electrical Installations
PublicationBlended learning becomes more commonly used in teaching information technology or other subjects, which involve practice in computer laboratories. In case of subjects with no access to computer rooms blended learning supports lecturing and teaching classes e.g. interactive lessons. The article presents the use of blended learning forms in Gdansk University of Technology in teaching the subject of Safety of Electrical Installations....
-
Limitations of Emotion Recognition from Facial Expressions in e-Learning Context
PublicationThe paper concerns technology of automatic emotion recognition applied in e-learning environment. During a study of e-learning process the authors applied facial expressions observation via multiple video cameras. Preliminary analysis of the facial expressions using automatic emotion recognition tools revealed several unexpected results, including unavailability of recognition due to face coverage and significant inconsistency...
-
Ultrasound and Clinical Preoperative Characteristics for Discrimination Between Ovarian Metastatic Colorectal Cancer and Primary Ovarian Cancer: A Case-Control Study
PublicationThe aim of this study was to describe the clinical and sonographic features of ovarian metastases originating from colorectal cancer (mCRC), and to discriminate mCRC from primary ovarian cancer (OC). We conducted a multi-institutional, retrospective study of consecutive patients with ovarian mCRC who had undergone ultrasound examination using the International Ovarian Tumor Analysis (IOTA) terminology, with the addition of evaluating...
-
Agnieszka Landowska dr hab. inż.
PeopleAgnieszka Landowska works for Gdansk University of Technology, FETI, Department of Software Engineering. Her research concentrates on usability, accessibility and technology adoption, as well as affective computing methods. She initiated Emotions in HCI Research Group and conducts resarch on User eXperiene evaluation of applications and other technologies.
-
Data Analysis 2023/24
e-Learning CoursesData Analysisdr inż. Karol Flisikowski, prof. PG - winter semester 2023/24
-
SUBSOIL CHARACTERISTICS OF THE VISTULA RIVER DIKES
PublicationThe results of CPTU tests are used to determine the strength parameters of a dike subsoil. Stress state and stress history of the subsoil under the flood embankment was evaluated with CPTU and DMT tests. Normally consolidated soil was found under the central part of the dike, while the subsoil near the dike toe is found to be overconsolidated. Due to consolidation the undrained shear strength of the subsoil under the central part...
-
Two- and three-dimensional elastic networks with rigid junctions: modeling within the theory of micropolar shells and solids
PublicationFor two- and three-dimensional elastic structures made of families of flexible elastic fibers undergoing finite deformations, we propose homogenized models within the micropolar elasticity. Here we restrict ourselves to networks with rigid connections between fibers. In other words, we assume that the fibers keep their orthogonality during deformation. Starting from a fiber as the basic structured element modeled by the Cosserat...
-
Frequency response spectra applied to assess efficiency of the training techniques
PublicationThe purpose of the research is to assess the increase of the muscle strength and power. Movement of the human body when the moving one impacts a stationary or moving body is taken under consideration. The waveform produced by an impact is transformed into frequency domain. The acceleration record is transformed as a complex spectrum, by the use of a Discrete Fourier Transformation. In this paper the applications of the discrete...
-
Multi-functional sensor based on photonic crystal fiber using plasmonic material and magnetic fluid
PublicationA unique highly sensitive photonic crystal fiber is investigated based on plasmonic material and magnetic fluid (MF) for the simultaneous measurement of temperature and magnetic field sensor. The designed sensor is explored by tracing the different parameters such as birefringence, coupling length, power spectrum, and the peak wavelength of the transmission intensity. The magnetic field and temperature computation are attained...