Filtry
wszystkich: 6359
-
Katalog
- Publikacje 4883 wyników po odfiltrowaniu
- Czasopisma 764 wyników po odfiltrowaniu
- Konferencje 46 wyników po odfiltrowaniu
- Osoby 259 wyników po odfiltrowaniu
- Projekty 34 wyników po odfiltrowaniu
- Kursy Online 112 wyników po odfiltrowaniu
- Wydarzenia 6 wyników po odfiltrowaniu
- Dane Badawcze 255 wyników po odfiltrowaniu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: APPLIED MACHINE LEARNING
-
Attention-Based Deep Learning System for Classification of Breast Lesions—Multimodal, Weakly Supervised Approach
PublikacjaBreast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering-constrained Attention Multiple Instance Learning (CLAM) classifier able to train under data scarcity effectively. We used a private...
-
Induction motor bearings diagnostic indicators based on MCSA and normalized triple covariance
PublikacjaInduction motors are one of the most widely used electrical machines. Statistics of bearing failures of induction motors indicate, that they constitute more than 40% of induction motor damage. Therefore, bearing diagnosis is so important for trouble-free work of induction motors. The most common methods of bearing diagnosis are based on vibration signal analysis. The main disadvantage of those methods is the need for physical access...
-
Reducing common mode voltage and bearing currents in quasi - resonant DC - link inverter
PublikacjaIn the paper, a concept of separation of an inverter-fed induction motor drive from its mains supply by two transistor switches inserted in the dc-link circuit is reexamined based on the proposed parallel quasi-resonant dc-link inverter (PQRDCLI). The objective of the paper is to show an advantage of the proposed topology in limiting high frequency common mode voltage and bearing currents. In the laboratory setup, an induction...
-
ColorNephroNet: Kidney tumor malignancy prediction using medical image colorization
PublikacjaRenal tumor malignancy classification is one of the crucial tasks in urology, being a primary factor included in the decision of whether to perform kidney removal surgery (nephrectomy) or not. Currently, tumor malignancy prediction is determined by the radiological diagnosis based on computed tomography (CT) images. However, it is estimated that up to 16% of nephrectomies could have been avoided because the tumor that had been...
-
„Eulerian – Eulerian” versus ,,Eulerian –Lagrangean” models of condensation
PublikacjaLiquid phase in the flowing vapor through stages of the steam turbine is the cause of a lot of failures. Nowadays, due to work of steam turbines at partial load, process of homogeneous and heterogeneous condensation still is current. The formation of drops of condensate under conditions other than nominal operation of turbine is a process still unknown. Engineers and designers involved in the development of power station machines...
-
RAPORT - EKSPERTYZA Z POMIARÓW DRGAŃ LINII WAŁÓW NA JEDNOSTCE ORP „DĄBIE”
PublikacjaEkspertyza diagnostyczna dotycząca stanu technicznego dwóch linii transmisji mocy (linii wałów) opracowana na podstawie przeprowadzonych pomiarów drgań w 26 punktach pomiarowych, przy jednoczesnej pracy silników napędowych L i PB (wspólnej pracy linii wałów obu burt), w II zakresach ustalonego obciążenia „pół-naprzód” i „cała-naprzód”. Pomiary prędkości i przyspieszeń drgań generowanych przez węzły konstrukcyjne okrętowego układu...
-
Efficiency of linear and non-linear classifiers for gas identification from electrocatalytic gas sensor
PublikacjaElectrocatalytic gas sensors belong to the family of electrochemical solid state sensors. Their responses are acquired in the form of I-V plots as a result of application of cyclic voltammetry technique. In order to obtain information about the type of measured gas the multivariate data analysis and pattern classification techniques can be employed. However, there is a lack of information in literature about application of such...
-
Crack propoagation in MgO-PSZ ceramic materials
PublikacjaThe properties of ceramic materials such as elevated hardness, high temperature capability, low coefficient of thermal expansion are of interest for rolling element materials. Widely used ceramic materials in engineering applications are silicon nitride, zirconia and alumina. The paper presents an experimental study of the fatigue life of MgO-PSZ ceramic material in lubricated contact with defined types of cracks. A ceramic angular...
-
Histogram of Oriented Gradients with Cell Average Brightness for Human Detection
PublikacjaA modification of the descriptor in a human detector using Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) is presented. The proposed modification requires inserting the values of average cell brightness resulting in the increase of the descriptor length from 3780 to 3908 values, but it is easy to compute and instantly gives ≈ 25% improvement of the miss rate at 10‒4 False Positives Per Window (FPPW). The...
-
MCSA with Normalized Triple Covariance as a bearings diagnostic indicator in an induction motor
PublikacjaStatistics of bearing failures in induction motors indicate, that they constitute more than 40% of IM damage, therefore bearing diagnosis is very important. Vibration methods for bearing diagnostics have one major disadvantage - they require the availability of the machine for sensors installation. This is the reason for seeking new methods based on motor supply current analysis. Diagnosis of induction motors, conducted remotely...
-
Friction-Induced Oscillations of a Non-Asbestos Organic Pin Sliding on a Steel Disc
PublikacjaFriction-induced oscillations result in deterioration of performance of disc brakes and are generally undesired. We conduct experimental study of friction-induced oscillations in a non-asbestos organic material / steel pair used in disc brakes of motor vehicles. The tests are done by use of a pin-on-disc machine which has the pin sample supported on a deformable beam. The adjustable friction parameters are the disc velocity, contact...
-
Comparable analysis of PID controller settings in order to ensure reliable operation of active foil bearings
PublikacjaIn comparison to the traditional solutions, active bearings offer great operating flexibility, ensure better operating conditions over a wider range of rotational speeds and are safe to use. In order to ensure optimum bearing performance a bearing control system is used that adapts different geometries during device operation. The selection of optimal controller parameters requires the use of modern optimization methods that make...
-
Studying the Effect of Working Conditions on WEDM Machining Performance of Super Alloy Inconel 617
PublikacjaWire electrical discharge machining (WEDM) has been for many years a precise and efficient non-conventional manufacturing solution in various industrial applications, mostly involving the use of hard-to machine materials like, among other, the Inconel super alloys. The focus of the present study is on exploring the effect of selected control parameters, including pulse duration, pulse-off time and the dielectric flow pressure on...
-
Modeling of a Quasi-Resonant DC Link Inverter Dedicated to Common-Mode Voltage and Ground Current Reduction
PublikacjaIn this paper, the modeling methodology of the AC drive system with a Parallel Quasi-Resonant DC Link Inverter (PQRDCLI) is described. A presented modeling approach is an attractive tool used for the effective evaluation of a common-mode (CM) voltage and grounds current reduction methods. Designed models of inverter, induction machine (IM), and cable are simple, thus the methods for parameter extraction are not complicated. Verification...
-
Wireless Body Area Network for Preventing Self-Inoculation Transmission of Respiratory Viral Diseases
PublikacjaThis paper proposes an idea of Wireless Body Area Networks (WBANs) based on Bluetooth Low-Energy (BLE) standards to recognize and alarm a gesture of touching the face, and in effect, to prevent self-inoculation of respiratory viral diseases, such as COVID-19 or influenza A, B, or C. The proposed network comprises wireless modules placed in bracelets and a necklace. It relies on the received signal strength indicator (RSSI) measurements...
-
Optical monitoring of electrochemical processes with ITO-based lossy-mode resonance optical fiber sensor applied as an electrode
PublikacjaIn this work we discuss the application of optical fiber sensors based on lossy-mode resonance (LMR) phenomenon for real-time optical monitoring of electrochemical processes. The sensors were obtained by a reactive high power impulse magnetron sputtering of indium tin oxide (ITO) on a 2.5 cm-long core of polymer-clad silica fibers. The LMR effect made monitoring of changes in optical properties of both ITO and its surrounding medium...
-
Particle Filter Modification using Kalman Optimal Filtering Method as Applied to Road Detection from Satellite Images
PublikacjaIn the paper recursive state estimation approach is presented as applied to satellite images. Especially, a model of dynamic systems of the non-linear and non-Gaussian systems is presented, and finally the Kalman filter and particle filter and an integration of both is figured out. Special attention is paid to the application for satellite image analysis.
-
Computer Aided Machine Design and Manufacturing (PG_00060425)
Kursy Online -
Automated detection of pronunciation errors in non-native English speech employing deep learning
PublikacjaDespite significant advances in recent years, the existing Computer-Assisted Pronunciation Training (CAPT) methods detect pronunciation errors with a relatively low accuracy (precision of 60% at 40%-80% recall). This Ph.D. work proposes novel deep learning methods for detecting pronunciation errors in non-native (L2) English speech, outperforming the state-of-the-art method in AUC metric (Area under the Curve) by 41%, i.e., from...
-
An Adaptive Network Model for a Double Bias Perspective on Learning from Mistakes within Organizations
PublikacjaAlthough making mistakes is a crucial part of learning, it is still often being avoided in companies as it is considered as a shameful incident. This goes hand in hand with a mindset of a boss who dominantly believes that mistakes usually have negative consequences and therefore avoids them by only accepting simple tasks. Thus, there is no mechanism to learn from mistakes. Employees working for and being influenced by such a boss...
-
Grzegorz Graff prof. dr hab.
Osoby -
Inter Applied Chemistry Programme 6 A practical approach to novel industrial enzymes Dr Natasha Bozic
Kursy OnlineInter Applied Chemistry Programme 6 - A practical approach to novel industrial enzymes Dr Natasha Bozic The purpose of the course is to introduce students to the technologies of industrial enzymes discovery and manufacturing and to provide in depth insight about the advantages of using enzyme preparations in industry. Lectures will cover the common workflows of industrial enzymology including following topics: general enzyme...
-
AUTOMATIC LEARNING OF STRATEGY AND RULES IN CARD GAMES USING IMAGE FROM CAMERA
PublikacjaBelow work tries to answer a question: if it is possible to replace real human with computer system in social games. As a subject for experiments, card games were chosen, because they require a lot of player interaction (playing and taking cards), while their rules are easy to present in form of clear list of statements. Such a system, should allow real players to play without constant worrying about guiding or helping computer...
-
Long-term operation of Kickuth-type constructed wetland applied to municipal wastewater treatment in temperate climate
PublikacjaThe purpose of this paper is to discuss the problem of changes of effectiveness of Kickuth-type constructed wetland with subsurface flow applied to domestic wastewater treatment. This study is based on an example of a wetland 3000 m2 in surface, serving 800 inhabitants, located in Poland. The results of chemical analysis showed that after an initial year of ‘start-up time’, the efficiency of pollutant removal gradually increased...
-
Projektowanie zajęć prowadzonych na odległość (10h e-learning)
Kursy Online -
Research on Innovative Hybrid Excited Synchronous Machine
Publikacja -
Research of IPM electrical machine with flux barriers
Publikacja -
Work parameters research of wood pellet machine
Publikacja -
Cluster-based instance selection for machine classification
Publikacja -
An Approach to Data Reduction and Integrated Machine Classification
Publikacja -
Precision of cutting system in circular sawing machine
PublikacjaW pracy przedstawiono analizę dokładności układu przecinania pilarki tarczowej, w której uwzglednoino dokładność struktury geometryczno- ruchowej przecinarki.
-
Dynamics of the circular sawing machine spindle system
PublikacjaW pracy przedstawiono wyniki badań wpływu prędkości obrotowej na dynamikę układu wrzecionowego pilarki tarczowej. Czynnikami badanymi były bicie osiowe i promieniowe wrzeciona, które mierzono za pomocą czujników wiroprądowych na kierunku działania przekładni pasowej, a także na kierunku do niego prostopadłym. Przeprowadzone badania eksperymentalne wykazały, że wartość prędkości obrotowej wrzeciona oraz sposób przekazywania mocy...
-
Frequency characteristics of induction machine speed observers
PublikacjaWłaściwości napędu bezczujnikowego z silnikiem indukcyjnym zależą od struktury obserwatora prędkości. System ten wymaga starannej analizy w przypadku uszkodzenia maszyny, której celem jest odpowiedź na pytania: jak układ regulacji pracuje przy niesymetrii maszyny spowodowanej np. uszkodzeniem klatki wirnika oraz jak obserwator odtwarza pulsacje prędkości spowodowane niesymetrią maszyny. W artykule przedstawiono charakterystyki...
-
Dynamics of the total system of the circular sawing machine
PublikacjaW pracy przedstwaiono przyczyny i efekty zmiany położenia ostrzy piły tarczowej. Opisana metoda pomiaru zachowania dynamicznego piły pozwala uzytkownikowi okreslic przyczyny drgań. Ponadto, może wskazać drogi efektywnej ich minimalizacji.
-
Emissivity of the one-plate lapping machine tool
PublikacjaPrzedstawiono wyniki badań własnych emisyjności docieraka żeliwnego docierarki jednotarczowej. Omówiono konstrukcje produkowanych docierarek jednotarczowych wyposażonych w system kontroli temperatury lub chłodzenia tarczy docierającej. Podano warunki pomiarów temperatury przy użyciu kamery termowizyjnej typu V-20II firmy VIGO System S.A.
-
Bearing testing machine with rotating load vector.
PublikacjaW pracy przedstawiono koncepcję konstrukcyjną i prototyp stanowiska badawczego z wirująca reakcją łożyskową przeznaczonego do testowania wytrzymałości zmęczeniowej warstw ślizgowych w łożyskach poprzecznych. Konstrukcja i przeznaczenie maszyny zbudowanej w laboratorium tribologicznym Politechniki Gdańskiej jest zgodna z zaleceniami normy ISO 7905. Przeanalizowano zalety i wady maszyny badawczej o takim wzorcu obciążenia testującego.
-
THERMOPLASTIC POLYMER MACHINE GUARDS – EXPLOITATION SAFETY
Publikacja -
Deep eutectic solvents with solid supports used in microextraction processes applied for endocrine-disrupting chemicals
PublikacjaThe determination of endocrine-disrupting chemicals (EDCs) has become one of the biggest challenges in Analytical Chemistry. Due to the low concentration of these compounds in different kinds of samples, it becomes necessary to employ efficient sample preparation methods and sensitive measurement techniques to achieve low limits of detection. This issue becomes even more struggling when the principles of the Green Analytical Chemistry...
-
Beata Bochentyn dr hab. inż.
Osoby -
Visual Content Learning in a Cognitive Vision Platform for Hazard Control (CVP-HC)
PublikacjaThis work is part of an effort for the development of a Cognitive Vision Platform for Hazard Control (CVP-HC) for applications in industrial workplaces, adaptable to a wide range of environments. The paper focuses on hazards resulted from the nonuse of personal protective equipment (PPE). Given the results of previous analysis of supervised techniques for the problem of classification of a few PPE (boots, hard hats, and gloves...
-
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning
PublikacjaIn this work, we investigate exemplar-free class incremental learning (CIL) with knowledge distillation (KD) as a regularization strategy, aiming to prevent forgetting. KDbased methods are successfully used in CIL, but they often struggle to regularize the model without access to exemplars of the training data from previous tasks. Our analysis reveals that this issue originates from substantial representation shifts in the teacher...
-
Pursuing the Deep-Learning-Based Classification of Exposed and Imagined Colors from EEG
PublikacjaEEG-based brain-computer interfaces are systems aiming to integrate disabled people into their environments. Nevertheless, their control could not be intuitive or depend on an active external stimulator to generate the responses for interacting with it. Targeting the second issue, a novel paradigm is explored in this paper, which depends on a passive stimulus by measuring the EEG responses of a subject to the primary colors (red,...
-
Effect of applied standard wood machining fluid on colour and chemical composition of the machined wood surface
PublikacjaAppropriate monitoring of wood machining processes is a key issue to ensure the expected quality of the processed wood, expected efficiency and minimize energy consumption of production processes. A new trend is the design of environmentally friendly machining fluids. In this paper, as a preliminary study in this field, the effect of applied standard wood machining fluid on changes in the colour and chemical composition of the...
-
Deep Learning Optimization for Edge Devices: Analysis of Training Quantization Parameters
PublikacjaThis 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...
-
A consensus-based approach to the distributed learning
Publikacja -
Prototype selection algorithms for distributed learning
Publikacja -
An agent-based framework for distributed learning
Publikacja -
Some aspects of blended-learning education
Publikacja -
Note on universal algoritms for learning theory
PublikacjaW 2001 Cucker i Smale zaproponowali nowe podejście do teorii uczenia się w oparciu o problematykę teorii aproksymacji.W 2005 i 2007 Bivev, Cohen, Dahmen, DeVore i Temlyakov opublikowali dwie prace z teorii uczenia się. W omawianej publikacji uogólniliśmy ich rezultaty jednocześnie upraszczając dowody.
-
Structure and Randomness in Planning and Reinforcement Learning
PublikacjaPlanning in large state spaces inevitably needs to balance the depth and breadth of the search. It has a crucial impact on the performance of a planner and most manage this interplay implicitly. We present a novel method \textit{Shoot Tree Search (STS)}, which makes it possible to control this trade-off more explicitly. Our algorithm can be understood as an interpolation between two celebrated search mechanisms: MCTS and random...