Filtry
wszystkich: 979
-
Katalog
Wyniki wyszukiwania dla: machine learning optimization techniques
-
Nonlinear Control of a Doubly Fed Generator Supplied by a Current Source Inverter
PublikacjaNowadays, wind turbines based on a doubly fed induction generator (DFIG) are a commonly used solution in the wind industry. The standard converter topology used in these systems is the voltage source inverter (VSI). The use of reverse-blocking insulated gate bipolar transistor (RB-IGBT) in the current source inverter topology (CSI), which is an alternative topology, opens new possibilities of control methods. This paper presents...
-
Analysis of Organic Rankine Cycle efficiency and vapor generator heat transfer surface in function of the reduced pressure
PublikacjaIn the paper presented is analysis of the influence of reduced pressure on efficiency and heat transfer area of vapor generator of Organic Rankine Cycle (ORC) in case of subcritical and supercritical parameters of operation. Compared are two cases of subcritical and supercritical ORC featuring a similar arrangement of heat source supply and heat removal, that is featuring the same temperatures of working fluid before the turbine,...
-
Functional safety and reliability analysis methodoloogy for hazardous industrial plants
PublikacjaThis monograph is devoted to current problems and methods of the functional safety and reliability analyses of the programmable control and protection systems for industrial hazardous plants. The results of these analyses are useful in the process of safety management in life cycle, for effective reducing relevant risks at the design stage, and then controlling these risks during the operation of given installation. The methodology...
-
Losses and energy efficiency of drive motors and systems
PublikacjaLosses and energy efficiency of every drive motor must be presented as functions of physical quantities independent of losses in the motor. Such quantities are speed and load required by the machine or device driven by the motor, changing in the drive operating field. Speed and load of the motor decide of the instantaneous useful power of the motor and also in a differentiated way of kinds and values of losses occurring in the...
-
Is It Right To Predict Cutting Forces On The Basis Of Wood Density?
PublikacjaSeveral properties of wood can be correlated to wood density. It is widely accepted that the cutting power requirements are following this general assumption. Therefore, according to classic literature sources available for determination of the cutting power for both band- and circular- sawing machines, the cutting power requirements (and/or cutting forces) are computed as a function of the wood specific gravity SG. It was shown...
-
Losses and energy efficiency of drive motors and systems
PublikacjaLosses and energy efficiency of every drive motor must be presented as functions of physical quantities independent of losses in the motor. Such quantities are speed and load required by the machine or device driven by the motor, changing in the drive operating field. Speed and load of the motor decide of the instantaneous useful power of the motor and also in a differentiated way of kinds and values of losses occurring in the...
-
Nonlinear control of five phase induction motor with synchronized third harmonic flux injection
PublikacjaThe paper deals with the novel control system for five phase induction motor (IM) that enables the injection of the rotor flux 3rd harmonic component. Two multiscalar models are transformed from the 1-1 and 2-2 vector models developed in the 1st and 3rd harmonic planes. Based on the obtained multiscalar models the synthesis of dual multiscalar control is established. The obtained two multiscalar control systems can independently...
-
Joint workshop on Multimodal Interaction and Related Machine Learning Algorithms (now ICMI-MLMI)
Konferencje -
Uczenie maszynowe do samoorganizacji systemów rozproszonych w zastosowaniach gospodarczych
PublikacjaW pracy omówiono uczenie maszynowe do samoorganizacji systemów rozproszonych w zastosowaniach gospodarczych ze szczególnym uwzględnieniem sieci neuronowych do predykcji finansowych oraz szacowania ratingu przedsiębiorstw. Oprócz sieci neuronowych, istotną rolę w przygotowaniu i testowaniu informatycznych systemów finansowych może pełnić programowanie genetyczne. Z tego powodu omówiono uczenie maszynowe w aplikacjach konstruowanych...
-
Mariusz Deja dr hab. inż.
OsobyAdiunkt w Katedrze Technologii Maszyn i Automatyzacji Produkcji. Ukończył w 1993 roku studia wyższe magisterskie na Wydziale Mechanicznym Politechniki Gdańskiej, kierunek: Mechanika i Budowa Maszyn, specjalność: Projektowanie Procesów Technologicznych. Po ukończeniu studiów podjął pracę w Katedrze Technologii Maszyn i Automatyzacji Produkcji, a jego podstawowy obszar działalności naukowej związany był z technologią docierania...
-
Improved RSS-Based DoA Estimation Accuracy in Low-Profile ESPAR Antenna Using SVM Approach
PublikacjaIn this paper, we have shown how the overall performance of direction-of-arrival (DoA) estimation using lowprofile electronically steerable parasitic array radiator (ESPAR) antenna, which has been proposed for Internet of Things (IoT) applications, can significantly be improved when support vector machine (SVM) approach is applied. Because the SVM-based DoA estimation method used herein relies solely...
-
Improving automatic surveillance by sound analysis
PublikacjaAn automatic surveillance system, based on event detection in the video image can be improved by implementing algorithms for audio analysis. Dangerous or illegal actions are often connected with distinctive sound events like screams or sudden bursts of energy. A method for detection and classification of alarming sound events is presented. Detection is based on the observation of sudden changes in sound level in distinctive sub-bands...
-
Comparison of Tire Rolling Resistance Measuring Methods for Different Surfaces
PublikacjaThe rolling resistance of car tires is one of the most important parameters characterizing tires today. This resistance has a very significant contribution to the energy consumption of wheeled vehicles. The climate crisis has forced tire and car manufacturers to place great emphasis on the environmental impact of their products. Paradoxically, the development of electric vehicles has led to an even greater importance of rolling...
-
A Simple Neural Network for Collision Detection of Collaborative Robots
PublikacjaDue to the epidemic threat, more and more companies decide to automate their production lines. Given the lack of adequate security or space, in most cases, such companies cannot use classic production robots. The solution to this problem is the use of collaborative robots (cobots). However, the required equipment (force sensors) or alternative methods of detecting a threat to humans are usually quite expensive. The article presents...
-
Influence of dispersed phase content on the mechanical properties of electroless nanocomposite Ni-P/Si3N4 and hybrid Ni-P/Si3N4/graphite layers deposited on the AW-7075 alloy.
PublikacjaThe article presents the results of mechanical testing of Ni-P/Si3N4 nanocomposite and hybrid Ni-P/Si3N4/graphite coatings deposited on AW-7075 aluminum alloy using the chemical reduction method. In terms of mechanical testing, microhardness was measured, and surface roughness and adhesion of the coatings to the aluminum substrate were determined using the “scratch test” method. The surface morphology of the deposited layers was...
-
Faults and Fault Detection Methods in Electric Drives
PublikacjaThe chapter presents a review of faults and fault detection methods in electric drives. Typical faults are presented that arises for the induction motor, which is valued in the industry for its robust construction and cost-effective production. Moreover, a summary is presented of detectable faults in conjunction with the required physical information that allow a detection of specific faults. In order to address faults of a complete...
-
Behavioral state classification in epileptic brain using intracranial electrophysiology
PublikacjaOBJECTIVE: Automated behavioral state classification can benefit next generation implantable epilepsy devices. In this study we explored the feasibility of automated awake (AW) and slow wave sleep (SWS) classification using wide bandwidth intracranial EEG (iEEG) in patients undergoing evaluation for epilepsy surgery. APPROACH: Data from seven patients (age [Formula: see text], 4 women) who underwent intracranial depth electrode...
-
User Authentication by Eye Movement Features Employing SVM and XGBoost Classifiers
PublikacjaDevices capable of tracking the user’s gaze have become significantly more affordable over the past few years, thus broadening their application, including in-home and office computers and various customer service equipment. Although such devices have comparatively low operating frequencies and limited resolution, they are sufficient to supplement or replace classic input interfaces, such as the keyboard and mouse. The biometric...
-
Optimized Stress and Geometry Control of Spherical structures under Lateral Loadings
PublikacjaIn this paper, a numerical model of a double-layer spherical structure has been examined under lateral loadings. When the structure has been distorted due to loadings, the dislocated joints have been moved to their original positions utilizing the adjustment techniques based on the force method. Meanwhile, the members’ internal forces were kept in the desired domain. Optimization techniques were also implemented in order to minimalize...
-
Rapid design optimization of antennas using variable-fidelity EM models and adjoint sensitivities
PublikacjaPurpose – Development of techniques for expedited design optimization of complex and numerically expensive electromagnetic (EM) simulation models of antenna structures validated both numerically and experimentally. The paper aims to discuss these issues. Design/methodology/approach – The optimization task is performed using a technique that combines gradient search with adjoint sensitivities, trust region framework, as well as...
-
Spiral Search Grasshopper Features Selection with VGG19-ResNet50 for Remote Sensing Object Detection
PublikacjaRemote sensing object detection plays a major role in satellite imaging and is required in various scenarios such as transportation, forestry, and the ocean. Deep learning techniques provide efficient performance in remote sensing object detection. The existing techniques have the limitations of data imbalance, overfitting, and lower efficiency in detecting small objects. This research proposes the spiral search grasshopper (SSG)...
-
Blended Learning in Teaching Safety of Electrical Installations
PublikacjaBlended 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....
-
Screening evaluation of the quality of commercially available cigars, cigarillos, and bidis based on emission levels of selected terpenes and terpenoids
PublikacjaThe aim of the research was to verify the use of the solvent-free, non-destructive and easy to operate analytical method to study and compare the emissions of 16 representatives of terpenes and terpenoids from commercially available cigars, cigarillos and bidis − a potential screening analysis for the quality of combustible tobacco products. To assess the amount of organic compounds emitted to the gaseous phase from investigated...
-
Monolithic vs. Microservice Architecture: A Performance and Scalability Evaluation
PublikacjaContext. Since its proclamation in 2012, microservices-based architecture has gained widespread popularity due to its advantages, such as improved availability, fault tolerance, and horizontal scalability, as well as greater software development agility. Motivation. Yet, refactoring a monolith to microservices by smaller businesses and expecting that the migration will bring benefits similar to those reported by top global companies,...
-
Art and Healthcare - Healing Potential of Artistic Interventions in Medical Settings
PublikacjaThe stereotype of a machine for healing seems to be well rooted in common thinking and social perception of hospital buildings. The technological aspect of healthcare architecture has been influenced for several years by three major factors. The first is linked to the necessity of providing safety and security in the environment of elevated epidemiological risk. The second concerns the need for incorporating advanced technology...
-
Separation and determination of the group-type composition of modern base and lubricating oils with a wide range of polarity, especially emitted to the environment
PublikacjaLubricating oils are composed of base oils (>85% v/v) and enriching additives (<15% v/v). Three types of base oils may be distinguished: 1) traditional bases (obtained by low-volatile fractions from crude oil distillation refining), 2) synthetic bases (mainly poly-alpha-olefins, sometimes esters, especially succinic acid esters), 3) bases of natural origin (especially obtained from refined plant oils). The bases of natural origin...
-
Investigations on fracture in reinforced concrete beams in 3-point bending using continuous micro-CT scanning
PublikacjaThis study explores a fracture process in rectangular reinforced concrete (RC) beams subjected to quasi-static three-point bending. RC beams were short and long with included longitudinal reinforcement in the form of a steel or basalt bar. The ratio of the shear span to the effective depth was 1.5 and 0.75. The focus was on the load–deflection diagram and crack formation. Three-dimensional (3D) analyses of the size and distribution...
-
International Conference on Integration of Artificial Intelligence and Operations Research Techniques in Constraint Programming for Combinatorial Optimization Problems
Konferencje -
Supporting First Year Students Through Blended-Learning - Planning Effective Courses and Learner Support
PublikacjaHigher education has been actively encouraged to find more effective and flaxible delivery models to provide all students with access to good quality learning experiences. This paper describes students opinion about using e-learning techniques and their participation in courses provided in different ways as additional help and expectations of first year students.
-
EM-Driven Multi-Objective Design of Impedance Transformers By Pareto Ranking Bisection Algorithm
PublikacjaIn the paper, the problem of fast multi-objective optimization of compact impedance matching transformers is addressed by utilizing a novel Pareto ranking bisection algorithm. It approximates the Pareto front by dividing line segments connecting the designs found in the previous iterations, and refining the obtained candidate solutions by means of poll-type search involving Pareto ranking. The final Pareto set is obtained using...
-
Międzynarodowa Szkoła Letnia na temat algorytmów
WydarzeniaKatedra Algorytmów i Modelowania Systemów WETI PG organizuje 4. edycję Międzynarodowej Szkoły Letniej na temat algorytmów dla problemów optymalizacji dyskretnej i głębokiego uczenia
-
Semi-definite programming and quantum information
PublikacjaThis paper presents a comprehensive exploration of semi-definite programming (SDP) techniques within the context of quantum information. It examines the mathematical foundations of convex optimization, duality, and SDP formulations, providing a solid theoretical framework for addressing optimization challenges in quantum systems. By leveraging these tools, researchers and practitioners can characterize classical and quantum correlations,...
-
Akustyczna analiza parametrów ruchu drogowego z wykorzystaniem informacji o hałasie oraz uczenia maszynowego
PublikacjaCelem rozprawy było opracowanie akustycznej metody analizy parametrów ruchu drogowego. Zasada działania akustycznej analizy ruchu drogowego zapewnia pasywną metodę monitorowania natężenia ruchu. W pracy przedstawiono wybrane metody uczenia maszynowego w kontekście analizy dźwięku (ang.Machine Hearing). Przedstawiono metodologię klasyfikacji zdarzeń w ruchu drogowym z wykorzystaniem uczenia maszynowego. Przybliżono podstawowe...
-
Zero-Pole Approach in Microwave Passive Circuit Design
PublikacjaIn this thesis, optimization strategies for design of microwave passive structures including filters, couplers, antenna and impedance transformer and construction of various surroogate models utilized to fasten the design proces have been discussed. Direct and hybrid optimization methodologies including space mapping and multilevel algorithms combined with various surrogate models at different levels of fidelity have been utilized...
-
Aerodynamic shape optimization by variable-fidelity computational fluid dynamics models: a review of recent progress
PublikacjaA brief review of some recent variable-fidelity aerodynamic shape optimization methods is presented.We discuss three techniques that—by exploiting information embedded in low-fidelity computationalfluid dynamics (CFD) models—are able to yield a satisfactory design at a low computational cost, usu-ally corresponding to a few evaluations of the original, high-fidelity CFD model to be optimized. Thespecific techniques considered here...
-
Phong B. Dao D.Sc., Ph.D.
OsobyPhong B. Dao received the Engineer degree in Cybernetics in 2001, the M.Sc. degree in Instrumentation and Control in 2004, both from Hanoi University of Science and Technology in Vietnam, and the Ph.D. degree in Control Engineering in 2011 from the University of Twente, the Netherlands. In May 2020, Dr. Dao received the degree of D.Sc. (Habilitation) in Mechanical Engineering from the AGH University of Science and Technology, Poland....
-
Modelling and analysis of a synchronous generator in more electric aircraft power system using Synopsys/Saber simulator = Modelowanie i analiza generatora synchronicznego w systemie elektroenergetycznym nowoczesnego samolotu. Zastosowanie symulatora Synopsys/Saber
PublikacjaStreszczenie angielskie: A model for studying synchronous machine (SM) dynamic behaviour in more electric aircraft (MEA) power system is developed and implemented in the Synopys/Saber simulation environment. The modelling language MAST has been used to elaborate the SM model. The elaborated model exhibit a network with the same number of external terminals/ports as the real SM, and represents its behaviour in terms of the electrical...
-
Mechanical response of human thoracic spine ligaments under quasi-static loading: An experimental study
PublikacjaPurpose This study aimed to investigate the geometrical and mechanical properties of human thoracic spine ligaments subjected to uniaxial quasi-static tensile test. Methods Four human thoracic spines, obtained through a body donation program, were utilized for the study. The anterior longitudinal ligament (ALL), posterior longitudinal ligament (PLL), capsular ligament (CL), ligamenta flava (LF), and the interspinous ligament and...
-
Underground Water Level Prediction in Remote Sensing Images Using Improved Hydro Index Value with Ensemble Classifier
PublikacjaThe economic sustainability of aquifers across the world relies on accurate and rapid estimates of groundwater storage changes, but this becomes difficult due to the absence of insitu groundwater surveys in most areas. By closing the water balance, hydrologic remote sensing measures offer a possible method for quantifying changes in groundwater storage. However, it is uncertain to what extent remote sensing data can provide an...
-
Adrian Kastrau mgr inż.
Osoby -
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Database (PKDD and ECML combined from 2008)
Konferencje -
Tomasz Deręgowski dr inż.
OsobyTomasz Deręgowski jest adiunktem w Katedrze Informatyki w Zarządzaniu na Wydziale Zarządzania i Ekonomii Politechniki Gdańskiej, oraz kierownikiem Departamentu Inżynierii Platform Danych, pracującego nad rozwiązaniami Big Data, uczenia maszynowego i inżynierii danych w Nordea Bank AB - największej Skandynawskiej instytucji finansowej. Wcześniej pracował przez 15 lat w branży IT jako programista, lider zespołu, kierownik programu...
-
On deterministic procedures for low-cost multi-objective design optimization of miniaturized impedance matching transformers
PublikacjaPurpose This paper aims to investigate deterministic strategies for low-cost multi-objective design optimization of compact microwave structures, specifically, impedance matching transformers. The considered methods involve surrogate modeling techniques and variable-fidelity electromagnetic (EM) simulations. In contrary to majority of conventional approaches, they do not rely on population-based metaheuristics, which permit lowering...
-
Software Factory project for enhancement of student experiential learning
PublikacjaProviding opportunities for students to work on real-world software development projects for real customers is critical to prepare students for the IT industry. Such projects help students to understand what they will face in the industry and experience real customer interaction and challenges in collaborative work. To provide this opportunity in an academic environment and enhance the learning and multicultural teamwork experience,...
-
Julita Wasilczuk dr hab.
OsobyUrodzona 5 kwietnia 1965 roku w Gdańsku. W latach 1987–1991 odbyła studia na Wydziale Ekonomiki Transportu Uniwersytetu Gdańskiego (obecnie Wydział Ekonomii). Od 1993 roku zatrudniona na nowo utworzonym Wydziale Zarządzania i Ekonomii, Politechniki Gdańskiej, na stanowisku asystenta. W 1997 roku uzyskała stopień doktora nauk ekonomicznych na WZiE, a w 2006 doktora habilitowanego nauk ekonomicznych w dyscyplinie nauki o zarządzaniu,...
-
Multi-objective optimization of microextraction procedures
PublikacjaOptimization of extraction process requiresfinding acceptable conditions for many analytes and goodperformance in terms of process time or solvent consumption. These optimization criteria are oftencontradictory to each other, the performance of the system in given conditions is good for some criteriabut poor for others. Therefore, such problems require special assessment tools that allow to combinethese contradictory criteria into...
-
Spotkanie politechnicznego klubu sztucznej inteligencji
WydarzeniaPierwsze w tym roku akademickim spotkanie klubu AI Bay – Zatoka Sztucznej Inteligencji, który działa na Politechnice Gdańskiej odbędzie się w Gmachu B Wydziału Elektroniki, Telekomunikacji i Informatyki (Audytorium 1P).
-
PPAM 2022
WydarzeniaThe PPAM 2022 conference, will cover topics in parallel and distributed computing, including theory and applications, as well as applied mathematics.
-
Abdalraheem Ijjeh Ph.D. Eng.
OsobyThe primary research areas of interest are artificial intelligence (AI), machine learning, deep learning, and computer vision, as well as modeling physical phenomena (i.e., guided waves in composite laminates). The research interests described above are utilized for SHM and NDE applications, namely damage detection and localization in composite materials.
-
General concept of functional safety - standarisation and sector aspects
PublikacjaRozdział poświęcono koncepcji bezpieczeństwa funkcjonalnego. Bezpieczeństwo funkcjonalne jest częścią bezpieczeństwa całkowitego zależną od odpowiedniej odpowiedzi systemów sterowania i/lub zabezpieczeń na sygnały wejściowe podczas wystąpienia stanów nienormalnych maszyny, instalacji lub obiektu podwyższonego ryzyka. Koncepcja bezpieczeństwa funkcjonalnego przedstawiona w normie IEC 51508 stanowi przykład dobrej praktyki inżynierskiej...