Wyszukiwarka
Filtry
wszystkich: 1192
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: artificial neural network, modelling,ship speed, engine fuel consumption
-
Optimisation of turbine shaft heating process under steam turbine run-up conditions
PublikacjaAn important operational task for thermal turbines during run-up and run-down is to keep the stresses in the structural elements at a right level. This applies not only to their instantaneous values, but also to the impact of them on the engine lifetime. The turbine shaft is a particularly important element. The distribution of stresses depends on geometric characteristics of the shaft and its specific locations. This means a groove manufactured...
-
PROPELLER INVESTIGATIONS BY MEANS OF NUMERICAL SIMULATION
PublikacjaThe analyses of hydroacoustics are of high interest at the moment due to strong impact of hydroacoustic phenomena on marine environment; the noises, generated e.g. by marine traffic, may be harmful for sea life. The analyses presented here are focused on one of main sources of noises generated by ships, i.e. cavitating propeller. The goal of the work is the assessment of the cavitation phenomenon, carried out with the standard...
-
CONTROL OF THE WAVES IN A TOWING TANK WITH THE USE OF A BLACK-BOX MODEL
PublikacjaThe paper describes an adaptive control system of the waves, implemented in the Ship Design and Research Centre, CTO S.A. The purpose of generating the waves in the towing tank is the modelling of the environmental conditions during hydrodynamic model tests. The tests are performed on scale models of towed or free running ships, anchored structures like oil rigs or bottommounted structures, e.g. wind turbines. In the towing tank...
-
Simplified approach to assess the dynamic response of a container ship subjected to bow slamming load
PublikacjaSimplified approach to assess the dynamic response of a container ship subjected to the bow slamming load, resulting in a transient vibratory response, typically called a 'whip-ping', is presented. The accurate numerical modelling is very complex and involves cou-pling of the hydrodynamic and structural solution at every time step, leading to huge com-putational and workload cost. Thus, the one-way coupling methodology is adopted,...
-
Architektury klasyfikatorów obrazów
PublikacjaKlasyfikacja obrazów jest zagadnieniem z dziedziny widzenia komputerowego. Polega na całościowej analizie obrazu i przypisaniu go do jednej lub wielu kategorii (klas). Współczesne rozwiązania tego problemu są w znacznej części realizowane z wykorzystaniem konwolucyjnych głębokich sieci neuronowych (convolutional neural network, CNN). W tym rozdziale opisano przełomowe architektury CNN oraz ewolucję state-of-the-art w klasyfikacji...
-
Adaptive Hounsfield Scale Windowing in Computed Tomography Liver Segmentation
PublikacjaIn computed tomography (CT) imaging, the Hounsfield Unit (HU) scale quantifies radiodensity, but its nonlinear nature across organs and lesions complicates machine learning analysis. This paper introduces an automated method for adaptive HU scale windowing in deep learning-based CT liver segmentation. We propose a new neural network layer that optimizes HU scale window parameters during training. Experiments on the Liver Tumor...
-
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...
-
Intelligent Autonomous Robot Supporting Small Pets in Domestic Environment
PublikacjaIn this contribution, we present preliminary results of the student project aimed at the development of an intelligent autonomous robot supporting small pets in a domestic environment. The main task of this robot is to protect a freely moving small pets against accidental stepping on them by home residents. For this purpose, we have developed the mobile robot which follows a pet and makes an alarm signal when a human is approaching....
-
Real-Time Basic Principles Nuclear Reactor Simulator Based on Client-Server Network Architecture with WebBrowser as User Interface
PublikacjaThe real-time simulator of nuclear reactor basic processes (neutron kinetics, heat generation and its exchange, poisoning and burn- ing up fuel) build in a network environment is presented in this paper. The client-server architecture was introduced, where the server is a pow- erful computing unit and the web browser application is a client for user interface purposes. The challenge was to develop an application running under the...
-
Improving Social Justice, Environmental Integrity, and Geopolitical Resilience in EU Electric Mobility Transition
PublikacjaWe recommend improving social justice, environmental integrity, and geopolitical resilience in electric mobility transition. To achieve this policy recommendation, we propose the following: (1) Increase societal acceptance and justice of climate policies by engaging local stakeholders; (2) Prioritize sustainable mobility practices over replacement of internal combustion engine vehicle (ICEV) with battery electric vehicle (BEV);...
-
Advancing Urban Transit: Gepard and CAR projects - Innovations in Trolleybus Technology
PublikacjaThe Gepard project in Gdynia, Poland, revolutionized the city's trolleybus network with the introduction of “Trolleybus 2.0” vehicles and an innovative charging system. “Trolleybus 2.0” vehicles combine features of traditional trolleybuses and electric buses boasting traction batteries for autonomous driving and dual legal approval. Statistical analysis of energy consumption informed the development of a hybrid charging concept,...
-
Multi-objective optimization of tool wear, surface roughness, and material removal rate in finishing honing processes using adaptive neural fuzzy inference systems
PublikacjaHoning processes are usually employed to manufacture combustion engine cylinders and hydraulic cylinders. A crosshatch pattern is obtained that favors the oil flow. In this paper, Adaptive Neural Fuzzy Inference System (ANFIS) models were obtained for tool wear, average roughness Ra, cylindricity and material removal rate in finish honing processes. In addition, multi-objective optimization with the desirability function method...
-
Poprawa jakości klasyfikacji głębokich sieci neuronowych poprzez optymalizację ich struktury i dwuetapowy proces uczenia
PublikacjaW pracy doktorskiej podjęto problem realizacji algorytmów głębokiego uczenia w warunkach deficytu danych uczących. Głównym celem było opracowanie podejścia optymalizującego strukturę sieci neuronowej oraz zastosowanie uczeniu dwuetapowym, w celu uzyskania mniejszych struktur, zachowując przy tym dokładności. Proponowane rozwiązania poddano testom na zadaniu klasyfikacji znamion skórnych na znamiona złośliwe i łagodne. W pierwszym...
-
Machine-learning-based precise cost-efficient NO2 sensor calibration by means of time series matching and global data pre-processing
PublikacjaAir pollution remains a considerable contemporary challenge affecting life quality, the environment, and economic well-being. It encompasses an array of pollutants—gases, particulate matter, biological molecules—emanating from sources such as vehicle emissions, industrial activities, agriculture, and natural occurrences. Nitrogen dioxide (NO2), a harmful gas, is particularly abundant in densely populated urban areas. Given its...
-
Comparison of Absorbed and Intercepted Fractions of PAR for Individual Trees Based on Radiative Transfer Model Simulations
PublikacjaThe fraction of absorbed photosynthetically active radiation (fAPAR) is a key parameter for estimating the gross primary production (GPP) of trees. For continuous, dense forest canopies, fAPAR, is often equated with the intercepted fraction, fIPAR. This assumption is not valid for individual trees in urban environments or parkland settings where the canopy is sparse and there are well-defined tree crown boundaries. Here, the distinction...
-
Smart Approach for Glioma Segmentation in Magnetic Resonance Imaging using Modified Convolutional Network Architecture (U-NET)
PublikacjaSegmentation of a brain tumor from magnetic resonance multimodal images is a challenging task in the field of medical imaging. The vast diversity in potential target regions, appearance and multifarious intensity threshold levels of various tumor types are few of the major factors that affect segmentation results. An accurate diagnosis and its treatment demand strict delineation of the tumor affected tissues. Herein, we focus on...
-
Multi-nodal PWR reactor model — Methodology proposition for power distribution coefficients calculation
PublikacjaIn the paper the multi-nodal Pressurized Water Reactor (PWR) model called Mann’s model is presented. This models is used for modelling purposes of the heat transfer from fuel to coolant in reactor core. The authors expand widely used in literature approach by defining additional coefficients for the heat transfer model. These parameters approximate the power generation distribution in the PWR reactor core according to the to the...
-
Application of gas chromatographic data and 2D molecular descriptors for accurate global mobility potential prediction
PublikacjaMobility is a key feature affecting the environmental fate, which is of particular importance in the case of persistent organic pollutants (POPs) and emerging pollutants (EPs). In this study, the global mobility classification artificial neural networks-based models employing GC retention times (RT) and 2D molecular descriptors were constructed and validated. The high usability of RT was confirmed based on the feature selection...
-
Endoscopic image processing and analysis of pistons' service failures of marine diesel engines
PublikacjaThe paper deals with diagnostic issues concerning endoscopic examinations of working spaces within marine diesel engines. In the beginning, endoscopy apparatus being on laboratory equipment of the Department of Ship Power Plants of Gdansk University of Technology has been characterized. The endoscopy considerations have been focused on theoretical bases of a digital image processing and especially - on the "Shadow" measurement...
-
Assessment of under power ed propulsion machinery in electrically driven small inland waterway passenger ships from classification society point of view
PublikacjaPaper presents short operat ional a nd engineering analysis of underpowered propulsion in small electrically propelled small inland passenger ships. There is evidence that in certain weather conditions the phenomena of added aerodynamic resistance of small water crafts may have seriou s influence on their speed and manoeuvrability. Existing regulations like class societies rules for ship classification and construction or EU Directive 2006/87/EC do...
-
Poroelastic Low Noise Road Surfaces
PublikacjaNoise is one of the most important problems related to road traffic. During the last decades, noise emitted by engine and powertrain of vehicles was greatly reduced and tyres became a clearly dominant noise source. The paper describes the concept of low noise poroelastic road surfaces that are composed with mineral and rubber aggregate bound by polyurethane resin. Those surfaces have a porous structure and are much more flexible...
-
Hardware-Software Implementation of Basic Principles Simulator of Nuclear Reactor Processes
PublikacjaThe paper presents implementation process of basic principle simulators of a nuclear reactor processes. Simulators are based on point-models of processes: kinetics of neutrons, heat generation and exchange, poisoning and burning-up nuclear fuel. Reference simulator was developed in MATLAB/Simulink without taking into account real-time operation. Second simulator was built using the toolbox xPC with hard real-time requirements....
-
Personal Branding and Brand Loyalty, Social Network Users Brand Identification: Polish-French Model
PublikacjaSocial network brand sites are increasingly attracting the attention of scientists and managers intrigued by their potential application for brand value creation. The aim of this research, based on a multinational sample, is to fill the gap in understanding how users choose among social networking sites as an act of brand identification. The authors of the paper point to the fact that creating a personal brand is becoming more...
-
Method of Forming Road Surface Replicas Using 3D Printing Technology
PublikacjaRolling resistance is a critical factor that influences vehicle energy consumption, emissions, and overall performance. It directly impacts fuel efficiency, tire longevity, and driving dynamics. Traditional rolling resistance tests are conducted on smooth steel drums, which fail to replicate real-world road surface textures, potentially skewing results. This article presents the process of designing surface replicas using 3D printing...
-
MODEL OF MULTILEVEL STOCHASTIC ANALYSIS OF ROAD SAFETY ON REGIONAL LEVEL
PublikacjaIn this paper multilevel approach to the issue of road safety level on the road network of European regions, classified as NUTS 2 in statistical databases of the European Union, has been presented. Following the pattern of many publications on road safety it has been assumed that the risk calculated as the number of death casualties in road accidents per 100,000 inhabitants of a given region has Poisson distribution. Therefore,...
-
Smooth start for strategry game development supported by XNA framework
PublikacjaTo attract young and casual game developers, Microsoft created a set of libraries oriented towards easier game development and end-product management. The aim of XNA Framework is to provide a unified software development environment for creating games for both PC's and dedicated platforms like XBOX consoles or mobile phones capable of 3D acceleration. The use of modern, object oriented languages available for the .NET platform...
-
MARSTRUCT benchmark study on nonlinear FE simulation of an experiment of an indenter impact with a ship side-shell structure
PublikacjaThis paper presents a benchmark study on collision simulations that was initiated by the MARSTRUCT Virtual Institute. The objective was to compare assumptions, finite element models, modelling techniques and experiences between established researchers within the field. Fifteen research groups world-wide participated in the study. An experiment involving a rigid indenter penetrating a ship-like side structure was used as the case...
-
Towards bees detection on images: study of different color models for neural networks
PublikacjaThis paper presents an approach to bee detection in videostreams using a neural network classifier. We describe the motivationfor our research and the methodology of data acquisition. The maincontribution to this work is a comparison of different color models usedas an input format for a feedforward convolutional architecture appliedto bee detection. The detection process has is based on a neural...
-
MACHINE LEARNING SYSTEM FOR AUTOMATED BLOOD SMEAR ANALYSIS
PublikacjaIn this paper the authors propose a decision support system for automatic blood smear analysis based on microscopic images. The images are pre-processed in order to remove irrelevant elements and to enhance the most important ones - the healthy blood cells (erythrocytes) and the pathologic (echinocytes). The separated blood cells are analyzed in terms of their most important features by the eigenfaces method. The features are the...
-
Driver fatigue detection method based on facial image analysis
PublikacjaNowadays, ensuring road safety is a crucial issue that demands continuous development and measures to minimize the risk of accidents. This paper presents the development of a driver fatigue detection method based on the analysis of facial images. To monitor the driver's condition in real-time, a video camera was used. The method of detection is based on analyzing facial features related to the mouth area and eyes, such as...
-
Glacial Landform Classification with Vision Transformer and Digital Elevation Model
PublikacjaClassification of glacial landforms is a task in geomorphology that has not been widely explored with deep neural network methods. This study uses Vision Transformer (ViT) architecture to classify glacial landforms using Digital Elevation Model (DEM) in three study sites: Elise Glacier in Svalbard, Norway; Gardno-Leba Plain and Lubawa Upland in Poland. In datasets each of those sites has different DEM resolutions and terrain types...
-
Instance segmentation of stack composed of unknown objects
PublikacjaThe article reviews neural network architectures designed for the segmentation task. It focuses mainly on instance segmentation of stacked objects. The main assumption is that segmentation is based on a color image with an additional depth layer. The paper also introduces the Stacked Bricks Dataset based on three cameras: RealSense L515, ZED2, and a synthetic one. Selected architectures: DeepLab, Mask RCNN, DEtection TRansformer,...
-
Deep learning for recommending subscription-limited documents
PublikacjaDocuments recommendation for a commercial, subscription-based online platform is important due to the difficulty in navigation through a large volume and diversity of content available to clients. However, this is also a challenging task due to the number of new documents added every day and decreasing relevance of older contents. To solve this problem, we propose deep neural network architecture that combines autoencoder with...
-
Towards Cancer Patients Classification Using Liquid Biopsy
PublikacjaLiquid biopsy is a useful, minimally invasive diagnostic and monitoring tool for cancer disease. Yet, developing accurate methods, given the potentially large number of input features, and usually small datasets size remains very challenging. Recently, a novel feature parameterization based on the RNA-sequenced platelet data which uses the biological knowledge from the Kyoto Encyclopedia of Genes and Genomes, combined with a classifier...
-
Photos of LEGO bricks
Dane BadawczeRandom photos of the following LEGO bricks: 2419, 2450, 3022, 3031, 4070, 30357, 41682, 44570, 47998, 52107, 54383, 54384, 64799, 87609, 93274, 99206, 99781. The bricks were placed on a white sheet of paper, the photos were taken by hand, using Huawei P20 PRO camera positioned above the bricks. The photos were taken with and without flashlight. The...
-
The harmonic distortion of voltage waveforms in the ship's electrical power system
Dane BadawczeThe dataset is a part of the research results on the quality of supply voltage on bus bars of the ship's electrical power system's main switchboard in different states of ship exploitation. The attached dataset contains the results of a harmonic distortion analysis expressed by the total harmonic distortion (THD) coefficient of voltage waveforms recorded...
-
Application of semi-Markov processes for evaluation of diesel engines reliability with regards to diagnostics
PublikacjaThe paper presents semi-Markov models of technical state transitions for diesel engines, useful for determination of their reliability, as a result of the conducted statistical empirical studies. Interpretation of technical states provided for this sort of engines refers to ship main engines, i.e. engines employed in propulsion systems of sea-going ships. The considerations recognize diesel engine as a diagnosed system (SDN), of...
-
Adaptive dynamic control allocation for dynamic positioning of marine vessel based on backstepping method and sequential quadratic programming
PublikacjaIt is generally assumed in dynamic positioning of over-actuated marine vessels that the control effectiveness matrix (input matrix) is known and constant, or, in case of fault information, it is estimated by the fault detection and diagnosis system. The purpose of the study is to develop the adaptive dynamic positioning control system for an over-actuated marine vessel in the presence of uncertainties and with emphasis on limited...
-
Intracranial hemorrhage detection in 3D computed tomography images using a bi-directional long short-term memory network-based modified genetic algorithm
PublikacjaIntroduction: Intracranial hemorrhage detection in 3D Computed Tomography (CT) brain images has gained more attention in the research community. The major issue to deal with the 3D CT brain images is scarce and hard to obtain the labelled data with better recognition results. Methods: To overcome the aforementioned problem, a new model has been implemented in this research manuscript. After acquiring the images from the Radiological...
-
Regulacja napięcia w sieci nN z rozproszonymi źródłami energii
PublikacjaPodłączanie rozproszonych źródeł energii do sieci energetycznych niskiego napięcia powoduje powstawanie problemów zmienności i niesymetrii napięcia, zwłaszcza w przypadku dużych odległości od transformatora zasilającego. W skrajnych przypadkach zachodzi konieczność redukcji mocy generowanej przez źródło podczas oddawaniu energii do sieci. Rozwiązaniem tego problemu jest zastosowanie energoelektronicznego regulatora napięcia składającego...
-
Algorithms for Ship Movement Prediction for Location Data Compression
PublikacjaDue to safety reasons, the movement of ships on the sea, especially near the coast should be tracked, recorded and stored. However, the amount of vessels which trajectories should be tracked by authorized institutions, often in real time, is usually huge. What is more, many sources of vessels position data (radars, AIS) produces thousands of records describing route of each tracked object, but lots of that records are correlated...
-
Automated hearing loss type classification based on pure tone audiometry data
PublikacjaHearing problems are commonly diagnosed with the use of tonal audiometry, which measures a patient’s hearing threshold in both air and bone conduction at various frequencies. Results of audiometry tests, usually represented graphically in the form of an audiogram, need to be interpreted by a professional audiologist in order to determine the exact type of hearing loss and administer proper treatment. However, the small number of...
-
A comparative analysis of the effectiveness of corporate bankruptcy prediction models based on financial ratios: Evidence from Colombia, 2008 to 2015
PublikacjaLogit and discriminant analyses have been used for corporate bankruptcy prediction in several studies since the last century. In recent years there have been dozens of studies comparing the several models available, including the ones mentioned above and also probit, artificial neural networks, support vector machines, among others. For the first time for Colombia, this paper presents a comparative analysis of the effectiveness...
-
Rapid Surrogate-Aided Multi-Criterial Optimization of Compact Microwave Passives Employing Machine Learning and ANNs
PublikacjaThis article introduces an innovative method for achieving low-cost and reliable multi-objective optimization (MO) of microwave passive circuits. The technique capitalizes on the attributes of surrogate models, specifically artificial neural networks (ANNs), and multi-resolution electromagnetic (EM) analysis. We integrate the search process into a machine learning (ML) framework, where each iteration produces multiple infill points...
-
Soft Sensor Application in Identification of the Activated Sludge Bulking Considering the Technological and Economical Aspects of Smart Systems Functioning
PublikacjaThe paper presented the methodology for the construction of a soft sensor used for activated sludge bulking identification. Devising such solutions fits within the current trends and development of a smart system and infrastructure within smart cities. In order to optimize the selection of the data-mining method depending on the data collected within a wastewater treatment plant (WWTP), a number of methods were considered, including:...
-
Prognozowanie wpływu drgań komunikacyjnych na budynki mieszkalne za pomocą sztucznych sieci neuronowych i maszyn wektorów wspierających
PublikacjaDrgania komunikacyjne mogą stanowić duże obciążenie eksploatacyjne budynku, powodując zarysowania i spękania tynków, odpadanie wypraw, zarysowania konstrukcji, pękanie elementów konstrukcji lub nawet zawalenie się budynku. Pomiary drgań na rzeczywistych konstrukcjach są pracochłonne i kosztowne, a co ważne nie w każdym przypadku są one uzasadnione. Celem pracy jest analiza autorskiego algorytmu, dzięki któremu z dużym prawdopodobieństwem...
-
Optimisation of cooperation of hybrid renewable energy sources with hydrogen energy storage toward the lowest net present cost
PublikacjaThe paper presents the results of a technical and economic analysis of the power supply for a model industrial facility based on intermittent renewable energy sources in the form of wind turbines and photovoltaic modules, supplemented with hydrogen energy storage. The adopted power supply strategy assumed the maximisation of self-consumption of self-produced electricity. Six variants were considered, including two with an energy...
-
Impact of the Manufacturing Sector on the Export Competitiveness of European Countries – a Spatial Panel Analysis
PublikacjaThe purpose of this paper is to determine how changes in the export competitiveness of the EU economy (measured by exports and net exports) depend on changes in the competitiveness of processing industries, on the basis of manufacturing data from 19 EU countries over years 1995-2009 and using a spatial panel data model. The determinants of export competitiveness are selected in the light of predictions from international trade...
-
Deep Video Multi-task Learning Towards Generalized Visual Scene Enhancement and Understanding
PublikacjaThe goal of this thesis was to develop efficient video multi-task convolutional architectures for a range of diverse vision tasks, on RGB scenes, leveraging i) task relationships and ii) motion information to improve multi-task performance. The approach we take starts from the integration of diverse tasks within video multi-task learning networks. We present the first two datasets of their kind in the existing literature, featuring...
-
Training of Deep Learning Models Using Synthetic Datasets
PublikacjaIn order to solve increasingly complex problems, the complexity of Deep Neural Networks also needs to be constantly increased, and therefore training such networks requires more and more data. Unfortunately, obtaining such massive real world training data to optimize neural networks parameters is a challenging and time-consuming task. To solve this problem, we propose an easy-touse and general approach to training deep learning...