Filtry
wszystkich: 2155
-
Katalog
- Publikacje 1799 wyników po odfiltrowaniu
- Czasopisma 26 wyników po odfiltrowaniu
- Konferencje 18 wyników po odfiltrowaniu
- Osoby 89 wyników po odfiltrowaniu
- Projekty 1 wyników po odfiltrowaniu
- Kursy Online 48 wyników po odfiltrowaniu
- Wydarzenia 7 wyników po odfiltrowaniu
- Dane Badawcze 167 wyników po odfiltrowaniu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: MATCHING TRANSFORMER
-
Evaluation of aspiration problems in L2 English pronunciation employing machine learning
PublikacjaThe approach proposed in this study includes methods specifically dedicated to the detection of allophonic variation in English. This study aims to find an efficient method for automatic evaluation of aspiration in the case of Polish second-language (L2) English speakers’ pronunciation when whole words are analyzed instead of particular allophones extracted from words. Sample words including aspirated and unaspirated allophones...
-
Study of various machine learning approaches for Sentinel-2 derived bathymetry
PublikacjaIn recent years precise and up-to-date information regarding seabed depth has become more and more important for companies and institutions that operate on coastlines. While direct, in-situ measurements are performed regularly, they are expensive, time-consuming and impractical to be performed in short time intervals. At the same time, an ever-increasing amount of satellite imaging data becomes available. With these images, it...
-
Selection of form factors of machine carrying systems in reliance on the process duty
Publikacja -
Features of Machine Cyclogram Optimization with the Account of Interaction of Mechanism Links with Stops
Publikacja -
Determination of the rigidity and deformation energy of the technological machine load-carrying systems
Publikacja -
Predictions of cervical cancer identification by photonic method combined with machine learning
PublikacjaCervical 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...
-
Research on a permanent magnet assisted synchronous reluctance machine with hybrid excitation
Publikacja -
Control system based on the modified multiscalar model for the double fed machine
PublikacjaPrzedstawiono układ sterowania maszyną asynchroniczą dwustronnie zasilaną wykorzystujący zmodyfikowany model multisaklarny. Wprowadzone nielinowe sprzężenia pozwalają na podział systemu na dwa niezależne podukłady. Pododuje to brak zauważalnych sprzężeń przy regulacji mocy czynnej i biernej regulowanej przez kontrolery PI. W układzie wyeliminowano konieczność stosowania kaskadowego połączenia regulatorów. Przedstawiono wyniki symulacji.
-
Simulation of influence of the air gap asymmetryon voltage waveforms of a synchronous machine
PublikacjaResults of simulation of a synchronous generator with the air gap asymmetry characterised by eccentricity are presented in the paper. The Lagrange's energy method has been used in derivation of the model equations. Analysis of influence of the air gap asymmetry on characteristics of self and mutual inductances of windings, as well as analysis of induced voltage waveforms as a function of the air gap asymmetry have been performed....
-
Efficient sampling of high-energy states by machine learning force fields
Publikacja -
Modeling lignin extraction with ionic liquids using machine learning approach
PublikacjaLignin, next to cellulose, is the second most common natural biopolymer on Earth, containing a third of the organic carbon in the biosphere. For many years, lignin was perceived as waste when obtaining cellulose and hemicellulose and used as a biofuel for the production of bioenergy. However, recently, lignin has been considered a renewable raw material for the production of chemicals and materials to replace petrochemical resources....
-
Testing motional accuracy of a manufacturing machine - a task imposed on modern maintenance
PublikacjaArtykuł dotyczy zagadnień utrzymania ruchu maszyn w powiązaniu z problemami parametryzacji zautomatyzowanych napędów. Przedstawiono krótki przegląd i kierunki rozwoju wspomagania komputerowego w ramach zakładowych systemów utrzymania ruchu. Zwrócono uwagę na pomijanie w popularnie publikowanych graficznych modelach systemów informatycznych CIM, ich podsystemów dedykowanych dla wspomagania utrzymania ruchu maszyn, podczas gdy takie...
-
Rotor-Flux Vector based Observer of Interior Permanent Synchronous Machine
PublikacjaThe sensorless control system of the interior permanent magnet machine is considered in this paper. The control system is based on classical linear controllers. In the machine, there occurs non-sinusoidal distribution of rotor flux together with the slot harmonics, which are treated as the control system disturbances. In this case, the classical observer structure in the (d-q) is unstable for the low range of rotor speed resulting...
-
Stacking and rotation-based technique for machine learning classification with data reduction
Publikacja -
POPULATION-BASED MULTI-AGENT APPROACH TO SOLVING MACHINE LEARNING PROBLEMS
Publikacja -
Calculation of self and mutual inductances of the switched reluctance machine mathematical model.
PublikacjaA mathematical model of the switched reluctance machine (SRM) in a drive system obtained using Lagrange's energy method and a method of calculation of self and mutual inductances of the SRM are presented in the paper. The self and mutual inductances are elements of Lagrange's function in generalised coordinates and have been calculated using the finite element method (FEM). Selected calculation results for the particular machine...
-
Modular machine learning system for training object detection algorithms on a supercomputer
PublikacjaW 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...
-
Dangerous sound event recognition using Support Vector Machine classifiers
PublikacjaA method of recognizing events connected to danger based on their acoustic representation through Support Vector Machine classification is presented. The method proposed is particularly useful in an automatic surveillance system. The set of 28 parameters used in the classifier consists of dedicated parameters and MPEG-7 features. Methods for parameter calculation are presented, as well as a design of SVM model used for classification....
-
Molecular Diffusion Simulation on ARUZ – Massively-parallel FPGA-based Machine
Publikacja -
Tests on lateral resistance in railway track during operation of tamping machine
PublikacjaArtykuł prezentuje koncepcję prowadzenia badań oporów poprzecznych w trakcie procesu regulacji geometrycznej toru kolejowego za pomocą podbijarki. Jest to zatem kontynuacja badań nad zastosowaniem podbijarki torowej w diagnostyce toru bezstykowego; wcześniej zajmowano się kwestią określania sił podłużnych w szynach. Przedstawiono sposób wyznaczania oporów poprzecznych polegający na ciągłej rejestracji przemieszczenia oraz siły...
-
The use of tamping machine for diagnosising the longitudinal forces in rails of CWR track
PublikacjaW pracy przedstawiono przebieg prowadzonych od kilkunastu lat w Politechnice Gdańskiej badań nad wyznaczaniem sił podłużnych w szynach toru bezstykowego. Opisano skonstruowaną aparaturę pomiarową. Badania eksperymentalne polegały na podnoszeniu, a następnie poprzecznym nasuwaniu rusztu torowego za pomocą podbijarki. Rejestrowano przy tym wartości przemieszczeń toru oraz odkształcenia siłowników hydraulicznych. W rezultacie ostatnich...
-
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...
-
Quantitative Risk Assessment in Construction Disputes Based on Machine Learning Tools
PublikacjaA high monetary value of the construction projects is one of the reasons of frequent disputes between a general contractor (GC) and a client. A construction site is a unique, one-time, and single-product factory with many parties involved and dependent on each other. The organizational dependencies and their complexity make any fault or mistake propagate and influence the final result (delays, cost overruns). The constant will...
-
Process of Medical Dataset Construction for Machine Learning-Multifield Study and Guidelines
PublikacjaThe acquisition of high-quality data and annotations is essential for the training of efficient machine learning algorithms, while being an expensive and time-consuming process. Although the process of data processing and training and testing of machine learning models is well studied and considered in the literature, the actual procedures of obtaining data and their annotations in collaboration with physicians are in most cases...
-
Real and Virtual Instruments in Machine Learning – Training and Comparison of Classification Results
PublikacjaThe 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...
-
Electrodes array for contactless ECG measurement of a bathing person - a sensitivity analysis
PublikacjaAn applicability of a remote (contactless) electrocardiogram (ECG) measurements in a bathtub is presented in the paper. Possibility of ECG measurements in shallowly filled tube with a water was examined. A bathing person was, both, sitting and lying during experiments performed. The problem became non-trivial when the bathing person was moving in reference to a fixed set of electrodes and located at the longer walls of the bathtub....
-
High gain/bandwidth off‑chip antenna loaded with metamaterial unit‑cell impedance matching circuit for sub‑terahertz near‑field electronic systems
PublikacjaAn innovative off-chip antenna (OCA) is presented that exhibits high gain and efficiency performance at the terahertz (THz) band and has a wide operational bandwidth. The proposed OCA is implemented on stacked silicon layers and consists of an open circuit meandering line. It is shown that by loading the antenna with an array of subwavelength circular dielectric slots and terminating it with a metamaterial unit cell, its impedance...
-
Michał Michna dr hab. inż.
OsobyJest absolwentem Wydziału Elektrycznego Politechniki Gdańskiej (1998). W 2004 r. uzyskał stopień doktora. Od 2004 r. zatrudniony w Katedrze Energoelektroniki i Maszyn Elektrycznych Politechniki Gdańskiej (asystent, adiunkt, starszy wykładowca). W latach 2010-2015 zastępca kierownik katedry. Jego zainteresowania naukowe i dydaktyczne obejmują szerokie spektrum zagadnień związanych z projektowanie, modelowanie i diagnostyką maszyn...
-
Nested Kriging Surrogates for Rapid Multi-Objective Optimization of Compact Microwave Components
PublikacjaA procedure for rapid EM-based multi-objective optimization of compact microwave components is presented. Our methodology employs a recently developed nested kriging modelling to identify the search space region containing the Pareto-optimal designs, and to construct a fast surrogate model. The latter permits determination of the initial Pareto set, further refined using a separate surrogate-assisted process. As an illustration,...
-
Multi-objective design optimization of antenna structures using sequential domain patching with automated patch size deter-mination
PublikacjaIn this paper, a simple yet efficient and reliable technique for fully automated multi-objective design optimization of antenna structures using sequential domain patching (SDP) is discussed. The optimization procedure according to SDP is a two-step process: (i) obtaining the initial set of Pareto-optimal designs representing the best possible trade-offs between considered conflicting objectives, and (ii) Pareto set refinement...
-
Patch size setup and performance/cost trade-offs in multi-objective antenna optimization using domain patching technique
PublikacjaA numerical study concerning multi-objective optimization of antenna structures using sequential domain patching (SDP) technique has been presented. We investigate the effect of various setups of the patch size on the operation of the SDP algorithm and possible trade-offs concerning the quality of the Pareto set found by SDP and the computational cost of the optimization process. Our considerations are illustrated using a UWB monopole...
-
Sensorless Multiscalar Control of Five-Phase Induction Machine with Inverter Output Filter
PublikacjaThe paper presents a complete solution for speed sensorless control system for five-phase induction motor with voltage inverter, LC filter and nonlinear control of combined fundamental and third harmonic flux distribution. The control principle, also known as multiscalar control, nonlinear control or natural variables control, is based on a use of properly selected scalar variables in control feedback to linearize controlled system....
-
Application of Support Vector Machine for Determination of Impact of Traffic-Induced Vibrations on Buildings
PublikacjaThe aim of the article is to present an algorithm of Support Vector Machine created to forecast the impact of traffic-induced vibrations on residential buildings. The method is designed to classify the object into one of two classes. The classification into the first class means that there is no impact of vibrations on the building, while classification to the second class indicates the possible influence and suggests the execution...
-
The methodology for determining of the value of cutting power for cross cutting on optimizing sawing machine
PublikacjaIn the article the methodology of forecasting the energy effects of the cross-cutting process using the classical method, which takes into account the specific cutting resistance, is presented. The values of cutting power for the cross-cutting process of two types of wood (softwood and hardwood) were forecasted for the optimizing sawing machine with using presented methodology. The cross-cutting process with high values of feed...
-
Application of sliding switching functions in backstepping based speed observer of induction machine
PublikacjaThe paper presents an analysis of the speed observer which is based on the backstepping and sliding mode approach. The speed observer structure is based on the extended mathematical model of an induction machine. The observer structure is based on the measured phase stator currents and transformed to ( αβ ) coordinate system. The stator voltage vector components are treated as known values. Additionally, such an observer structure...
-
Detection of People Swimming in Water Reservoirs with the Use of Multimodal Imaging and Machine Learning
PublikacjaEvery year in many countries, there are fatal unintentional drownings in different water reservoirs like swimming pools, lakes, seas, or oceans. The existing threats of this type require creating a method that could automatically supervise such places to increase the safety of bathers. This work aimed to create methods and prototype solutions for detecting people bathing in water reservoirs using a multimodal imaging system and...
-
Preeclampsia Risk Prediction Using Machine Learning Methods Trained on Synthetic Data
PublikacjaThis paper describes a research study that investigates the use of machine learning algorithms on synthetic data to classify the risk of developing preeclampsia by pregnant women. Synthetic datasets were generated based on parameter distributions from three real patient studies. Four models were compared: XGBoost, Support Vector Machine (SVM), Random Forest, and Explainable Boosting Machines (EBM). The study found that the XGBoost...
-
Machine learning techniques combined with dose profiles indicate radiation response biomarkers
Publikacja -
Slowly-closing valve behaviour during steam machine accelerated start-up
PublikacjaThe paper discusses the state of stress in a slowly-closing valve during accelerated start-up of a steam turbine. The valve is one of the first components affected by high temperature gradients and is a key element on which the power, efficiency and safety of the steam system depend. The authors calibrated the valve model based on experimental data and then performed extended Thermal-FSI analyses relative to experiment. The issue...
-
Machine-aided detection of SARS-CoV-2 from complete blood count
PublikacjaThe current gold standard for SARS-CoV-2 detection methods lacks the functionality to perform population screening. Complete blood count (CBC) tests are a cost-effective way to reach a wide range of people – e.g. according to the data of the Central Statistical Office of Poland from 2016, there are 3,000 blood diagnostic laboratories in Poland, and 46% of Polish people have at least one CBC test per year. In our work, we show...
-
Multivariate Features Extraction and Effective Decision Making Using Machine Learning Approaches
Publikacja -
Analytical model of torsional vibrations of typical sawing machine main drive system
PublikacjaPrzedstawiono model fizyczny i matematyczny drgań skrętnych napędu głównego typowej pilarki tarczowej. Model tworzą elementy sztywne SES połączone między sobą za pośrednictwem elementów sprężysto - tłumiących EST w układzie szeregowym. W modelu matematycznym uwzględniono: właściwości dynamiczne silnika napędowego, wymiary piły tarczowej, cechy materiału obrabianego (wymiary, rodzaj drewna, wilgotność drewna) oraz właściwości dynamiczne...
-
Influence of frame sawing machine´s kinematics on saw blade tooth wear.
PublikacjaW pracy przedstawiono wpływ kinematyki pilarki ramowej na zużycie ostrzy piłtrakowych.
-
Driver’s Condition Detection System Using Multimodal Imaging and Machine Learning Algorithms
PublikacjaTo this day, driver fatigue remains one of the most significant causes of road accidents. In this paper, a novel way of detecting and monitoring a driver’s physical state has been proposed. The goal of the system was to make use of multimodal imaging from RGB and thermal cameras working simultaneously to monitor the driver’s current condition. A custom dataset was created consisting of thermal and RGB video samples. Acquired data...
-
Machine learning for the management of biochar yield and properties of biomass sources for sustainable energy
PublikacjaBiochar is emerging as a potential solution for biomass conversion to meet the ever increasing demand for sustainable energy. Efficient management systems are needed in order to exploit fully the potential of biochar. Modern machine learning (ML) techniques, and in particular ensemble approaches and explainable AI methods, are valuable for forecasting the properties and efficiency of biochar properly. Machine-learning-based forecasts,...
-
Advancing Solar Energy: Machine Learning Approaches for Predicting Photovoltaic Power Output
PublikacjaThis research is primarily concentrated on predicting the output of photovoitaic power, an essential field in the study of renewable energy. The paper comprehensively reviews various forecasting methodologies, transitioning from conventional physical and statistical methods to advanced machine learning (ML) techniques. A significant shift has been observed from traditional point forecasting to machine learning-based forecasting...
-
Predicting emotion from color present in images and video excerpts by machine learning
PublikacjaThis work aims at predicting emotion based on the colors present in images and video excerpts using a machine-learning approach. The purpose of this paper is threefold: (a) to develop a machine-learning algorithm that classifies emotions based on the color present in an image, (b) to select the best-performing algorithm from the first phase and apply it to film excerpt emotion analysis based on colors, (c) to design an online survey...
-
DNAffinity: a machine-learning approach to predict DNA binding affinities of transcription factors
PublikacjaWe present a physics-based machine learning approach to predict in vitro transcription factor binding affinities from structural and mechanical DNA properties directly derived from atomistic molecular dynamics simulations. The method is able to predict affinities obtained with techniques as different as uPBM, gcPBM and HT-SELEX with an excellent performance, much better than existing algorithms. Due to its nature, the method can...
-
Machine learning approach to packaging compatibility testing in the new product development process
PublikacjaThe paper compares the effectiveness of selected machine learning methods as modelling tools supporting the selection of a packaging type in new product development process. The main goal of the developed model is to reduce the risk of failure in compatibility tests which are preformed to ensure safety, durability, and efficacy of the finished product for the entire period of its shelf life and consumer use. This kind of testing...
-
Machine learning-based seismic response and performance assessment of reinforced concrete buildings
PublikacjaComplexity and unpredictability nature of earthquakes makes them unique external loads that there is no unique formula used for the prediction of seismic responses. Hence, this research aims to implement the most well-known Machine Learning (ML) methods in Python software to propose a prediction model for seismic response and performance assessment of Reinforced Concrete Moment-Resisting Frames (RC MRFs). To prepare 92,400 data...